# Skill Creator: requirements, concerns and evaluation

> Drafts and improves skills through example tasks, baseline comparisons, human feedback and trigger evaluations.

Canonical page: https://ionbin.com/skills/anthropic-skill-creator/
Agent guide: https://ionbin.com/llms.txt

This is a readable version of the published page. Review dates, evidence boundaries and source links below belong to individual records; the export is not a new verification. Examples are reference material, not instructions to execute.

Runtime probedSkill authoringExplored

Anthropic / skills/skill-creator/SKILL.md

## Skill Creator

Drafts and improves skills through example tasks, baseline comparisons, human feedback and trigger evaluations.

[Read upstream skill](https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/skills/skill-creator/SKILL.md)[GitHub repository](https://github.com/anthropics/skills)[Add to comparison](https://ionbin.com/skills/?compare=anthropic-skill-creator#directory)

Runtime probed · reviewed Oct 18, 2026 · A helper or bounded runtime behavior was probed. This does not establish model task effectiveness or comprehensive security.

The Ion perspective

### The five-point review

Judgment, not a score. Documentation checked 2026-10-18.

**Value**: Drafts and improves skills through example tasks, baseline comparisons, human feedback and trigger evaluations.

**Differentiation**: Turning a repeatable workflow into a skill; Comparing a skill revision with its baseline. This describes the reviewed fit, not an exclusive capability.

**Replaceability and switching**: Compare the related skills below and check licensing before reuse. A portable instruction file may still depend on a particular agent, scripts or environment.

**Ease and technical aptitude**: 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](https://ionbin.com/wiki/questions/what-is-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.

**Interoperability and portability**: Create skill files, evaluation outputs and temporary .claude/commands entries. Run [Claude](https://ionbin.com/tools/claude/) subprocesses that inherit the surrounding environment and can use the configured [Claude](https://ionbin.com/tools/claude/) service. Serve evaluation artifacts locally; live-viewer startup can terminate processes on its chosen port. The host controls execution and connectors. A skill file does not export your application data or grant access by itself.

Connections: [MCP connections](https://ionbin.com/wiki/concepts/mcp/) · [APIs](https://ionbin.com/wiki/concepts/api/) · [Portability and vendor lock-in](https://ionbin.com/wiki/questions/how-to-avoid-ai-vendor-lock-in/).

01 / Task fit

### Where it may help.

These are intended uses indicated by the upstream material. They are not measured outcomes.

- Turning a repeatable workflow into a skill

- Comparing a skill revision with its baseline

02 / Setup & access

### What it asks of your environment.

#### Requirements

- 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](https://ionbin.com/wiki/questions/what-is-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.

#### Permissions & data access

- Create skill files, evaluation outputs and temporary .claude/commands entries.

- Run [Claude](https://ionbin.com/tools/claude/) subprocesses that inherit the surrounding environment and can use the configured [Claude](https://ionbin.com/tools/claude/) service.

- Serve evaluation artifacts locally; live-viewer startup can terminate processes on its chosen port.

**Check the host, too.**

Instructions alone do not enforce a sandbox. The agent host, connected tools and approvals determine what the skill can actually read, change or send.

03 / Things to check

### Security concerns & practical limits.

These concerns follow from the reviewed sources. They describe possible exposure or required review; they are not confirmed vulnerabilities.

Higher attention

#### 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.

Higher attention

#### Viewer can terminate another process

generate_review.py calls lsof and sends SIGTERM to processes listening on its selected port before starting the viewer (default 3117). IonBin assessment: use static output or inspect the port before live mode.

Review before use

#### Evaluation data and consumption

The improver sends skill content and evaluation examples to claude -p; repeated runs use the configured [Claude](https://ionbin.com/tools/claude/) account. The viewer embeds outputs. IonBin assessment: use approved sample data and review cost and artifact exposure.

#### Limits and nuances

- Selected runner, improver and viewer code paths reviewed; packaging, all graders and the full optimization loop were not audited.

- A good score on a small task set does not establish general reliability or resistance to hostile inputs.

04 / Review record

### What we checked. What’s still open.

Runtime probed

#### Recorded review scope

- SKILL.md drafting, baseline-evaluation and description-optimization sections

- scripts/run_eval.py subprocess launch, environment and pipe handling

- scripts/improve_description.py [Claude](https://ionbin.com/tools/claude/) subprocess and prompt construction

- eval-viewer/generate_review.py artifact embedding, port cleanup and localhost server paths

- LICENSE.txt

- Bounded evaluation; exact operations, counts, environment and limitations in the linked public report

Not verified

#### Not tested or established

- No effectiveness benchmark or security certification

- Transitive dependencies, current advisories and host-agent permission controls not audited

- No generated-skill quality or trigger-rate measurements

- No [Claude](https://ionbin.com/tools/claude/) subprocess, live model, API credential, optimization loop or generated-skill effectiveness evaluation

- Port-cleanup lsof/os.kill effects were mocked; no real process was terminated

**Review date**: Oct 18, 2026

**Source revision**: `34040c9c568585f6929bedeaad110ad08f079624`

**Our relationship**: **Explored.** Investigated through the recorded review. No use or replication is claimed.

Upstream content can change after review. A repository revision identifies source scope; it does not prove that every script, dependency or runtime behavior was tested. [How freshness is handled](https://ionbin.com/skills/methodology/#freshness).

Recorded evaluation / Helper probe

### Results with their limits attached.

Completed within scopeOct 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.

**Passed**: 5

**Failed**: 2

**Total recorded**: 7

These counts refer to the cases in this report. They are not a benchmark against other skills. A helper probe does not measure model task effectiveness or establish comprehensive security.

 [Read the evidence report](https://ionbin.com/skill-evaluations/anthropic-skill-creator.json)

[Download the authored reproduction harness (JSON bundle) ↗](https://ionbin.com/skill-evaluations/helper-harness.json)

The report provides the case definitions, observations and baseline scope. Missing baselines or untested behaviors remain limitations.

#### Recorded environment

- Windows-11-10.0.26200-SP0; Python 3.12.10; Node 24.18.0; Chrome 155.0.8059.82

- Synthetic local fixtures; minimal child environment; no live account or credential; no OS sandbox

- Dependencies: pypdf 6.19.0, reportlab 4.4.9, Pillow 12.3.0, pdf2image 1.17.0, defusedxml 0.7.1

- Git Bash 5.3.15(1)-release (x86_64-pc-cygwin); Poppler 26.07.0

Recorded commands (2)

Commands document this evaluation. They are not setup instructions for your environment.

```
python run_evals.py --runtime-libs <existing-bundled-site-packages> --poppler-bin <poppler-binaries>
```

```
node viewer_probe.mjs
```

#### Findings from this evaluation

Higher attention

#### Evaluation text can escape the viewer script context

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.

#### Evaluation limitations

- No [Claude](https://ionbin.com/tools/claude/) subprocess, live model, API credential, optimization loop or generated-skill effectiveness evaluation

- Port-cleanup lsof/os.kill effects were mocked; no real process was terminated

- The browser payload only set a marker; no sensitive data or exfiltration was involved

- All browser requests were blocked, including attempted Google Fonts and SheetJS requests

- The viewer may need those external resources for fonts or XLSX rendering; their downloaded code was not evaluated

- Supervised local processes, not an OS sandbox

- No container, VM or memory/resource quota

- Application guards do not establish containment of arbitrary hostile code

- No real credential, remote account, or destructive-effect testing

05 / Reuse & discovery

### License, attribution & popularity.

#### [Apache-2.0](https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/skills/skill-creator/LICENSE.txt)

Per-skill license. Preserve its applicable license and notice obligations when distributing modifications.

#### Why it is in this collection

Rounded repository-wide [GitHub](https://ionbin.com/tools/github/) stars observed in the public repository page; not skill installs, a quality score, or a measured trend.

**182,000** repository stars (rounded)

**Scope**: Repository-wide; not individual skill usage.

**Observed**: Oct 18, 2026

**Time window**: Single observation; no trend is established.

[Discovery source ↗](https://github.com/anthropics/skills)

Popularity and inclusion do not establish quality, compatibility or security. Counts belong to their named metric and date; they are not a current ranking.

06 / Follow the evidence

### Go to the original.

- [Authoring and evaluation workflow](https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/skills/skill-creator/SKILL.md)github.com

- [Trigger runner requirements and subprocess permissions](https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/skills/skill-creator/scripts/run_eval.py)github.com

- [Authentication and transmitted evaluation content](https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/skills/skill-creator/scripts/improve_description.py)github.com

- [Viewer output, localhost binding and process termination](https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/skills/skill-creator/eval-viewer/generate_review.py)github.com

- [Skill license](https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/skills/skill-creator/LICENSE.txt)github.com

- [Repository popularity context](https://github.com/anthropics/skills)github.com

IonBin’s source notes are independent assessments. Upstream authors retain their work and attribution. This page does not install or execute the skill.

ASSESSMENT RECORD

### Read the scope
before the verdict.

**Review coverage**: Runtime probed

**Our experience**: Explored

**Evaluation report**: [Read evidence ↗](https://ionbin.com/skill-evaluations/anthropic-skill-creator.json)

**Version reference**: Recorded

A helper or bounded runtime behavior was probed. This does not establish model task effectiveness or comprehensive security.

[Read the full rubric](https://ionbin.com/skills/methodology/)

[← Back to all skills](https://ionbin.com/skills/)
