← ClaudeAtlas

setup-cantrips-looplisted

Configure this repo's cantrips loop — knowledge stores and storage backend — by writing docs/agents/cantrips-loop.md.
toverux/cantrips · ★ 2 · AI & Automation · score 76
Install: claude install-skill toverux/cantrips
Configure how this repo runs the cantrips loop: which opt-in knowledge stores are enabled, and which backend the six storage verbs translate to. The result is one prose doc, `docs/agents/cantrips-loop.md`, that storage-touching skills read in place of the plugin defaults ([defaults.md](defaults.md)). ## Process 1. Read `docs/agents/cantrips-loop.md` if it exists. An existing doc makes this run an edit: summarize the current configuration, ask what the user wants to change, and carry every unrevisited answer forward unchanged. 2. Explain each opt-in knowledge store's role in plain words, then ask which to enable: - `docs/adr/` holds durable decisions with supersession chains — an outdated record names the record that replaced it, so decisions have history instead of silent drift. Written only through `/compound`'s user gate; read back by `/spec` as the repo's decision memory. - `docs/solutions/` holds problem-shaped learnings — root cause, the gotcha, what didn't work — so the next session that hits the same problem starts from the answer. 3. Ask which backend seed translates the six storage verbs (the verbs and their meaning: [defaults.md](defaults.md)): - **Local markdown** — the default made explicit: the verb translations in [defaults.md](defaults.md). Ask where the artifacts live: gitignored `.scratch/<feature>/` (the default — disposable working material, deleted by the human when the feature closes) or a committed path such as `docs/specs/` f