asklisted

Explain Clio — what each clio:* command does, when to run it, which files it reads and writes, and how the three ledgers work. Use when the user asks "what does /clio:memo do", "how does Clio work", "which clio command should I run", or anything about the Clio plugin.
nhhthong/clio · ★ 2 · Data & Documents · score 78

Install: claude install-skill nhhthong/clio

Read-only. Answer from the plugin's own files; never invent behaviour a SKILL.md does not describe. No `.claude/clio/` in this project → say so first, point at `/clio:setup`. Question (may be empty): $ARGUMENTS **No argument** → print this, then one line: *`clio:context` runs before work; `/clio:memo` after is the one command to remember — the only reminder is a once-per-session nudge when git has work the ledger does not.* | Command | Does | Run when | |---|---|---| | `/clio:setup` | scaffold `.claude/`, fill CLAUDE.md / CONTEXT.md by asking. Never touches the stack | once per repo | | `/clio:ingest <doc>` | distil a requirement document into `docs/specs/memory/*.md` + `requirements.md` | once, and when a new source arrives | | `/clio:plan <area>` | split a spec area into the smallest testable tasks → `docs/plans/<area>.md`. `infra` is the foundation: it settles the stack, writes `docs/plans/infra.md` and `rules/<stack>.md`, and needs no spec | `infra` right after setup; an area after ingest, and when a row moves | | `/clio:context [x]` | no arg: where are we (plans done/open, debt queue) �� with area/row/id/question: spec, what was built, what is owed, quoted from the docs | Claude triggers it before work; you, when asking "where are we?" or "why?" | | `/clio:memo` | record finished work: task doc, `index.jsonl`, `debt.jsonl` | after each feature / fix | | `/clio:update` | a spec changed: record the delta vs. existing code, move the row marker | when requirements change