AF shuxia-skill-library
Use when creating, reviewing, or refining an agent skill and the goal is to make the skill more obedient, better bounded, and harder to misuse. Especially useful when extracting reusable ideas from strong external skills, turning them into boundary rules, constraint patterns, review checklists, and concrete revisions for local skills.
Especially useful when extracting reusable ideas from strong external skills, turning them into boundary rules, constraint patterns, review checklists, and…
As a process F 50/100 · Will not run — References files that are not bundled: /Users/xiaomao11/.codex/skills/shuxia-skill-library/skill-patterns.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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: /Users/xiaomao11/.codex/skills/shuxia-skill-library/skill-patterns.md
Process rating: all ten parameters 50/100
- 0Tools and files. 1 referenced file(s) missing: /Users/xiaomao11/.codex/skills/shuxia-skill-library/skill-patterns.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 105 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1552 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
- +5Description has no quoted example phrases that should trigger the skill
- +4No input/output examples
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 336: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 105 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.