Skill Frontmatter Doctor
v1.0.0修复 frontmatter、metadata、requires、install 和目录结构问题，贴合当前 OpenClaw 规范。；use for skills, frontmatter, validation workflows；do not use for 编造不存在的字段, 忽略单行 JSON 约束.
⭐ 0· 89·0 current·0 all-time
byvx：17605205782@52yuanchangxing
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description state it audits and repairs frontmatter/metadata/requires/install/dirs. The bundle includes a local Python script (scripts/run.py) that implements directory/skill audits and uses resources/spec.json and resources/template.md. Requesting python3 only is appropriate and expected.
Instruction Scope
SKILL.md explicitly instructs the agent to run the local script or to synthesize output from resources when execution isn't available. The runtime steps focus on reading files in the provided input (skill dir or files) and producing audit reports; they do not instruct any hidden network calls, secret collection, or system-wide changes. Note: the script will read any path you provide, so avoid pointing it at sensitive system directories or credential stores.
Install Mechanism
No install spec; this is instruction-only with a bundled Python script. Nothing is downloaded or extracted during install. Risk is low because the code is included in the package and depends only on the Python standard library.
Credentials
Requires only python3 and declares no environment variables or credentials. The script does not reference secrets or external credentials. This is proportionate to the stated auditing task.
Persistence & Privilege
always:false and user-invocable:true. The skill does not request persistent system-wide changes or other skills' credentials. It may write an output file when invoked with --output, which is expected for a reporting tool.
Assessment
This skill appears coherent and low-risk: it runs a local Python audit script and produces reviewable Markdown. Before installing/using it: (1) inspect scripts/run.py yourself (it is bundled and contains no network or exec calls), (2) run it with a non-sensitive test directory and use --dry-run or redirect output to a safe location, (3) do not point the tool at system root or credential directories (it will read whatever path you provide), and (4) if you allow autonomous agent invocation, limit the agent's input scope so the skill cannot be run against sensitive paths automatically.Like a lobster shell, security has layers — review code before you run it.
latestvk9770yxgvmvba5s927hnx13tf1839ntz
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🩺 Clawdis
OSmacOS · Linux · Windows
Binspython3