content-minelisted

Scan recent agent sessions for content-worthy moments and capture them as drafts in a publishing funnel, publishing nothing. Zero-token detector, then a taste judge, then capture. Triggers: "/content-mine", "mine sessions for content", "what in our sessions deserves a post".
tonydzi/second-brain-starter-kit · ★ 6 · AI & Automation · score 78

Install: claude install-skill tonydzi/second-brain-starter-kit

CONTENT_MINE — sessions → funnel drafts (draft-first, taste delegated to me) GOAL: mine our Claude Code sessions for content-worthy MOMENTS and drop them as DRAFTS into the content-factory funnel. Publishing happens only on the operator's explicit "+" through /episode. Nothing goes out. The operator delegated the taste call — "what deserves to be content" — to me (2026-07-08). I don't ask what to add; I decide. PATHS: - Engine: `$IMPORTS_ROOT/content-factory\content_miner.py` (same family as alpha-extraction / intention_mine; reads the live `vault_sessions` pool). - Funnel (intake): `content-factory\triage\posts.jsonl` (+ `posts.md`), `source_kind: session`. Writes through `voice_triage.py append` (dedup/upsert). - Digest: `content-factory\miner\candidates\cand-latest.md`. Ledger: `miner\captured.jsonl`. STEPS: 1. SCAN (deterministic, 0 tokens). Recent by default: `python content_miner.py mine --days 7`. Backlog / the whole archive: `mine --all --operator Anton --cap 150`. Flags: `--day YYYY-MM-DD`, `--operator all`, `--cap N`. Note `OVER_THRESHOLD` and `OUT`. 2. Empty (SESSIONS=0 / OVER_THRESHOLD=0) → say "no fresh moments worth capturing" and stop. 3. READ the digest `cand-latest.md` (or `OUT`). Each ### = a session `src | date | machine | operator [PRIV] {score · tags}` + a headline + snippets ([U]=the operator, [A]=Claude). Look at the top ones (HOT→WARM); on large volumes, fan out Sonnet judges over slices (see `miner\slices\`), they return JSON verdicts, you dedup a