agentleFS
Sign inStart free
loganware05loganware05/captains-compass-cursor/.cursor/skills/notion-integration/SKILL.md

notion-integration

Skill2 starsChanged 33 days agoMITView on GitHub

Reads Notion requirements/research and writes release summaries when MCP is available; never stores approval-critical state only in Notion

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After validation, optionally write a short release summary page/section.

    line 27
  2. Distinctive:

    If Notion is unavailable, continue with repo docs only and report the gap.

    line 29
  3. Very specific:

    Run ./scripts/ingest-notion-live.sh explicitly.

    line 36
  4. Distinctive:

    Never ingest pages outside the allowlist.

    line 37
  5. Very specific:

    NorthStar bridge (non-authoritative): after REVIEW_READY, ./scripts/run-northstar-routine.sh ...

    line 39
  6. Distinctive:

    Do not store implementation-critical approvals only in Notion

    line 47
  7. Very specific:

    Do not replace IMPLEMENTATION_PLAN.md / DECISIONS.md with Notion-only records

    line 48
  8. Distinctive:

    Do not grant write access to pages outside the agreed project space

    line 49

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Notion Integration (MCP Stage 4)

Use this Skill when

Reading product requirements or research from Notion, or writing release summaries after a completed change.

Prerequisites

  • Notion MCP enabled in Cursor with least-privilege access
  • Repository remains authoritative for plans, decisions, and approvals

Allowed Stage 4 capabilities

  • Reading requirements
  • Reading project research
  • Writing release summaries

Procedure

  1. Confirm Notion access via MCP.
  2. Pull requirements/research into the planning phase; cite page links in IMPLEMENTATION_PLAN.md.
  3. After validation, optionally write a short release summary page/section.
  4. Mirror any durable decisions into DECISIONS.md in the repository.
  5. If Notion is unavailable, continue with repo docs only and report the gap.

  6. Live knowledge ingest (allowlist-gated — separate from file export):

    • Maintain .agent/knowledge/notion-allowlist.txt with approved page IDs.
    • Fetch allowlisted pages via notion-fetch MCP.
    • Save markdown under .agent/knowledge/external/notion-live/<page-id>.md or export a JSON payload for ./scripts/ingest-notion-live.sh --source live.
    • Run ./scripts/ingest-notion-live.sh explicitly; provenance is mcp_live.
    • Never ingest pages outside the allowlist.
  7. NorthStar bridge (non-authoritative): after REVIEW_READY, ./scripts/run-northstar-routine.sh ... --notion-mode fixtures|live may gather research context and write a summary mirror under .agent/evidence/<run_id>/notion-summary-mirror.json. Live mode requires Notion MCP authentication (Cursor desktop). Approvals stay on GitHub.

Prohibited actions

  • Do not store implementation-critical approvals only in Notion
  • Do not replace IMPLEMENTATION_PLAN.md / DECISIONS.md with Notion-only records
  • Do not grant write access to pages outside the agreed project space

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free