BF Skill Audit & Publish
Audit-first pipeline to publish an OpenClaw skill to ClawHub without leaking personal data, credentials, or model-specific references. Five stages — Sanitize, Transform, Verify, Publish, Install-check — with explicit user approval before every irreversible step. Use this when the user wants to publish a skill to ClawHub, sanitize a skill before publishing, run a pre-publish PII/secret audit, or follow the ClawHub publish workflow. Bundled helper script: scripts/sync_skill_to_github.js mirrors a publish folder to a GitHub repo via the GitHub Contents API using a user-supplied token (GITHUB_TOKEN/GITHUB_PAT env var); it only creates or updates files and never deletes anything. Trigger phrases: 'publish to ClawHub', 'publish my skill', 'sanitize before publish', 'pre-publish checklist', 'clawhub publish command', 'upload a skill to clawhub'.
Audit-first pipeline to publish an OpenClaw skill to ClawHub without leaking personal data, credentials, or model-specific references.
As a process F 43/100 · Will not run — References files that are not bundled: references/*.md
How to improve
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
missing-refreference to a missing file: references/*.md - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName"
Process rating: all ten parameters 43/100
- 0Tools and files. 1 referenced file(s) missing: references/*.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (Skill Audit & Publish) differs from the folder (skill-audit-publish)
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 100Steps. 52 steps
- 100Execution cost. Instruction body is 3577 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (11 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 850: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +4Structure: 11 headings
- +3Step-by-step instructions: 52 items
- +4Has examples (0 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.