scribe-cli

# scribe CLI — operations agent skill `scribe` is a single-binary Go CLI that runs a knowledge-base pipeline: discover repos → extract knowledge → mine agent sessions → absorb URLs → lint → reindex with qmd. It normally runs unattended on cron. This skill is for **driving the CLI by hand** — diagnosing health, running a step manually, and choosing the right command for a goal. Two sibling skills own the other halves and this skill routes to them: - **scribe-kb** — authoring/searching KB *content* (articles, drop files, qmd). - **scribe-kb-tidy** — working the `scribe lint` content-quality queue (split bloated, archive rolling, merge thin/self-named-dirs). ## Golden rule: diagnose read-only before you act Always start with the two read-only commands. They never write and never call an LLM, so they are safe to run anytime: ``` scribe doctor # deps, config, cron, state, run-freshness, errors, ledgers — read-only health scribe status # scoreboard: raw-by-density, absorb/contextualize progress, backlog, last sync ``` Read the output first, then run the *one* command it points you at. `doctor` prints a FAIL/WARN per check and ends with the `status` scoreboard; most WARN lines already name the command that clears them. See `references/TROUBLESHOOT.md` for how to read each section. ## Respect the daemon (the lock rule) scribe runs on the user's cron. Two commands take a **machine-wide lock shared with that daemon**: - `scribe sync` — the full pipeline (discover →...