knowledge-refresh
Knowledge Refresh
Close the self-healing loop for a bound cogni-knowledge base. Wiki pages age — the vendored lint_wiki.py flags stale_page (>365d) and stale_draft (>180d) findings, but lint alone doesn't bring fresh evidence. Push-mode lints the wiki, asks the user which stale topics they want fresh evidence on, then runs the inverted pipeline per selected topic: the seven-phase chain knowledge-plan → knowledge-curate → knowledge-fetch → knowledge-ingest → knowledge-distill (optional, fail-soft) → knowledge-compose → knowledge-verify → knowledge-finalize. Each topic ends with a freshly-composed, claim-verified type: synthesis page deposited into the bound wiki, and the distill step enriches the concept/entity web. An orthogonal opt-in --resweep flag re-verifies the bound wiki's cited claims against live source URLs.
This skill is a pure orchestrator — push-mode composes existing cogni-knowledge phase skills via Skill(...), never re-implementing them. Push-mode dispatches zero cogni-research skills — cogni-research is 0% of the runtime path.
Read ${CLAUDE_PLUGIN_ROOT}/references/delegation-contract.md once per session to remember the delegation boundary and the Skill-dispatch convention (§"How Skill(...) blocks are written").
When to run
- User wants to refresh stale pages in a bound knowledge base
- User wants the system to auto-research the stale topics (push-mode)
- User wants to re-verify the bound wiki's cited claims against live source URLs —
--resweep(opt-in)