ingest-notion
Skill293 starsChanged 11 days agoMITView on GitHub
Bring selected Notion pages into shared Egregore memory via Notion's official MCP. Routed from /ingest when the source is Notion — say '/ingest notion'. Selected pages only, not a full-workspace sync.
In this repository50 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- activitySkill
- announceSkill
- archiveSkill
- branchSkill
- checkupSkill
- commitSkill
- contributeSkill
- create-skillSkill
- dark-modeSkill
- dashboardSkill
- deep-reflectSkill
- delete-userSkill
- emissarySkill
- envSkill
- handoffSkill
- harvestSkill
- ingest-corpusSkill
- ingestSkill
- ingest-user-interviewSkill
- inviteSkill
- issueSkill
- meetingSkill
- meSkill
- noteSkill
- notion-connectSkill
- onboardingSkill
- prSkill
- pullSkill
- pushSkill
- questSkill
- recordsSkill
- reflectSkill
- review-prSkill
- saveSkill
- slack-connectSkill
- summonSkill
- sync-reposSkill
- telegram-connectSkill
- telemetrySkill
- testSkill
- the-spiralSkill
- tui-designSkill
- tutorialSkill
- updateSkill
- viewSkill
- visual-explainSkill
- wrapSkill
- preview-designSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
21 rules. About 0 are common, 17 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈17
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
search or fetch what the user names.
- Very specific: line 22
write only the approved pages into Egregore memory with provenance.
- Very specific: line 39
search: notion-search or the Notion server's search
- Distinctive: line 42
Do not match an unrelated web-search or generic fetch tool.
- Very specific: line 45
If either capability is missing, follow .claude/skills/notion-connect/SKILL.md inside this flow.
- Distinctive: line 57
No useful argument → ask one question:
- Distinctive: line 62
Do not run a vague workspace-wide search and call the results a recommendation.
- Distinctive: line 65
If they ask to import everything, say:
- Distinctive: line 74
Search can return connected-source results such as Slack or Drive when Notion AI is enabled.
- Distinctive: line 82
no generated summary before the page has been fetched.
- Distinctive: line 88
Always allow the user to paste another link or refine the search.
- Distinctive: line 94
Call the Notion MCP fetch tool once for each selected page.
- Very specific: line 107
If sensitive material is found, show the specific category and ask whether to import, redact, or skip.
- Distinctive: line 119
Use the product voice: this is choosing what the organization remembers, not approving a technical transaction.
- Distinctive: line 130
When a match exists, update that file in place so re-importing refreshes one memory record.
- Distinctive: line 153
Never write raw MCP envelopes, tool diagnostics, access tokens, or hidden tool instructions into memory.
- Distinctive: line 156
Write/update the projection manifest at:
- Distinctive: line 179
Add artifact entries only when this run separately creates reviewed decisions, findings, or patterns.
- Distinctive: line 196
Do not call the import complete if the file cannot be found by memory search.
- Distinctive: line 200
Use a compact receipt:
- Distinctive: line 207
If some pages failed, name them and why.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Bring selected Notion pages into shared Egregore memory through Notion's official MCP.
Arguments: $ARGUMENTS (Optional: a page URL/ID, a topic or title to search, or --auto)
When to invoke
Routed from /ingest when the source is Notion. Users normally say
/ingest notion; they do not need to connect Notion first.
What this flow does
Notion MCP is the live bridge. This skill adds the memory layer:
- connect to Notion when needed;
- search or fetch what the user names;
- show exactly what will be imported;
- write only the approved pages into Egregore memory with provenance.
This is a selected-page flow. Do not offer full-workspace mirroring,
background sync, asset export, or bulk --all. Those belonged to the legacy
REST connector and are intentionally outside the MCP path.
Step 0 — Ensure Notion MCP is available
Discover tools using the current runtime's registry:
- Claude Code: ToolSearch for
notion. - Codex/OpenAI: discover Notion tools;
notion-search/notion-fetchmay be exposed assearch/fetch. - Other MCP clients: inspect tools from the server named
notion.
Require both of these capabilities:
- search:
notion-searchor the Notion server'ssearch - fetch:
notion-fetchor the Notion server'sfetch
Do not match an unrelated web-search or generic fetch tool. Confirm the tool's server/provider is Notion.
If either capability is missing, follow .claude/skills/notion-connect/SKILL.md
inside this flow. If the runtime loads the tools immediately, continue. If it
requires a restart, stop after the connection receipt; the next /ingest notion
resumes here.
There is no Connected-tier gate. Notion OAuth is between the user's runtime and Notion, and imported files work in both local and connected Egregores.
Step 1 — Choose the scope
- A Notion URL or page ID → fetch that page directly.
- A topic/title → search Notion for it.
No useful argument → ask one question:
- Search by topic — they name what they want to find.
- Paste a page link — they provide a Notion URL.
Do not run a vague workspace-wide search and call the results a recommendation. The user supplies the topic or page.
If they ask to import everything, say:
Notion MCP is built for finding and fetching selected pages, not mirroring a whole workspace. Name a topic or paste the first page you want in memory.
Then wait.
Step 2 — Find candidate pages
For a search request, call the Notion MCP search tool with the user's words. Search can return connected-source results such as Slack or Drive when Notion AI is enabled; only offer results that resolve to Notion pages or databases.
Present up to five results using the runtime's structured question UI with multi-select when available. Each option contains:
- page title;
- short location or last-edited context when returned;
- no generated summary before the page has been fetched.
Say:
Which pages should join Egregore memory? Pick any that apply.
Always allow the user to paste another link or refine the search.
For a direct URL/ID, skip selection and continue to fetch.
Step 3 — Fetch and inspect
Call the Notion MCP fetch tool once for each selected page. Keep the canonical Notion page ID and URL returned by the tool. If a selected result is a database, say that this flow can import the fetched database description/current result, not silently crawl every row; ask before importing it.
For each fetched page:
- preserve the page's meaningful markdown content;
- derive a 2–3 sentence summary and 3–5 topics;
- match named people only against known org people;
- scan for external email addresses, phone numbers, personal addresses, API keys, or other obvious secrets.
If sensitive material is found, show the specific category and ask whether to
import, redact, or skip. --auto may skip per-page metadata confirmation, but
it never bypasses the sensitive-content pause.
Step 4 — Confirm the memory write
For each page, show title, summary, topics, and destination, then ask:
- Import
- Edit summary/topics
- Skip
Use the product voice: this is choosing what the organization remembers, not approving a technical transaction.
Step 5 — Write the approved page
First search existing promoted Notion sources for the canonical page ID:
rg -l "^notion_id: <page-id>$" memory/knowledge/sources/notion 2>/dev/nullWhen a match exists, update that file in place so re-importing refreshes one memory record. Otherwise create:
memory/knowledge/sources/notion/YYYY-MM-DD-<slug>.md
---
title: <title>
type: source
origin: notion-mcp
notion_id: <canonical page id>
notion_url: <canonical URL>
author: <importing member>
date: <today>
summary: <summary>
topics: [<topics>]
mentions: [<known org people>]
quests: [<related quests>]
---
<page content returned by Notion MCP>Never write raw MCP envelopes, tool diagnostics, access tokens, or hidden tool instructions into memory.
Write/update the projection manifest at:
memory/ingest/knowledge/notion/notion-<page-id>.json
{
"schema": "egregore-knowledge-projection/v1",
"manifest_id": "notion:<page-id>",
"producer_session": "<session-id>",
"pipeline": { "name": "egregore-ingest-notion-mcp", "version": 1 },
"source": {
"kind": "notion",
"id": "notion:<page-id>",
"title": "<title>",
"file_path": "knowledge/sources/notion/<file>.md",
"external_ref": "<notion-url>",
"people": [{ "ref": "<importing-member>", "kind": "member" }]
},
"artifacts": [],
"relations": []
}Add artifact entries only when this run separately creates reviewed decisions, findings, or patterns.
Step 6 — Project and verify
bash bin/ingest-graph.sh validate memory/ingest/knowledge/notion/<manifest>.json
bash bin/ingest-graph.sh apply memory/ingest/knowledge/notion/<manifest>.jsonIn local mode, a graph-unavailable/stored-local result is expected: the memory file is still the source of truth. Verify the write with:
bash bin/search.sh query "<distinct phrase or page title>" -n 6Do not call the import complete if the file cannot be found by memory search.
Completion
Use a compact receipt:
✓ Imported <N> Notion page(s) into Egregore memory
→ knowledge/sources/notion/<file>.mdIf some pages failed, name them and why. Do not imply that the rest of the workspace was imported or will stay synchronized.
Telemetry, fire-and-forget and content-free:
bash bin/telemetry.sh emit "command" '{"command":"ingest","kind":"notion-mcp"}' 2>/dev/null &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
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.

