← ClaudeAtlas

slack-channel-digestlisted

Pull recent activity from a Slack channel and write structured memories tied to the channel's surface entity. Use when the user asks "what's happening in
ayushmall/memoryvault-kit · ★ 1 · AI & Automation · score 77
Install: claude install-skill ayushmall/memoryvault-kit
# slack-channel-digest Turn a Slack channel into structured memories. The channel itself is a **surface entity** (`entities/surfaces/slack-<name>.md`); the memories from it carry `source_surface:` pointing back. ## Goal When the vault owner asks **"what's happening in #channel?"** the retrieval can answer it via entity-mediated lookup on the surface, not keyword match. That requires every Slack-derived memory to carry a structural link to the channel surface — not just a passing mention. ## Read (before saving) 1. **Does the channel surface entity exist?** ``` entity_resolve "#<channel-name>" ``` If no, create it with `surface_kind: slack-channel`, `medium: slack`, inferred `about:` (customer, project, or topic), and `participants:` (start empty; updated as you ingest messages). 2. **Search recent vault for memories already tied to this channel:** ``` memory_search entities=["[[#<channel-name>]]"] ``` Read the top 5 — what already exists shapes what new memories to write. 3. **Check active gap memories tied to this channel's `about:` entities:** ``` memory_search type=feedback tags=coverage-gap entities=["[[<about-entity>]]"] ``` If a gap matches new channel content, prioritize filling it. ## Reflect For each non-trivial thread or message-cluster (skip emoji replies, acks, single-line "thanks"): - Is it a **decision**? (commitment language → `type: decision`, run the `docs/memory-playbooks/decision.md` playbook) - Is it a