AC skill-doctor
Audit, debug, and clean up the OpenClaw skills you already have installed. Use this skill whenever the user asks to check, audit, review, clean up, or debug their installed skills, or says things like 'why did the wrong skill fire,' 'which skill handles X,' 'do any of my skills conflict,' 'are my skills safe,' 'scan my skills for security issues,' 'are any of my skills out of date,' 'which skills overlap,' 'why isn't my skill triggering,' 'audit my skill library,' or 'is this skill safe to keep.' Detects duplicate and conflicting triggers (skills that fight over the same prompts), inline security red flags (credential exfiltration, remote code execution, hard-coded secrets), and out-of-date versions, and predicts which installed skill will fire for any given prompt. The missing health check for a growing skill collection.
As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 2
✓ No critical or high findings
Medium and low: 2
✓ Guard found no suspicious behaviour. 2 matches are attack strings quoted in this security skill's own documentation.
Files scanned: 5. 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 56/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (skill-doctor) differs from the folder (skill-doctor-audit)
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 7 branches
- 100Steps. 13 steps
- 100Execution cost. Instruction body is 1438 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- medium 2 test cases, all positive: not one "should refuse" or "should ask first"
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 833: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 8 headings
- +3Step-by-step instructions: 13 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.