knowledge-gardenlisted

This skill should be used when the user asks to audit, health-check, or structurally validate one or more SPECIFIC named notes or a bounded topic cluster — 'audit these notes', 'check this note for orphans or broken links', 'fourth-wall check on [note]', 'validate the structure of [note]', 'spot-check [note]'. Runs a read-only audit inline. NOT for fixing issues (use /knowledge-maintain), NOT for freeform topic questions (use /knowledge-ask), and NOT for whole-graph audits ('audit my knowledge graph', 'graph health', 'full audit', no arguments) — those belong to the knowledge-gardener agent, which this skill delegates to when invoked graph-wide.
voxpelli/vp-claude · ★ 3 · AI & Automation · score 73

Install: claude install-skill voxpelli/vp-claude

# Knowledge Garden Audit Basic Memory notes for structural and quality issues, then report actionable, copy-paste-ready findings. **Read-only — never writes or modifies notes.** Fixes are handed off to `/knowledge-maintain`. This skill is the scoped, interactive sibling of the `knowledge-gardener` agent. It owns the common case — auditing a handful of named notes inline in the main session — and delegates the heavy, graph-wide sweep to the agent so the full audit's hundreds of note reads stay out of the main context window. ## Arguments The user names the notes or topics to audit after the invocation: | Form | Example | |------|---------| | One note title | `/knowledge-garden npm-fastify` | | Several notes | `/knowledge-garden npm-umzeption npm-umzug` | | Prefixed identifier | `/knowledge-garden brew:ripgrep` | | Topic phrase | `/knowledge-garden the IndieWeb concept notes` | | No arguments | `/knowledge-garden` → whole-graph audit (delegated) | ## 1. Decide venue (scoped inline vs delegate) This is the first and most important step. Classify the request: **Delegate to the agent** when the request is graph-wide — any of: - No arguments are provided. - The argument is a whole-graph phrase: "my knowledge graph", "the whole graph", "everything", "all notes", "full audit", "--full", "graph health". - The request implies graph-wide checks the inline path cannot do efficiently: schema drift across a whole type, version drift across ecosystems, cross-project scope leak