Filters match written requirements, not verified compatibility or enforced permissions.
43 skills
Design & accessibility
Web Design Guidelines
Reviews UI source against Vercel's interface rules and returns findings with file and line references.
An agent with file-reading and an HTTP-fetch capability; the entrypoint names WebFetch.
Network access to raw.githubusercontent.com for the external guideline file on every review.
No skill-specific account, API key or executable runtime is specified. Host compatibility was not tested.
Scenario checked · Oct 18, 2026
One synthetic decision scenario, checked against a prewritten action rubric. Skill-conditioned 8/8; baseline 8/8. No measured advantage or executed workflow is claimed.
A prioritized React and Next.js review guide covering request waterfalls, bundle size, rendering and server behavior.
An agent able to read SKILL.md and the referenced rule files; no executable helper is invoked by the reviewed entrypoint.
Access to the target React/Next.js source. Building and measuring changes needs that project's own runtime and tooling.
No Vercel account or skill-specific API key is specified. Operating-system support depends on the host agent and project; not tested here.
Scenario checked · Oct 18, 2026
One synthetic decision scenario, checked against a prewritten action rubric. Skill-conditioned 7/7; baseline 7/7. No measured advantage or executed workflow is claimed.
Server changes need security review. Requirements describe access needs, not verified host compatibility.
Drafts and improves skills through example tasks, baseline comparisons, human feedback and trigger evaluations.
Drafting needs an agent and writable workspace; automated trigger evaluation additionally uses Python 3 and the claude CLI.
The description improver uses the session's Claude Code authentication; its source explicitly says no separate ANTHROPIC_API_KEY is needed.
The live viewer uses Python's standard library, a browser and a local TCP port; its port cleanup invokes lsof when available. Static HTML output is supported.
The trigger runner uses select() on subprocess pipes; native Windows operation was not verified. Shell examples include Unix commands.
Runtime probed · Oct 18, 2026
Viewer generation, mocked port cleanup and offline browser marker: 5 of 7 expectations passed. Two checks confirm one script-context injection issue at the pinned revision.
Evaluation text can escape the viewer script context. Requirements describe access needs, not verified host compatibility.
Guidance and helpers for PDF extraction, creation, page operations, OCR and form filling.
Python with task-specific libraries: pypdf for page/form operations, pdfplumber for extraction and ReportLab for creation.
Image/OCR examples use pdf2image and pytesseract; native Poppler/Tesseract setup must also be checked in the target environment. CLI examples include qpdf, Poppler tools and optional pdftk.
No dedicated API key is specified in the reviewed local helpers; access to the hosting agent and permitted use under Anthropic's terms are separate requirements.
Only the named helpers and dependency versions were probed on Windows; other workflows and platforms remain unverified.
Runtime probed · Oct 18, 2026
Form discovery/filling, invalid input and rasterization helpers: 7 of 9 expectations passed. Diagnostic value echo and non-form handling need attention.
Non-form PDF raises AttributeError. Requirements describe access needs, not verified host compatibility.
Creates and edits Word documents through JavaScript generation, XML editing and rendered-output checks.
Creation examples use Node.js and the docx npm package; reading examples use Pandoc.
Editing and verification use Python, ZIP tools, LibreOffice (soffice) and Poppler's pdftoppm; merge_runs.py imports defusedxml.
The optional restricted-socket workaround invokes gcc and LD_PRELOAD, a Linux-style path; native Windows compatibility is unverified.
No dedicated API key is specified for the reviewed local helpers. Hosted-agent access and Anthropic's reuse terms remain separate.
Runtime probed · Oct 18, 2026
Synthetic merge, formatting/revision boundaries, XML errors and ZIP traversal: 7 of 7 expectations passed. No rendered Word or LibreOffice workflow was tested.
A four-stage debugging method: investigate evidence, compare patterns, test a hypothesis and verify one focused fix.
A coding agent with access to relevant source, logs and the project's reproduction/test environment.
The optional find-polluter.sh helper needs Bash, Unix utilities and npm test; the core method is not restricted to JavaScript.
The workflow refers to the Superpowers TDD and verification skills. No skill-specific account or key is specified; project credentials may be required for a reproduction.
Host and operating-system compatibility depends on chosen tools; the Bash helper was not tested on Windows.
Scenario checked · Oct 18, 2026
One synthetic decision scenario, checked against a prewritten action rubric. Skill-conditioned 8/8; baseline 8/8. No measured advantage or executed workflow is claimed.
Diagnostic data needs boundaries. Requirements describe access needs, not verified host compatibility.
Guides an agent through a failing behavior test, the smallest passing change and subsequent refactoring.
A coding agent able to edit tests and implementation and run the target project's test suite.
A runnable test framework for the language in use. npm test and TypeScript are examples, not a universal runtime requirement.
No skill-specific API key, account or service is specified; host-agent and project requirements still apply.
The method is text-based, but shell and test compatibility were not verified on any operating system.
Scenario checked · Oct 18, 2026
One synthetic decision scenario, checked against a prewritten action rubric. Skill-conditioned 8/8; baseline 8/8. No measured advantage or executed workflow is claimed.
Delete-and-restart instruction. Requirements describe access needs, not verified host compatibility.
A discovery workflow for locating and installing agent skills through the Skills CLI.
The reviewed Skills CLI package declares Node.js >=22.20.0; npm/npx and Git/network access are needed for its documented installation flow.
No service account or API key is specified for public discovery. Private repositories need their own authorized access.
Agent-specific installation paths and Windows/macOS/Linux behavior were not tested.
Scenario checked · Oct 18, 2026
One synthetic decision scenario, checked against a prewritten action rubric. Skill-conditioned 8/8; baseline 8/8. No measured advantage or executed workflow is claimed.
An art-direction workflow that turns a brief into deliberate typography, palette, layout, and responsive implementation.
A coding agent with project-file access; the target application's own runtime/build tools for implementation.
A screenshot-capable browser is useful for visual critique. No dedicated package, account, or API key is required by the reviewed instruction file.
The guidance names multiple web stacks; integration with any particular framework was not tested.
Scenario checked · Oct 18, 2026
One synthetic decision scenario, checked against a prewritten action rubric. Skill-conditioned 8/8; baseline 8/8. No measured advantage or executed workflow is claimed.
Context can enter public output. Requirements describe access needs, not verified host compatibility.
Python Playwright guidance for local web-app inspection, screenshots, and scripted UI checks.
Python 3, the Python Playwright package and its Chromium browser for the documented examples.
The application must have its own installed dependencies and launch command; with_server.py itself uses Python standard-library modules.
No cloud account or API key is required for local tests; authenticated sites need separately authorized state.
Examples use Unix-style paths and shell syntax; adapt paths and verify child-process cleanup on Windows.
Scenario checked · Oct 18, 2026
One synthetic decision scenario, checked against a prewritten action rubric. Skill-conditioned 9/9; baseline 9/9. No measured advantage or executed workflow is claimed.
Shell authority and incomplete process isolation. Requirements describe access needs, not verified host compatibility.
A browser-automation discovery skill backed by a native CLI and version-specific core guidance.
The reviewed npm package is agent-browser 0.39.1 and declares Node.js >=24; installation obtains a platform-specific native binary.
Chrome/Chromium via CDP is the main browser path. The source provides Windows/macOS/Linux handling; pnpm >=11 is declared for package development.
No API key is required for local browsing. Cloud browser, remote service and account workflows need their own credentials.
Load the core guidance matching the installed CLI. The entry-point SKILL.md alone is a discovery stub.
Scenario checked · Oct 18, 2026
One synthetic decision scenario, checked against a prewritten action rubric. Skill-conditioned 8/8; baseline 8/8. No measured advantage or executed workflow is claimed.
A router to Remotion guidance for creating, previewing and rendering programmatic videos.
Node.js and Git for the reviewed project-creation flow; npm dependencies include Remotion and React.
A browser for Studio preview; rendering requires the Remotion runtime and its platform-specific dependencies.
No account or API key is specified for the basic local flow. Cloud rendering, maps, voices and external media can add service costs and credentials.
The reviewed package is 4.0.536; published CLI commands use @latest or unpinned npx.
Scenario checked · Oct 18, 2026
One synthetic decision scenario, checked against a prewritten action rubric. Skill-conditioned 8/8; baseline 8/8. No measured advantage or executed workflow is claimed.
Guidance for compound components, shared state and explicit component variants.
A React project and coding agent; no dedicated executable helper, account or API key is specified.
The React 19 API section applies only to React 19+. React 18 projects must skip those changes.
Project tests, type checking and build tools are needed to validate a refactor.
Scenario checked · Oct 18, 2026
One synthetic decision scenario, checked against a prewritten action rubric. Skill-conditioned 8/8; baseline 8/8. No measured advantage or executed workflow is claimed.
Version-sensitive refactors. Requirements describe access needs, not verified host compatibility.
A structured audit framework for crawlability, technical foundations, on-page content and evidence-based priorities.
A browser or fetch tool and permission to inspect target URLs. Rendered-page checks are needed for client-injected schema.
Search Console/analytics access is needed for property-specific performance evidence; public-page checks can proceed without it.
Optional paid crawling and search tools are listed. No universal API key, CLI runtime or integration is specified.
Scenario checked · Oct 18, 2026
One synthetic decision scenario, checked against a prewritten action rubric. Skill-conditioned 9/9; baseline 9/9. No measured advantage or executed workflow is claimed.
Private marketing and analytics context. Requirements describe access needs, not verified host compatibility.
A brief-first workflow for preserving voice, tightening scope and drafting supportable marketing claims.
A writing agent, an approved brief and support for factual claims.
Relevant product-marketing context may be read from local files; no dedicated runtime, paid tool, account or API key is required.
Scenario checked · Oct 18, 2026
One synthetic decision scenario, checked against a prewritten action rubric. Skill-conditioned 8/8; baseline 8/8. No measured advantage or executed workflow is claimed.
A workflow for delegating a bounded code review with requirements and an explicit Git range.
Git history with meaningful base/head commits, a review-capable subagent and the reviewer template.
No dedicated package or API key is specified. Host model access and project test tools remain separate.
Shell examples use Bash syntax; adapt to the host platform.
Scenario checked · Oct 18, 2026
One synthetic decision scenario, checked against a prewritten action rubric. Skill-conditioned 9/9; baseline 9/9. No measured advantage or executed workflow is claimed.
Wrong range omits the work. Requirements describe access needs, not verified host compatibility.
A risk-focused review method connecting code changes to history, affected callers, test coverage and explicit reports.
A local Git repository, baseline/head revisions, source-reading/search tools and report-file access.
The PR path uses gh and authorized GitHub access. Local commit review does not require an account or API key.
Examples use Bash tools such as grep, find and wc; host adaptation may be needed. Optional companion skills/subagents extend the review.
Scenario checked · Oct 18, 2026
One synthetic decision scenario, checked against a prewritten action rubric. Skill-conditioned 9/9; baseline 9/9. No measured advantage or executed workflow is claimed.
Checkout can disturb active work. Requirements describe access needs, not verified host compatibility.
A searchable local design-guidance library with optional persistent design-system output.
Python 3.x; reviewed search/core modules use standard-library imports and local CSV data. Keep the script/data layout intact.
Resolve the full installed script path; the documented CLAUDE_PLUGIN_ROOT path may need adaptation outside that plugin host.
No account or API key is required for local search. Generated implementation may introduce its own libraries or external assets.
Scenario checked · Oct 18, 2026
One synthetic decision scenario, checked against a prewritten action rubric. Skill-conditioned 8/8; baseline 8/8. No measured advantage or executed workflow is claimed.
Persistence and force overwrite. Requirements describe access needs, not verified host compatibility.
An opinionated design workflow using direction selection, browser inspection, screenshot critique and asset sourcing.
Full inspector workflow: Node.js 22+ and installed Chrome, Edge or Chromium. Browser discovery covers Windows, macOS and Linux paths.
The lint fallback and assets helper state Node 18+; no npm dependencies are required by the selected helpers.
Asset search needs outbound network access and uses public collections without API keys. Run from the intended project root.
Scenario checked · Oct 18, 2026
One synthetic decision scenario, checked against a prewritten action rubric. Skill-conditioned 8/8; baseline 8/8. No measured advantage or executed workflow is claimed.
Local serving and sensitive output. Requirements describe access needs, not verified host compatibility.
A presentation authoring and editing workflow with OOXML helpers, template guidance and rendered-slide review. Useful for editable decks, with substantial file-mutation and licensing caveats.
A host agent with file and shell access in an environment where the per-skill terms permit use. The reviewed license is proprietary, not the repository's Apache-licensed skill terms.
Node and pptxgenjs for new decks; Python and named XML/image packages for helpers; markitdown for text extraction; LibreOffice and PDF image tools for rendering. Upstream claims of preinstallation do not establish availability on your machine.
An approved template, usable fonts and source content. Local file work does not inherently require an account; the host service and license conditions are separate.
Source reviewed · Oct 19, 2026
Runtime not run because of the per-skill license boundary. Six manual source-review expectations: four met and two concerns identified in cleanup logic. No presentation was generated, edited or rendered.
Runtime not run: restrictive per-skill terms. Requirements describe access needs, not verified host compatibility.
A spreadsheet workflow for formula-based workbooks, formatting and recalculation checks. It makes useful distinctions between formulas and cached values, but verification can rewrite the workbook and does not prove the calculations are correct.
An agent with local file and shell access in an environment permitted by the proprietary per-skill terms; the adjacent Apache-licensed skills do not extend their license to this folder.
Python with openpyxl, pandas and markitdown as needed; LibreOffice/soffice for actual formula recalculation. Formula strings alone do not supply cached results.
Copies of the intended workbook and source values. Macro-enabled files, external links and newer Excel functions require separate compatibility checks; no Excel account is inherently required for the local helpers.
Source reviewed · Oct 19, 2026
Runtime not run because of the per-skill license boundary; LibreOffice was unavailable too. Six manual source-review expectations: five met, with an error-scanning concern retained. No workbook was recalculated.
Runtime not run: restrictive per-skill terms. Requirements describe access needs, not verified host compatibility.
A guide for building MCP servers with clear tool contracts, transport choices and evaluation questions. Its included evaluation runner needs extra care around parallel tool calls and diagnostic disclosure.
An agent able to read the skill and references; Node/TypeScript or Python and an appropriate MCP SDK for actual server development.
Access to the target API specification and a deliberately scoped test service. Real integrations may require service credentials and network access.
The supplied evaluation requirements name anthropic>=0.39.0 and mcp>=1.1.0. Its real model-based runner needs Anthropic API access; this account-free pass used sentinel imports and fake provider/transport objects.
Runtime probed · Oct 19, 2026
Six bounded checks: three met expectations and three exposed practical limits. The parser/logging functions ran locally; model and MCP interactions were fake. No API, account or generated server was tested.
Multiple tool requests are only partly handled. Requirements describe access needs, not verified host compatibility.
A Python animation toolkit with drawing helpers, frame assembly and a lightweight validator. Useful for small custom animations; the validator's ready result covers dimensions rather than complete upload readiness.
Python plus Pillow and numpy for the exercised frame and validator helpers; imageio for GIFBuilder.save. The requirements file also lists imageio-ffmpeg.
An agent with local file/code execution access and an output folder. No Slack account is needed to create or inspect local files; uploading requires a workspace and appropriate permission.
Synthetic or authorized source images and a visual reviewer. This pass used existing Pillow 12.3.0 and numpy 2.3.5; imageio was unavailable and no global dependency was installed.
Runtime probed · Oct 19, 2026
Eight local frame/validator checks: four met expectations and four exposed readiness or timing limits. The full GIF builder and Slack upload path were not run; all inputs were synthetic.
The ready result checks dimensions, not full readiness. Requirements describe access needs, not verified host compatibility.
A topic-based SQL review guide covering query plans, schema design, connection management and row-level security.
An agent able to read the topic files and the relevant SQL or schema.
A separately configured disposable Postgres database is needed for runtime validation; Supabase-specific auth.uid() examples need matching identity facilities.
No account is needed to read the guide. Live Supabase access, connection strings and privileges are separate dependencies.
Source reviewed · Oct 19, 2026
Completed 6 bounded source checks covering requirements, workflow boundaries and practical security concerns. No skill workflow was executed.
A tenant setting is not authentication. Requirements describe access needs, not verified host compatibility.
A structured review of marketing pages and lead forms, with prioritized fixes, copy alternatives and experiments to validate.
An agent with page copy or a permitted page snapshot and product/audience context.
Product-marketing context files are optional but explicitly checked. Signup and test-design tasks route to separate skills.
No helper runtime or account is required for source-guided review. Live analytics, session recordings and enrichment tools add separate accounts and permissions.
Source reviewed · Oct 19, 2026
Completed 6 bounded source checks covering requirements, workflow boundaries and practical security concerns. No skill workflow was executed.
Recommendations are test hypotheses. Requirements describe access needs, not verified host compatibility.
A Bash hook setup guide that blocks selected Git command text, with important gaps in command parsing and error handling.
Claude Code hook support and an operator-chosen project or global settings scope.
Bash, jq, grep and cat must be available to the hook. Git Bash could not start in this evaluation sandbox.
No account is required for testing JSON inputs; a live Git remote is not needed and was not used.
Source reviewed · Oct 19, 2026
Six source checks completed. Runtime attempted but blocked before Bash could initialize; zero hook cases executed. Literal-pattern and parser-failure concerns remain source findings.
Substring patterns are not a Git permission boundary. Requirements describe access needs, not verified host compatibility.
A requirements conversation with explicit scope choices, a design review and an optional local visual companion.
An instruction-capable agent and a user who can confirm design decisions. Subagents are optional for the builder check.
Optional visual companion: Node.js, a browser, a local listening port and Bash for the supplied launcher scripts. The text-only path needs none of those helper services.
No hosted account is required. The default visual branding can reference a remote image; disable it when appropriate and review mockup assets separately.
Runtime probed · Oct 19, 2026
Seven exported upstream helper cases passed. The optional loopback server integration was attempted but blocked by host permissions; no full brainstorming workflow or HTTP security pass is claimed.
Local previews still contain active web content. Requirements describe access needs, not verified host compatibility.
A prioritized React and Next.js review guide covering request waterfalls, bundle size, rendering and server behavior.
Useful for
Reviewing React or Next.js performance changes
Finding avoidable sequential requests and oversized client bundles
Requirements & tradeoffs
An agent able to read SKILL.md and the referenced rule files; no executable helper is invoked by the reviewed entrypoint.
Access to the target React/Next.js source. Building and measuring changes needs that project's own runtime and tooling.
No Vercel account or skill-specific API key is specified. Operating-system support depends on the host agent and project; not tested here.
Server changes need security review. The rules explicitly address authentication and cross-request data leaks. IonBin assessment: performance refactors touching server state or actions still need application-specific authorization and concurrency checks.
7 passed · 0 failed · 7 total · counts describe this record’s scope, not a shared benchmark.
Reviews UI source against Vercel's interface rules and returns findings with file and line references.
Useful for
Checking forms, focus, semantics and interaction details
A code-review pass before manual accessibility testing
Requirements & tradeoffs
An agent with file-reading and an HTTP-fetch capability; the entrypoint names WebFetch.
Network access to raw.githubusercontent.com for the external guideline file on every review.
No skill-specific account, API key or executable runtime is specified. Host compatibility was not tested.
Mutable remote instructions. The pinned skill fetches command.md from another repository's main branch. IonBin assessment: pinning this SKILL.md alone does not freeze the instructions actually applied; review the fetched rules as well.
8 passed · 0 failed · 8 total · counts describe this record’s scope, not a shared benchmark.
NeedsDrafting needs an agent and writable workspace; automated trigger evaluation additionally uses Python 3 and the claude CLI.
Runtime probedExplored · Oct 18, 2026
Anthropic
Drafts and improves skills through example tasks, baseline comparisons, human feedback and trigger evaluations.
Useful for
Turning a repeatable workflow into a skill
Comparing a skill revision with its baseline
Requirements & tradeoffs
Drafting needs an agent and writable workspace; automated trigger evaluation additionally uses Python 3 and the claude CLI.
The description improver uses the session's Claude Code authentication; its source explicitly says no separate ANTHROPIC_API_KEY is needed.
The live viewer uses Python's standard library, a browser and a local TCP port; its port cleanup invokes lsof when available. Static HTML output is supported.
The trigger runner uses select() on subprocess pipes; native Windows operation was not verified. Shell examples include Unix commands.
Evaluation text can escape the viewer script context. Observed in the bounded evaluation: At revision 34040c9c568585f6929bedeaad110ad08f079624, generate_html embeds json.dumps output directly in an inline script. Synthetic prompt text with a closing script tag executed a harmless in-memory marker in fresh offline Chrome. The benign control did not execute the marker. This is confirmed only for the pinned files and fixture; current upstream HEAD was not tested. Two failed expectations describe this one issue.
5 passed · 2 failed · 7 total · counts describe this record’s scope, not a shared benchmark.
NeedsPython with task-specific libraries: pypdf for page/form operations, pdfplumber for extraction and ReportLab for creation.
Runtime probedExplored · Oct 18, 2026
Anthropic
Guidance and helpers for PDF extraction, creation, page operations, OCR and form filling.
Useful for
Understanding a PDF-processing workflow
Evaluating extraction and form-filling requirements before adoption
Requirements & tradeoffs
Python with task-specific libraries: pypdf for page/form operations, pdfplumber for extraction and ReportLab for creation.
Image/OCR examples use pdf2image and pytesseract; native Poppler/Tesseract setup must also be checked in the target environment. CLI examples include qpdf, Poppler tools and optional pdftk.
No dedicated API key is specified in the reviewed local helpers; access to the hosting agent and permitted use under Anthropic's terms are separate requirements.
Only the named helpers and dependency versions were probed on Windows; other workflows and platforms remain unverified.
Non-form PDF raises AttributeError. Observed in the bounded evaluation: Calling get_field_info on a valid synthetic PDF without AcroForm fields raised AttributeError instead of returning an empty list. This failed an added robustness expectation; it does not imply form-filling failure on supported inputs.
7 passed · 2 failed · 9 total · counts describe this record’s scope, not a shared benchmark.
NeedsCreation examples use Node.js and the docx npm package; reading examples use Pandoc.
Runtime probedExplored · Oct 18, 2026
Anthropic
Creates and edits Word documents through JavaScript generation, XML editing and rendered-output checks.
Useful for
Planning Word document generation and editing
Understanding tracked-change and rendering pitfalls
Requirements & tradeoffs
Creation examples use Node.js and the docx npm package; reading examples use Pandoc.
Editing and verification use Python, ZIP tools, LibreOffice (soffice) and Poppler's pdftoppm; merge_runs.py imports defusedxml.
The optional restricted-socket workaround invokes gcc and LD_PRELOAD, a Linux-style path; native Windows compatibility is unverified.
No dedicated API key is specified for the reviewed local helpers. Hosted-agent access and Anthropic's reuse terms remain separate.
Restricted reuse terms. The document skill has proprietary terms with copying, derivative-work and distribution restrictions. This entry is a source-linked evaluation, not permission to fork or bundle it.
7 passed · 0 failed · 7 total · counts describe this record’s scope, not a shared benchmark.
NeedsA coding agent with access to relevant source, logs and the project's reproduction/test environment.
Scenario checkedExplored · Oct 18, 2026
Jesse Vincent / Superpowers
A four-stage debugging method: investigate evidence, compare patterns, test a hypothesis and verify one focused fix.
Useful for
Repeated fixes that fail to address a defect
Bugs crossing application, build or service boundaries
Requirements & tradeoffs
A coding agent with access to relevant source, logs and the project's reproduction/test environment.
The optional find-polluter.sh helper needs Bash, Unix utilities and npm test; the core method is not restricted to JavaScript.
The workflow refers to the Superpowers TDD and verification skills. No skill-specific account or key is specified; project credentials may be required for a reproduction.
Host and operating-system compatibility depends on chosen tools; the Bash helper was not tested on Windows.
Diagnostic data needs boundaries. The entrypoint encourages logging data across component boundaries. IonBin assessment: redact secrets and customer data, and scope diagnostics before using it against a live service.
8 passed · 0 failed · 8 total · counts describe this record’s scope, not a shared benchmark.
NeedsA coding agent able to edit tests and implementation and run the target project's test suite.
Scenario checkedExplored · Oct 18, 2026
Jesse Vincent / Superpowers
Guides an agent through a failing behavior test, the smallest passing change and subsequent refactoring.
Useful for
Behavior changes with an executable test environment
Regression fixes that need a reproducible failure
Requirements & tradeoffs
A coding agent able to edit tests and implementation and run the target project's test suite.
A runnable test framework for the language in use. npm test and TypeScript are examples, not a universal runtime requirement.
No skill-specific API key, account or service is specified; host-agent and project requirements still apply.
The method is text-based, but shell and test compatibility were not verified on any operating system.
Delete-and-restart instruction. The entrypoint instructs deleting implementation written before its failing test. IonBin assessment: reconcile that instruction with ownership and change-preservation rules before enabling it on existing or uncommitted work.
8 passed · 0 failed · 8 total · counts describe this record’s scope, not a shared benchmark.
NeedsNode.js/npm with npx on PATH, Bash for the bundled wrapper and a working browser runtime.
Runtime probedExplored · Oct 18, 2026
OpenAI catalog / Microsoft CLI
A terminal-driven browser workflow for navigation, form interaction, screenshots and UI debugging. This catalog version is a historical reference.
Useful for
Understanding a browser automation workflow
Comparing CLI browser tooling and its access requirements
Requirements & tradeoffs
Node.js/npm with npx on PATH, Bash for the bundled wrapper and a working browser runtime.
The wrapper resolves @playwright/cli through npx; package/browser setup and target-page access may require networking.
No skill-specific API key is specified. Private sites need their own authorized account/session; host-agent access is separate.
The Bash wrapper and Unix examples are not a verified native-PowerShell workflow.
Unpinned executable dependency. The wrapper uses npx --yes --package @playwright/cli without a package version. IonBin assessment: pin and review the CLI package separately; a pinned skill commit does not pin the executable it launches.
6 passed · 0 failed · 6 total · counts describe this record’s scope, not a shared benchmark.
A discovery workflow for locating and installing agent skills through the Skills CLI.
Useful for
Finding a specialist workflow
Comparing candidate upstreams before installing
Requirements & tradeoffs
The reviewed Skills CLI package declares Node.js >=22.20.0; npm/npx and Git/network access are needed for its documented installation flow.
No service account or API key is specified for public discovery. Private repositories need their own authorized access.
Agent-specific installation paths and Windows/macOS/Linux behavior were not tested.
Global, unattended installs. The skill suggests -g -y installation and unversioned npx. IonBin assessment: review the exact package and destination first; the source pin does not pin future downloaded code.
8 passed · 0 failed · 8 total · counts describe this record’s scope, not a shared benchmark.
NeedsA coding agent with project-file access; the target application's own runtime/build tools for implementation.
Scenario checkedExplored · Oct 18, 2026
Anthropic
An art-direction workflow that turns a brief into deliberate typography, palette, layout, and responsive implementation.
Useful for
Distinctive landing pages
Improving a UI against a specific brief
Requirements & tradeoffs
A coding agent with project-file access; the target application's own runtime/build tools for implementation.
A screenshot-capable browser is useful for visual critique. No dedicated package, account, or API key is required by the reviewed instruction file.
The guidance names multiple web stacks; integration with any particular framework was not tested.
Context can enter public output. The instructions encourage using remembered client preferences. IonBin assessment: use only context authorized for the project and keep confidential facts out of generated pages.
8 passed · 0 failed · 8 total · counts describe this record’s scope, not a shared benchmark.
NeedsPython 3, the Python Playwright package and its Chromium browser for the documented examples.
Scenario checkedUsed · Oct 18, 2026
Anthropic
Python Playwright guidance for local web-app inspection, screenshots, and scripted UI checks.
Useful for
Testing a local development server
Finding selectors after rendered-page inspection
Requirements & tradeoffs
Python 3, the Python Playwright package and its Chromium browser for the documented examples.
The application must have its own installed dependencies and launch command; with_server.py itself uses Python standard-library modules.
No cloud account or API key is required for local tests; authenticated sites need separately authorized state.
Examples use Unix-style paths and shell syntax; adapt paths and verify child-process cleanup on Windows.
Shell authority and incomplete process isolation. with_server.py executes the supplied server string with shell=True and inherits the environment. Use inspected commands, synthetic data and a restricted process environment.
9 passed · 0 failed · 9 total · counts describe this record’s scope, not a shared benchmark.
A browser-automation discovery skill backed by a native CLI and version-specific core guidance.
Useful for
Stateful browser workflows
Accessibility-tree inspection and scoped local QA
Requirements & tradeoffs
The reviewed npm package is agent-browser 0.39.1 and declares Node.js >=24; installation obtains a platform-specific native binary.
Chrome/Chromium via CDP is the main browser path. The source provides Windows/macOS/Linux handling; pnpm >=11 is declared for package development.
No API key is required for local browsing. Cloud browser, remote service and account workflows need their own credentials.
Load the core guidance matching the installed CLI. The entry-point SKILL.md alone is a discovery stub.
Browser session authority. A logged-in session can act with account authority. Core guidance recommends named sessions and treats page/WebMCP text as untrusted; those instructions are not a hard isolation boundary.
8 passed · 0 failed · 8 total · counts describe this record’s scope, not a shared benchmark.
Node.js and Git for the reviewed project-creation flow; npm dependencies include Remotion and React.
A browser for Studio preview; rendering requires the Remotion runtime and its platform-specific dependencies.
No account or API key is specified for the basic local flow. Cloud rendering, maps, voices and external media can add service costs and credentials.
The reviewed package is 4.0.536; published CLI commands use @latest or unpinned npx.
Mutable executable setup. Creation guidance invokes create-video@latest and npm i. Pin and review resolved dependencies before running in a workspace with secrets.
8 passed · 0 failed · 8 total · counts describe this record’s scope, not a shared benchmark.
Guidance for compound components, shared state and explicit component variants.
Useful for
Refactoring boolean-heavy component APIs
Reviewing React component architecture
Requirements & tradeoffs
A React project and coding agent; no dedicated executable helper, account or API key is specified.
The React 19 API section applies only to React 19+. React 18 projects must skip those changes.
Project tests, type checking and build tools are needed to validate a refactor.
Version-sensitive refactors. The source explicitly gates ref-as-prop and use() recommendations to React 19. Applying them to earlier runtimes can break compatibility.
8 passed · 0 failed · 8 total · counts describe this record’s scope, not a shared benchmark.
NeedsA browser or fetch tool and permission to inspect target URLs. Rendered-page checks are needed for client-injected schema.
Scenario checkedExplored · Oct 18, 2026
Corey Haines
A structured audit framework for crawlability, technical foundations, on-page content and evidence-based priorities.
Useful for
Scoping a website SEO audit
Separating observed issues from missing data
Requirements & tradeoffs
A browser or fetch tool and permission to inspect target URLs. Rendered-page checks are needed for client-injected schema.
Search Console/analytics access is needed for property-specific performance evidence; public-page checks can proceed without it.
Optional paid crawling and search tools are listed. No universal API key, CLI runtime or integration is specified.
Private marketing and analytics context. The skill reads local product-marketing context and may use account reports. IonBin assessment: minimize sensitive data and keep fetched pages as untrusted evidence.
9 passed · 0 failed · 9 total · counts describe this record’s scope, not a shared benchmark.
NeedsA writing agent, an approved brief and support for factual claims.
Scenario checkedExplored · Oct 18, 2026
Corey Haines
A brief-first workflow for preserving voice, tightening scope and drafting supportable marketing claims.
Useful for
Landing-page copy
Focused edits that preserve an existing voice
Requirements & tradeoffs
A writing agent, an approved brief and support for factual claims.
Relevant product-marketing context may be read from local files; no dedicated runtime, paid tool, account or API key is required.
Confidential customer evidence. Reviews, support tickets and other voice-of-customer sources may contain personal or private data. IonBin assessment: use authorized, minimized material.
8 passed · 0 failed · 8 total · counts describe this record’s scope, not a shared benchmark.
NeedsGit history with meaningful base/head commits, a review-capable subagent and the reviewer template.
Scenario checkedExplored · Oct 18, 2026
Jesse Vincent / obra
A workflow for delegating a bounded code review with requirements and an explicit Git range.
Useful for
Review before merge
Separating implementation from review context
Requirements & tradeoffs
Git history with meaningful base/head commits, a review-capable subagent and the reviewer template.
No dedicated package or API key is specified. Host model access and project test tools remain separate.
Shell examples use Bash syntax; adapt to the host platform.
Wrong range omits the work. HEAD~1 only covers the last commit and uncommitted edits are outside the explicit commit diff. Verify the chosen range against the actual change.
9 passed · 0 failed · 9 total · counts describe this record’s scope, not a shared benchmark.
NeedsA local Git repository, baseline/head revisions, source-reading/search tools and report-file access.
Scenario checkedExplored · Oct 18, 2026
Trail of Bits
A risk-focused review method connecting code changes to history, affected callers, test coverage and explicit reports.
Useful for
Security-sensitive diffs
Reviewing validation or authorization changes
Requirements & tradeoffs
A local Git repository, baseline/head revisions, source-reading/search tools and report-file access.
The PR path uses gh and authorized GitHub access. Local commit review does not require an account or API key.
Examples use Bash tools such as grep, find and wc; host adaptation may be needed. Optional companion skills/subagents extend the review.
Checkout can disturb active work. The methodology literally proposes git checkout for baseline and head. IonBin assessment: use read-only git show/diff or an isolated worktree when work is in progress.
9 passed · 0 failed · 9 total · counts describe this record’s scope, not a shared benchmark.
NeedsPython 3.x; reviewed search/core modules use standard-library imports and local CSV data. Keep the script/data layout intact.
Scenario checkedExplored · Oct 18, 2026
Next Level Builder
A searchable local design-guidance library with optional persistent design-system output.
Useful for
Finding targeted UI guidance
Building a documented visual system for a known stack
Requirements & tradeoffs
Python 3.x; reviewed search/core modules use standard-library imports and local CSV data. Keep the script/data layout intact.
Resolve the full installed script path; the documented CLAUDE_PLUGIN_ROOT path may need adaptation outside that plugin host.
No account or API key is required for local search. Generated implementation may introduce its own libraries or external assets.
Persistence and force overwrite. The current instructions explicitly require a target directory and approval before --force. The parser forwards those options to design_system.py; verify the destination before saving.
8 passed · 0 failed · 8 total · counts describe this record’s scope, not a shared benchmark.
NeedsFull inspector workflow: Node.js 22+ and installed Chrome, Edge or Chromium. Browser discovery covers Windows, macOS and Linux paths.
Scenario checkedExplored · Oct 18, 2026
leonxlnx
An opinionated design workflow using direction selection, browser inspection, screenshot critique and asset sourcing.
Useful for
Exploring a deliberate visual direction
Auditing page composition across viewport sizes
Requirements & tradeoffs
Full inspector workflow: Node.js 22+ and installed Chrome, Edge or Chromium. Browser discovery covers Windows, macOS and Linux paths.
The lint fallback and assets helper state Node 18+; no npm dependencies are required by the selected helpers.
Asset search needs outbound network access and uses public collections without API keys. Run from the intended project root.
Local serving and sensitive output. The inspector can serve the current project root over loopback and captures rendered pages. IonBin assessment: use an isolated fixture without secrets and inspect generated artifacts before sharing.
8 passed · 0 failed · 8 total · counts describe this record’s scope, not a shared benchmark.
NeedsA host agent with file and shell access in an environment where the per-skill terms permit use. The reviewed license is proprietary, not the repository's Apache-licensed skill terms.
Source reviewedExplored · Oct 19, 2026
Anthropic
A presentation authoring and editing workflow with OOXML helpers, template guidance and rendered-slide review. Useful for editable decks, with substantial file-mutation and licensing caveats.
Useful for
Editable presentation drafts and template-based updates
Separating content, package-structure and rendered-slide review
Requirements & tradeoffs
A host agent with file and shell access in an environment where the per-skill terms permit use. The reviewed license is proprietary, not the repository's Apache-licensed skill terms.
Node and pptxgenjs for new decks; Python and named XML/image packages for helpers; markitdown for text extraction; LibreOffice and PDF image tools for rendering. Upstream claims of preinstallation do not establish availability on your machine.
An approved template, usable fonts and source content. Local file work does not inherently require an account; the host service and license conditions are separate.
Runtime not run: restrictive per-skill terms. The pinned PPTX license labels all skill components subject to Anthropic-service agreements and adds restrictions on copying outside those services, derivatives and redistribution. This pass stopped at source review; no PPTX helper was imported or executed here.
4 passed · 2 failed · 6 total · counts describe this record’s scope, not a shared benchmark.
NeedsAn agent with local file and shell access in an environment permitted by the proprietary per-skill terms; the adjacent Apache-licensed skills do not extend their license to this folder.
Source reviewedExplored · Oct 19, 2026
Anthropic
A spreadsheet workflow for formula-based workbooks, formatting and recalculation checks. It makes useful distinctions between formulas and cached values, but verification can rewrite the workbook and does not prove the calculations are correct.
Useful for
Formula-based workbook drafts with explicit assumptions
Careful updates to existing spreadsheet templates
Requirements & tradeoffs
An agent with local file and shell access in an environment permitted by the proprietary per-skill terms; the adjacent Apache-licensed skills do not extend their license to this folder.
Python with openpyxl, pandas and markitdown as needed; LibreOffice/soffice for actual formula recalculation. Formula strings alone do not supply cached results.
Copies of the intended workbook and source values. Macro-enabled files, external links and newer Excel functions require separate compatibility checks; no Excel account is inherently required for the local helpers.
Runtime not run: restrictive per-skill terms. The pinned XLSX license subjects the skill to Anthropic-service agreements and adds restrictions on outside copies, derivatives and redistribution. No XLSX helper was imported or executed here. LibreOffice was also unavailable in this evaluation environment.
5 passed · 1 failed · 6 total · counts describe this record’s scope, not a shared benchmark.
NeedsAn agent able to read the skill and references; Node/TypeScript or Python and an appropriate MCP SDK for actual server development.
Runtime probedExplored · Oct 19, 2026
Anthropic
A guide for building MCP servers with clear tool contracts, transport choices and evaluation questions. Its included evaluation runner needs extra care around parallel tool calls and diagnostic disclosure.
Useful for
Developing or reviewing MCP tool contracts
Planning synthetic, stable evaluation questions before connecting live services
Requirements & tradeoffs
An agent able to read the skill and references; Node/TypeScript or Python and an appropriate MCP SDK for actual server development.
Access to the target API specification and a deliberately scoped test service. Real integrations may require service credentials and network access.
The supplied evaluation requirements name anthropic>=0.39.0 and mcp>=1.1.0. Its real model-based runner needs Anthropic API access; this account-free pass used sentinel imports and fake provider/transport objects.
Multiple tool requests are only partly handled. In the fake-provider probe, a response requested two tool calls but the evaluation loop executed and answered only the first. This is a control-flow result with synthetic objects, not a live API response test; adapt and test the runner before relying on parallel tool use.
3 passed · 3 failed · 6 total · counts describe this record’s scope, not a shared benchmark.
NeedsPython plus Pillow and numpy for the exercised frame and validator helpers; imageio for GIFBuilder.save. The requirements file also lists imageio-ffmpeg.
Runtime probedExplored · Oct 19, 2026
Anthropic
A Python animation toolkit with drawing helpers, frame assembly and a lightweight validator. Useful for small custom animations; the validator's ready result covers dimensions rather than complete upload readiness.
Useful for
Small custom reactions and process illustrations drawn from known shapes
Local animation drafts before an authorized upload or brand review
Requirements & tradeoffs
Python plus Pillow and numpy for the exercised frame and validator helpers; imageio for GIFBuilder.save. The requirements file also lists imageio-ffmpeg.
An agent with local file/code execution access and an output folder. No Slack account is needed to create or inspect local files; uploading requires a workspace and appropriate permission.
Synthetic or authorized source images and a visual reviewer. This pass used existing Pillow 12.3.0 and numpy 2.3.5; imageio was unavailable and no global dependency was installed.
The ready result checks dimensions, not full readiness. The validator accepted a PNG, a four-second emoji GIF and a 6,291,967-byte padded GIF. The latter exceeds its five-MiB warning threshold, which does not affect the boolean. These are failed IonBin readiness expectations, not claims that the helper promises strict enforcement or that Slack accepted the files. Check format, bytes and duration separately.
4 passed · 4 failed · 8 total · counts describe this record’s scope, not a shared benchmark.
NeedsAn agent that can load the instruction file and retain the interview context.
Source reviewedExplored · Oct 19, 2026
Matt Pocock
A decision interview that groups questions by dependency and makes unresolved assumptions visible before work starts.
Useful for
Scoping a feature with unresolved permission or delivery decisions
Testing a plan before turning it into implementation tasks
Requirements & tradeoffs
An agent that can load the instruction file and retain the interview context.
A user available to settle consequential decisions. Subagent and filesystem/search tools are needed only for delegated fact finding.
No skill-specific account, API key, language runtime or installation helper is specified.
Fact finding can widen tool access. The instructions delegate missing facts to a subagent. Limit that subagent to the relevant project and permitted sources; the skill does not enforce access controls.
5 passed · 0 failed · 5 total · counts describe this record’s scope, not a shared benchmark.
NeedsA host that exposes the current conversation and can write a text file.
Source reviewedExplored · Oct 19, 2026
Matt Pocock
A compact continuation note that points to existing artifacts, records the next focus and asks the agent to redact sensitive content.
Useful for
Continuing a multi-session task
Passing a bounded review to a fresh agent
Requirements & tradeoffs
A host that exposes the current conversation and can write a text file.
Access to the existing artifacts the handoff references; receiving agent access is a separate requirement.
No external service or account is required by the entrypoint.
Redaction is an instruction, not a control. The guide tells the model to remove secrets and personal information but has no scanner or validator. Review a handoff before moving it to another agent or storage system.
5 passed · 0 failed · 5 total · counts describe this record’s scope, not a shared benchmark.
A topic-based SQL review guide covering query plans, schema design, connection management and row-level security.
Useful for
Reviewing Postgres SQL, schema changes and RLS assumptions
Planning query diagnostics before making performance changes
Requirements & tradeoffs
An agent able to read the topic files and the relevant SQL or schema.
A separately configured disposable Postgres database is needed for runtime validation; Supabase-specific auth.uid() examples need matching identity facilities.
No account is needed to read the guide. Live Supabase access, connection strings and privileges are separate dependencies.
A tenant setting is not authentication. The generic policy example reads app.current_user_id. If a caller can choose or overwrite that value, the example alone does not prove tenant isolation. Test trusted identity setup and both allowed and denied rows under the actual application role.
6 passed · 0 failed · 6 total · counts describe this record’s scope, not a shared benchmark.
NeedsAn agent with page copy or a permitted page snapshot and product/audience context.
Source reviewedExplored · Oct 19, 2026
Corey Haines
A structured review of marketing pages and lead forms, with prioritized fixes, copy alternatives and experiments to validate.
Useful for
Auditing a marketing page against a specific visitor intent
Reviewing lead/contact forms and planning measurable experiments
Requirements & tradeoffs
An agent with page copy or a permitted page snapshot and product/audience context.
Product-marketing context files are optional but explicitly checked. Signup and test-design tasks route to separate skills.
No helper runtime or account is required for source-guided review. Live analytics, session recordings and enrichment tools add separate accounts and permissions.
Recommendations are test hypotheses. The guide suggests prioritization and experiments, and its form reference includes numerical rules of thumb. Those numbers are source assertions, not results from this review or a forecast for your site.
6 passed · 0 failed · 6 total · counts describe this record’s scope, not a shared benchmark.
NeedsClaude Code hook support and an operator-chosen project or global settings scope.
Source reviewedExplored · Oct 19, 2026
Matt Pocock
A Bash hook setup guide that blocks selected Git command text, with important gaps in command parsing and error handling.
Useful for
Adding a narrow warning before selected Bash Git operations
Reviewing the limits of a hook before installing it
Requirements & tradeoffs
Claude Code hook support and an operator-chosen project or global settings scope.
Bash, jq, grep and cat must be available to the hook. Git Bash could not start in this evaluation sandbox.
No account is required for testing JSON inputs; a live Git remote is not needed and was not used.
Substring patterns are not a Git permission boundary. The script searches for literal phrases such as git push. By source inspection, global Git options, tabs or a quoted executable can avoid those exact phrases, while a harmless quoted description can match them. Treat this as a convenience warning, not repository protection.
6 passed · 0 failed · 6 total · counts describe this record’s scope, not a shared benchmark.
NeedsAn instruction-capable agent and a user who can confirm design decisions. Subagents are optional for the builder check.
Runtime probedExplored · Oct 19, 2026
Superpowers
A requirements conversation with explicit scope choices, a design review and an optional local visual companion.
Useful for
Clarifying a substantial feature or design request
Discussing layout alternatives through an optional local preview
Requirements & tradeoffs
An instruction-capable agent and a user who can confirm design decisions. Subagents are optional for the builder check.
Optional visual companion: Node.js, a browser, a local listening port and Bash for the supplied launcher scripts. The text-only path needs none of those helper services.
No hosted account is required. The default visual branding can reference a remote image; disable it when appropriate and review mockup assets separately.
Local previews still contain active web content. The server inserts supplied HTML without sanitizing it and serves helper JavaScript. Its frame-ancestors policy is not an outbound-content sandbox. Use reviewed synthetic content, avoid secrets and do not load untrusted markup as a preview.
7 passed · 0 failed · 7 total · counts describe this record’s scope, not a shared benchmark.
NeedsAn agent that can load the skill folder, including its examples/ guide files.
Source reviewedExplored · Oct 19, 2026
Anthropic
A small router that picks a format guide for status reports, newsletters, FAQs and other internal updates.
Useful for
Recurring internal updates that should follow one structure
Teams willing to adapt the bundled format guides
Requirements & tradeoffs
An agent that can load the skill folder, including its examples/ guide files.
No account or script is needed. Source material for the update comes from you.
The format guides are examples, not your house style. The entrypoint defers formatting and tone to bundled example guides. Review and edit those guides before relying on them, or the drafts will follow someone else's conventions.
4 passed · 0 failed · 4 total · counts describe this record’s scope, not a shared benchmark.
Agendas that need owners, timeboxes and links to sources
Requirements & tradeoffs
Codex with the Notion MCP server connected over OAuth (the skill gives Codex-specific setup commands).
A Notion workspace with the relevant pages shared with the connection.
It writes to Notion. The workflow creates pages and can update them and add tasks. Use a draft area and check the result before sharing it with attendees.
4 passed · 0 failed · 4 total · counts describe this record’s scope, not a shared benchmark.
NeedsA Linear workspace and the Linear MCP server connected over OAuth. The setup steps are Codex-specific.
Source reviewedExplored · Oct 19, 2026
OpenAI
A step-by-step routine for working in Linear through its MCP server: read first, then create or update, then summarize.
Useful for
Issue triage and status reports in Linear
Agents that should read before they write
Requirements & tradeoffs
A Linear workspace and the Linear MCP server connected over OAuth. The setup steps are Codex-specific.
Access to the teams and projects involved.
Bulk changes can touch many issues. Routines such as smart labeling and workload balancing can change many issues at once. The skill says to explain grouping first; still approve each batch.
4 passed · 0 failed · 4 total · counts describe this record’s scope, not a shared benchmark.
NeedsPython with the openai package, and an OPENAI_API_KEY in the environment.
Source reviewedExplored · Oct 19, 2026
OpenAI
Transcribes audio through OpenAI's API with a bundled Python script, with optional speaker labels.
Useful for
Transcripts of interviews and meetings
Speaker-labelled transcripts when you have reference clips
Requirements & tradeoffs
Python with the openai package, and an OPENAI_API_KEY in the environment.
Audio files on the machine the agent can reach.
Recordings leave your machine. The script uploads audio to OpenAI. Confirm that everyone recorded agreed to it and that the content may be processed by a third party.
4 passed · 0 failed · 4 total · counts describe this record’s scope, not a shared benchmark.
NeedsAn agent with read access to the repository, and a person who can answer questions about deployment and users.
Source reviewedExplored · Oct 19, 2026
OpenAI
Writes a repository-specific threat model: trust boundaries, assets, abuse paths and mitigations tied to evidence in the code.
Useful for
Pre-launch review of apps that handle data or credentials
Focused threat lists tied to the actual code
Requirements & tradeoffs
An agent with read access to the repository, and a person who can answer questions about deployment and users.
No account or service is needed to read the code.
Not a security assurance. The output is a model built from code reading and your answers. It doesn't test anything. Treat high-priority items as things to verify, not as findings.
4 passed · 0 failed · 4 total · counts describe this record’s scope, not a shared benchmark.
NeedsThe Google Ads MCP server (search, list_accessible_customers, get_resource_metadata), configured with Google Ads API access.
Source reviewedExplored · Oct 19, 2026
Google
Diagnoses drops in Google Ads conversions, leads and impression share with GAQL queries over Google's read-only Ads MCP server.
Useful for
First-pass diagnosis of Google Ads performance drops
Impression-share checks for budget and rank limits
Requirements & tradeoffs
The Google Ads MCP server (search, list_accessible_customers, get_resource_metadata), configured with Google Ads API access.
Access to the client accounts being diagnosed.
Recommendations still need judgment. The skill maps high budget-lost or rank-lost impression share to raising budgets or improving bids and quality. Check margins and goals before spending more.
5 passed · 0 failed · 5 total · counts describe this record’s scope, not a shared benchmark.
NeedsA Google Cloud project with the Analytics Data API enabled, the gcloud CLI, and access to the GA4 property.
Source reviewedExplored · Oct 19, 2026
Google
Sets up and runs Google Analytics 4 reports through the Data API v1beta, with read-only scopes and a field compatibility check.
Useful for
Scripted GA4 reports
Checking metric and dimension combinations before building a report
Requirements & tradeoffs
A Google Cloud project with the Analytics Data API enabled, the gcloud CLI, and access to the GA4 property.
A language runtime and client library (Python, Node.js, Java, PHP, Go, .NET or Ruby).
Local credentials are broader than Analytics. The login command also requests the cloud-platform scope. Use a dedicated project and account where possible, and revoke the credentials when finished.
5 passed · 0 failed · 5 total · counts describe this record’s scope, not a shared benchmark.
NeedsAn agent with browser tooling, ideally Chrome DevTools MCP, for traces and network data.
Source reviewedExplored · Oct 19, 2026
Cloudflare
A five-phase page-speed audit using Chrome DevTools MCP traces, network analysis, an accessibility snapshot and a codebase check.
Useful for
Page-speed audits with measured evidence
Linking trace findings to build configuration
Requirements & tradeoffs
An agent with browser tooling, ideally Chrome DevTools MCP, for traces and network data.
Codebase access for the optional fifth phase.
Lab numbers are not user experience. Traces come from one controlled load. Treat the thresholds and estimates as guides and verify them with field data before claiming gains.
4 passed · 0 failed · 4 total · counts describe this record’s scope, not a shared benchmark.
Needsuv for the bundled scanner script, and an agent with Read, Grep, Glob and Bash.
Source reviewedExplored · Oct 19, 2026
Sentry
Reviews an agent skill before you install it, with a static scan script plus checks for injection, risky scripts, permissions and supply-chain links.
Useful for
Pre-install review of third-party skills
Spotting skills that change agent configuration
Requirements & tradeoffs
uv for the bundled scanner script, and an agent with Read, Grep, Glob and Bash.
A local copy of the skill to scan.
The scanner runs code on your machine. Scanning uses a bundled script and requests Bash. Review the script or run it in a sandbox before scanning untrusted material.
4 passed · 0 failed · 4 total · counts describe this record’s scope, not a shared benchmark.
NeedsAn agent that can read the bundled reference files.
Source reviewedExplored · Oct 19, 2026
Sentry
Improves prompts against a small eval set: define success first, try a few candidate rewrites, keep the one that wins on held-out cases.
Useful for
Prompts used repeatedly where quality can be defined
Moving a prompt between model families
Requirements & tradeoffs
An agent that can read the bundled reference files.
Example inputs and success criteria, or time to build a small eval set.
Eval data can contain personal details. Test cases built from real tickets or emails can carry personal data into prompts and logs. Anonymize them first.
4 passed · 0 failed · 4 total · counts describe this record’s scope, not a shared benchmark.
A scoped personal access token for CI or agents, per the skill.
SQL runs with real privileges. The skill uses execute_sql and CLI commands that change schemas and policies. Point it at a development project and review migrations before they reach production.
5 passed · 0 failed · 5 total · counts describe this record’s scope, not a shared benchmark.
NeedsThe Microsoft Learn MCP server at learn.microsoft.com/api/mcp, or Node.js for the mslearn CLI.
Source reviewedExplored · Oct 19, 2026
Microsoft
Answers questions about Microsoft products from live Microsoft Learn documentation, through the Learn MCP server or the mslearn CLI.
Useful for
Current answers about Microsoft products with an official source
Setup steps and limits from Microsoft Learn
Requirements & tradeoffs
The Microsoft Learn MCP server at learn.microsoft.com/api/mcp, or Node.js for the mslearn CLI.
No Microsoft account is needed to search public documentation.
The CLI fallback runs a downloaded package. Running npx @microsoft/learn-cli fetches and runs code from npm. Pin a version or install it deliberately rather than running it ad hoc.
4 passed · 0 failed · 4 total · counts describe this record’s scope, not a shared benchmark.
Try a task such as “design” or remove a requirements filter.
Side by side
Compare the tradeoffs.
Compare task fit, setup, observed results and unknowns. Test counts describe each record’s own scope; they are not a shared benchmark score or a “safe to install” verdict.
Swipe or scroll sideways to see every selection →
Selected skills compared by fit, requirements, access, concerns and evidence
Behind the review
Check the evidence.
Sources, runtime checks, permissions and unknowns—recorded separately.
Read the collection as Markdown or JSON. These are review records, not installable skills.