AD skills-audit
Audit all installed skills to identify duplicates, platform-mismatched skills, and maintenance candidates. Use when: (1) the user asks to "clean up skills", "check for duplicate skills", "audit installed skills", or "find skills to remove"; (2) performing periodic skill maintenance; (3) investigating skill clutter or skill conflicts. Scans all SKILL.md files in ~/.workbuddy/skills/, compares against a golden list of approved skills, classifies each as approved / unknown / platform-specific, and generates a structured audit report.
Audit all installed skills to identify duplicates, platform-mismatched skills, and maintenance candidates.
As a process D 39/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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: 4. 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 39/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (skills-audit) differs from the folder (workbuddy-skills-audit)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 8 steps
- 100Execution cost. Instruction body is 451 tokens
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 536: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 8 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.