Skill Readme Rebuilder

v1.0.0

从 SKILL.md、脚本与资源反推 README、FAQ 与示例,保持说明一致。;use for skills, readme, docs workflows;do not use for 伪造脚本能力, 跳过真实依赖声明.

0· 108·0 current·0 all-time
byvx:17605205782@52yuanchangxing
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, declared requirement (python3), SKILL.md routing, resources/spec.json, and scripts/run.py all align with a 'directory_audit' README-rebuilding tool. The script's functions (directory_report, skill_audit, pattern_report, csv_report) are coherent with the stated goal of producing structured README drafts and audits.
Instruction Scope
SKILL.md instructs the agent to produce structured drafts and to run the local script when shell/exec is available (python3 "{baseDir}/scripts/run.py ..."). The script is read-only: it lists and reads files, generates reports, and has a --dry-run flag. Caveat: the tool reads file contents from the provided directory and may incorporate those contents into outputs (pattern scanning masks long-looking secrets but other file contents may be echoed). The skill explicitly warns not to fabricate capabilities or skip real dependency declarations.
Install Mechanism
No install spec is provided (instruction-only with an included helper script). No remote downloads or third-party package installs are performed. The only runtime dependency is python3 (standard library only, per README/SELF_CHECK).
Credentials
The skill requests no environment variables, no credentials, and no config paths. This is proportionate to a local directory-audit/document-generation utility.
Persistence & Privilege
always is false; the skill does not request persistent elevation or modify other skills. It can be invoked autonomously per default platform behavior, which is expected for skills — nothing in the code writes to unrelated system locations or alters other skills.
Assessment
This skill appears coherent and low-risk for local use: it reads a provided skill directory and produces a draft README/FAQ/report. Before running it (or allowing an agent to run it): 1) inspect scripts/run.py (it is included and readable) and run with --dry-run or on a copy/sandbox of the target directory; 2) avoid pointing it at directories containing secrets or private keys you don't want included in generated output (the pattern scanner masks long-looking secret strings but other sensitive content could still appear in reports); 3) if you will let the agent invoke the skill autonomously, be aware it can read any files under the provided directory — restrict inputs accordingly; 4) do not rely on the tool to modify external systems — it is intended to produce draft text that you should review before publishing or applying changes.

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

latestvk97erstkppqx7z8bzrr0k7nfss8398wp

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Runtime requirements

📗 Clawdis
OSmacOS · Linux · Windows
Binspython3

Comments