ClawHub

Skill Doc Enhancer

v1.0.0

Automatically analyze and enhance content-short SKILL.md files by analyzing skill directory structure, adding usage examples, script documentation, common us...

⭐ 0· 26·0 current·0 all-time
by风风@834948655
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description match the provided scripts and SKILL.md: the scripts analyze a skill directory and generate or append documentation to SKILL.md. There are no unrelated credentials, binaries, or config paths requested.
✓
Instruction Scope
SKILL.md runtime instructions tell the agent to run the included Python scripts against a local skill directory. The scripts only read files in the target directory (SKILL.md and files under scripts/, references/, assets/) and may write back to SKILL.md. They do not access other system paths, environment variables, or external endpoints.
✓
Install Mechanism
No install spec is provided (instruction-only with included scripts). The scripts assume a local python3 runtime, which is reasonable and proportional for the stated task. Nothing is downloaded or extracted from the network.
✓
Credentials
No environment variables, credentials, or config paths are requested. The scripts operate on the provided skill directory only and do not require external secrets.
✓
Persistence & Privilege
always is false and the skill does not request persistent or cross-skill privileges. It can modify only the SKILL.md in the target skill directory (normal for an enhancer). The skill does print JSON reports that include absolute skill paths, which is expected but worth noting.
Assessment
This skill appears to do what it says: it reads a skill directory and can append generated documentation to SKILL.md. Before running (especially without --dry-run): 1) Back up the original SKILL.md so you can revert unwanted changes. 2) Use --dry-run to preview changes. 3) Inspect any scripts in the target scripts/ directory before executing them (they could contain arbitrary code unrelated to documentation). 4) Be aware reports include absolute paths in their JSON output (may reveal local filesystem structure). If you only want to preview additions, always use --dry-run and review the preview before writing.

Like a lobster shell, security has layers — review code before you run it.

latestvk971ay6rsa1gqtcad8f6w3pkn184pch8

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments