From buap
Audit a repository and produce verified findings only, never trusting README/doc claims without implementation evidence. Use when asked to audit, assess, review the state of, or "tell me what actually works in" a repo or codebase, or to compare docs against source. Follows the BUAP repo-audit runbook and labels every finding.
How this skill is triggered — by the user, by Claude, or both
Slash command
/buap:buap-repo-auditThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Produce **verified findings only**. Do not trust README or doc claims without
Produce verified findings only. Do not trust README or doc claims without
implementation evidence. This is the BUAP runbooks/repo-audit.md procedure.
AGENTS.md, CLAUDE.md, CODEX.md,
.cursor/rules, README. A repo's own contract outranks generic assumptions.For non-trivial audits, delegate the inspection sweep to the lil-buddy subagent and
review its report before answering.
npx claudepluginhub codysumpter-cloud/buddy-universal-agent-profile --plugin buapScans a codebase for architectural friction, presents candidates as a visual HTML report with before/after diagrams, and guides you through deepening refactors.