Quality check
Agent Skill Infrastructure: quality check, behavior test runner, version awareness
npx -y skills add Liber1917/agent-skill-infra --skill quality-checkAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Analyze and score Agent Skills using an 8-dimension quality framework (helloandy methodology). Checks trigger accuracy, output structure, error tolerance, token efficiency, and security posture. Use when reviewing, improving, or evaluating SKILL.md files for quality.
SKILL.md
1.8 KB, as published. Nobody here has run it
Skill Quality Check
Evaluate Agent Skills against the helloandy 8-dimension quality framework.
Dimensions
Technical Quality (5 dimensions, 5 points each = 25 total)
- Trigger Accuracy — Does the skill activate on the right inputs and ignore irrelevant ones?
- Output Structure — Are outputs well-formatted, consistent, and follow expected schemas?
- Error Tolerance — Does the skill handle edge cases gracefully without crashing?
- Token Efficiency — Is the SKILL.md concise? Does it avoid unnecessary repetition?
- Tool Integration — Are tool calls correct, efficient, and properly error-handled?
Output Quality (3 dimensions, 5 points each = 15 total)
- Completeness — Does the skill fully address the user's request?
- Actionability — Are the outputs immediately usable without further clarification?
- Consistency — Are outputs deterministic across similar inputs?
Process
- Read the target SKILL.md file
- Score each dimension (1-5) with evidence
- Calculate total score (max 40)
- Provide specific improvement suggestions for any dimension scoring below 3
- Output a structured report with scores, evidence, and recommendations
Report Format
## Quality Report: [Skill Name]
| Dimension | Score | Evidence |
|-----------|-------|----------|
| Trigger Accuracy | X/5 | ... |
| Output Structure | X/5 | ... |
| ... | ... | ... |
**Total: XX/40**
**Grade: [A/B/C/D/F]**
### Improvement Suggestions
- [Specific actionable suggestion for low-scoring dimensions]