AB skill-deep-audit
Generic skill-quality auditor for any agent skill (Claude, OpenClaw, Cursor, etc.). Runs a 7-dimension static analysis (D1 process closure & idempotency, D2 tool/command conventions, D3 portability & defense, D4 skill usability, D5 security & op risk, D6 code & doc quality, D7 dependency & footprint) with explicit ERR / WARN severity, 120-point scoring (pass line 90 + zero ERR), and an opt-in `--fix` workflow that always backs up first. Two depths: L1 static (~2 min) and L2 dryRun (~5 min, read-only hub + reachability checks). Strict red lines — read-only by default, never executes the audited skill's writes. Use when the user asks to "audit a skill", "check skill quality", "is this skill ready to ship", "lint my skill", or runs this tool by name. Triggers also: "审计这个 Skill"、"检查 Skill 质量"、"Skill 能上线吗"、 "skill-deep-audit"、"审一下 xxx skill"。
Generic skill-quality auditor for any agent skill (Claude, OpenClaw, Cursor, etc.). Runs a 7-dimension static analysis (D1 process closure & idempotency, D2…
As a process B 70/100 · Nearly there — weak spots: result and completion
How to improve
- 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: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 70/100
- 0Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 48 steps, 1 vague phrases
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3660 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 15 top-level sections: this looks like several domains in one skill
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 849: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -223 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +4Structure: 24 headings
- +3Step-by-step instructions: 48 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.