Sign inGet started

Analyzes a repository's actual stack to sort agent skills, commands, rules, and hooks into always-loaded (DAILY) versus searchable (LIBRARY) buckets, producing an evidence-backed trimmed install plan.

Lift—not yet benchmarked
89
Trustsecurity · quality · license · upkeep
Scan Saferisk 0/100
LicenseMITserved via MCP

What it does

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

#skill-curation#install-planning#repo-analysis#evidence-based#configuration

Quality judgment

completeness
8.0/10
clarity
8.5/10
trigger quality
6.5/10
examples
7.5/10
structure
9.0/10
overall
7.5/10

A well-structured, actionable skill with a clear two-bucket model, concrete evidence table examples, parallel/sequential fallbacks, verification steps, and handoffs. Minor gaps: trigger description is somewhat jargon-heavy (ECC assumed known), and no guidance on edge cases like multi-language monorepos or conflicting evidence.

Files (3)

agents/openai.yaml · 0.2 KBLICENSE · 1.0 KBSKILL.md · 5.8 KB