clean-slatelisted

Re-initializes a project's agent knowledge from scratch when the existing knowledge files (CLAUDE.md, AGENTS.md, cursor rules, architecture docs, roadmaps, old plans) have rotted, contradict the code, or accumulated too much noise to patch. Salvages still-true facts by verifying them against the code, asks the user about backup before deleting anything, re-reads the actual codebase fresh, interviews the user on the intended direction, and rebuilds strong AGENTS.md, docs/ARCHITECTURE.md, and ROADMAP.md. Use when the user asks to reset, re-initialize, or rebuild project knowledge or architecture docs, says the docs are stale or wrong, or mentions clean-slate or /clean-slate.
silkyland/clean-slate · ★ 0 · Data & Documents · score 75

Install: claude install-skill silkyland/clean-slate

# Clean Slate Knowledge files rot: plans outlive their implementation, rules contradict the code, three generations of agents each left their own notes. Past a point, patching costs more than rebuilding. This skill burns it down **safely** and rebuilds from the only two sources that matter: **the code as it is, and the user's intent as they state it today.** ## Safety rules (non-negotiable) This skill deletes files. Therefore: 1. **Never delete anything before the user has confirmed BOTH the exact file list AND a backup decision.** Present the list, ask about backup (with a recommended answer), wait for explicit confirmation. No confirmation, no deletion. 2. **Never delete human/product documentation** — README, LICENSE, CHANGELOG, CONTRIBUTING, API docs for end users. Only agent-knowledge files are in scope; see [references/knowledge-file-patterns.md](references/knowledge-file-patterns.md). When a file is ambiguous, default to KEEP and ask. 3. **Salvage before you burn.** Old files are read and mined for claims before deletion — a rotten document usually still contains a few hard-won, still-true facts. Only claims re-verified against the current code survive into the new docs. 4. **Deletion without a verified backup is ONE-WAY** — it requires an explicit user confirmation and is never performed unattended. Deletion after a count-verified backup (Step 4) is REVERSIBLE and is the only kind this skill executes in a headless run. ## Headl