AI Engineering · Version 1.1.0 · Reviewed 2026-08-02
AI Skill Portfolio Auditor
Make AI behavior measurable and safer for skill inventory analysis and trigger collision detection with evidence, explicit trade-offs, and a verification plan.
4 method steps
5 documented failure modes
5 diagnostic checks
7 quality gates
Audits a skill collection for duplicated jobs, trigger collisions, missing coverage, inconsistent quality, and stale knowledge. It grounds the decision in skill frontmatter, descriptions, triggers, workflows, evaluation results, usage, versions, and ownership and explicitly prevents evaluating files independently and missing that two good skills compete for the same request or contradict each other.
₹199 one-time
Get this skill archive
What it checks first
AI Skill Portfolio Auditor audits a skill collection for duplicated jobs, trigger collisions, missing coverage, inconsistent quality, and stale knowledge. It grounds the decision in skill frontmatter, descriptions, triggers, workflows, evaluation results, usage, versions, and ownership and explicitly prevents evaluating files independently and missing that two good skills compete for the same request or contradict each other. Use it when the work involves Skill inventory analysis, Trigger collision detection, Portfolio coverage gap review.
- Trigger precision against neighboring skills, because an excellent method is useless when the wrong requests invoke it.
- Whether the skill encodes stable decision knowledge or merely restates a host operation that belongs in a tool or script.
- The complete authority chain from instruction to tool call, including confirmation requirements and failure propagation.
- Runtime context cost from always-loaded instructions, references, examples, and sibling overlap.
- Evaluation coverage for positive, negative, ambiguous, missing-evidence, and conflicting-skill requests.
Example task
Input
Apply the ai skill portfolio auditor to our current skill inventory analysis work. We need a concrete decision, bounded changes, and evidence that the result is correct.
Expected output
Start with skill frontmatter, descriptions, triggers, workflows, evaluation results, usage, versions, and ownership. The highest-risk failure is evaluating files independently and missing that two good skills compete for the same request or contradict each other. Assess routing and coverage at portfolio level, then rank consolidation, specialization, and retirement actions. Verify the result by running a shared intent corpus through the full portfolio and measuring ambiguous, missed, and incorrect routing.