AF skill-optimizer
Audit and improve existing Agent Skills (SKILL.md files) against the agentskills.io standard. Use this skill whenever the user wants to optimize, polish, improve, audit, review, fix, or refine an existing skill — even if they don't say "skill optimizer" explicitly. Triggers on phrases like "improve my skill", "audit SKILL.md", "make my skill trigger better", "fix the description", "is my skill well written?", "review this skill", "polish my skill", "this skill underperforms", or any request to update a SKILL.md for clarity, triggering accuracy, or structure. Runs a 3-dimension audit (Specification / Best Practices / Description Optimization), produces a severity-ranked report, and proposes concrete edits. For full eval-driven iteration with baseline comparisons, defer to the skill-creator skill.
Audit and improve existing Agent Skills (SKILL.md files) against the agentskills.io standard. Use this skill whenever the user wants to optimize, polish…
As a process F 47/100 · Will not run — References files that are not bundled: references/sub/deep/file.md, references/<topic>.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
missing-refreference to a missing file: references/sub/deep/file.md - warning
missing-refreference to a missing file: references/<topic>.md
Process rating: all ten parameters 47/100
- 0Tools and files. 2 referenced file(s) missing: references/sub/deep/file.md, references/<topic>.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-optimizer) differs from the folder (skill-optimize)
- 70Failures and branches. 4 branches
- 100Steps. 66 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 3036 tokens
- 100Running it twice. Mutating operations check current state
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
- +3Description length 806: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 17 headings
- +3Step-by-step instructions: 66 items
- +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: 84.