Scan a directory or workspace for SKILL.md files across all agents and repos, capture supporting files (references, scripts, linked docs), dedupe vendored copies, enrich each Tessl tile with registry signals, and emit a canonical JSON inventory validated by JSON Schema. Then run four analytical phases in parallel against the inventory — staleness + git provenance (history, broken refs, contributors), quality (Tessl `skill review`), duplicates (similarity + LLM judgement), registry-search (per-standalone-skill registry suggestions, HTTP only) — and render a self-contained interactive HTML report with a top-of-report health overview, top-issues panel, recently-changed list, and per-tessl.json manifests view.
84
90%
Does it follow best practices?
Impact
97%
1.44xAverage score across 2 eval scenarios
Advisory
Suggest reviewing before use
You're being asked to audit the skills in two of three repositories that share a parent directory. The repositories are at:
./resources/repo-a — should be included./resources/repo-b — should be included./resources/repo-c — must be excluded, even though it lives in the same parent directory and contains skillsThe team owner only cares about repo-a and repo-b for this audit, and they've explicitly asked you NOT to scan repo-c (it belongs to a different team and is being deprecated next month).
The repositories have already been initialised as real git repos by the setup script and each has one commit.
Produce a single consolidated report that covers both repo-a and repo-b at:
./.skill-insights/discovery.json./.skill-insights/staleness.json./.skill-insights/quality.json./.skill-insights/duplicates.json./.skill-insights/report.html(Note: place these in the working directory's .skill-insights/, NOT inside any individual repo, since this is a multi-repo scan with a shared parent.)
Then write ./scan-summary.md documenting:
discovery.jsonrepo-c was excluded