Skill Extraction

PassAudited by ClawScan on May 1, 2026.

Overview

This instruction-only skill coherently scans a project and writes extracted documentation or skill files, but users should review generated outputs before reusing them.

This skill appears consistent with its stated purpose and has no code or credential requirements. Before installing or running it, be comfortable with it reading the current repository and writing generated files under docs/extracted/ and ai/skills/. Review the generated skills and documentation for secrets, confidential project details, or unwanted instructions before reusing them.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

Running the command can add or change documentation and skill files in the current project.

Why it was flagged

The skill is designed to create files in the repository. This is purpose-aligned, but users should expect local file changes.

Skill content
Outputs to `ai/skills/` and `docs/extracted/`
Recommendation

Review generated files with normal version-control diffs before committing, installing, or relying on them.

What this means

Project patterns, architecture details, or unintended sensitive context could be preserved in reusable skill files.

Why it was flagged

The output can become persistent agent-consumable skill content. If extracted from private, untrusted, or overly specific project material, that content may affect future agent behavior.

Skill content
Create `ai/skills/[project]-[pattern]/SKILL.md`
Recommendation

Run it only on intended repositories, check generated skills for secrets or project-specific confidential details, and approve them before reuse.

What this means

Users may install from a remote source whose provenance is not fully described in the registry metadata.

Why it was flagged

The README documents a remote npx/GitHub-based installation path while the registry source is listed as unknown. No runnable code is included here, so this is a provenance note rather than a behavioral concern.

Skill content
npx add https://github.com/wpank/ai/tree/main/skills/extraction/pattern-extraction
Recommendation

Prefer the trusted registry install path or inspect the referenced repository before installing from the GitHub URL.