Skill usage review
Skill matt-bat/agent-command-center/skills/skill-usage-review
Use for periodically reviewing which skills are overused, underused, missing, or creating friction by examining recent governance artifacts, handoffs, instruction trackers, and task outcomes.From its SKILL.md
npx -y skills add matt-bat/agent-command-center --skill skill-usage-reviewAssembled 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.
- 4 stars4 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.
SKILL.md
2.5 KB, 512 tokens by cl100k_base, as published. Nobody here has run it
Skill Usage Review
Mission
Improve the skillpack from real usage evidence instead of intuition.
Authority and Artifact Policy
- Activating this skill grants no authority to create or update field notes, routing observations, governance artifacts, or policy files.
- Use existing evidence read-only unless the task separately authorizes a durable review artifact or remediation.
- Do not retain prompts, source content, hidden reasoning, or unbounded history as usage evidence.
Trigger Rule
Use this skill when:
- reviewing recent tasks for process quality
- checking whether skills are being over-applied
- deciding whether a skill should be split, merged, deprecated, or promoted
- preparing a periodic maintenance report
Scope Boundary
This skill owns usage-pattern review and improvement recommendations.
Use Deprecation Management for deprecation lifecycle decisions. Use Thoroughly Rate Review for scoring quality.
Evidence Sources
Prefer existing artifacts:
docs/governance/*.governance.jsondocs/governance/*.governance.md- root
user-instructions.mdwhen the repository has opted into durable tracking docs/handoffs/*.mdwhen present- recent commit messages or release notes
- bounded routing-observation summaries when present; never prompts, source content, or hidden reasoning
Review Checks
- most frequently selected skills
- skills selected without clear task value
- tasks missing expected safety or validation skills
- skills never selected despite documented triggers
- repeated user corrections or friction points
- artifacts created but not maintained
Anti-Overuse Rules
Use when:
- there is enough recent task evidence to review
- process behavior is being tuned
- the user asks whether the skillpack itself is working well
Do not use when:
- there is no usage evidence yet
- the task is a single implementation request
- a direct policy fix is already obvious and bounded
Stop after:
- usage findings are grouped by severity
- concrete skill changes are proposed
- no more than five next actions are recommended
Output Contract
When applying this skill, provide:
- evidence reviewed
- overused skills
- underused or missing skills
- friction points
- recommended changes with priority
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.