Notion Knowledge Capture
OpenAIOfficialCreated by Notion Labs, IncDistributed by OpenAI
- Skill
- Workflow
- Automation and integrations
- MIT
- No issues found
AutoGineer summary
Written by AutoGineer from the skill’s own files, not by the author
This skill provides a systematic approach to transforming ephemeral chat logs and notes into durable, searchable, and structured knowledge within Notion. It guides the user through defining the content type, identifying the appropriate database, extracting key information, and performing the necessary Notion API operations to create or update pages. By following these steps, teams can ensure that decisions, how-to guides, and FAQs are properly documented, linked, and maintained.
What it does
- Defines the purpose and audience for knowledge capture.
- Identifies the correct Notion database and template for the content type.
- Extracts facts, decisions, rationale, and action items from conversations.
- Structures content into standardized formats like FAQs, decision logs, or how-to guides.
- Creates or updates Notion pages using specific API tool calls.
- Links new content to existing hub pages and related records.
When to use it
- When you need to turn a productive team chat into a permanent wiki entry.
- When documenting a technical decision and its rationale for future reference.
- When creating a how-to guide based on a troubleshooting session.
- When building an FAQ database from recurring user or team questions.
Advantages
- Ensures consistent documentation standards across the team.
- Reduces information loss by formalizing informal discussions.
- Improves discoverability through structured tagging and linking.
- Provides clear guardrails for interacting with the Notion API.
Usage examples
- “We just decided on the new API authentication flow. Can you capture this in our decision log?”
- The agent will extract the alternatives, rationale, and final decision, then create a structured entry in the decision log database.
- “Turn our recent discussion about setting up the local dev environment into a how-to guide.”
- The agent will structure the steps, prerequisites, and edge cases into a Notion page using the how-to template.
Install
Download the skill as a ZIP:
https://autogineer.com/agent-skills/openai/notion-knowledge-capture/downloadUnzip it into the cross-client skills folder of your project:
mkdir -p .agents/skills && unzip notion-knowledge-capture.zip -d .agents/skills
Documentation by Notion Labs, Inc
Knowledge Capture
Convert conversations and notes into structured, linkable Notion pages for easy reuse.
Quick start
Clarify what to capture (decision, how-to, FAQ, learning, documentation) and target audience.
Identify the right database/template in
reference/(team wiki, how-to, FAQ, decision log, learning, documentation).Pull any prior context from Notion with
Notion:search→Notion:fetch(existing pages to update/link).Draft the page with
Notion:notion-create-pagesusing the database’s schema; include summary, context, source links, and tags/owners.Link from hub pages and related records; update status/owners with
Notion:notion-update-pageas the source evolves.
Tool-call guardrails
Notion tool availability can vary by workspace. If a Notion MCP call returns
Tool <name> not found, treat that tool as unavailable for the rest of the current task. Do not retry it with different arguments or call it again later; useNotion:searchandNotion:fetchwhere sufficient.Use one literal search query per
Notion:searchcall and includefilters: {}when no narrower filter is needed. If several query variants are useful, issue separate searches instead of writingoror+inside one query string.Only pass Notion page, database, or data-source URLs/IDs to
Notion:fetch. Search can also surface external connected-source URLs; use those as context or citations, but do not feed them intofetch.Create pages with an explicit
parentand apagesarray. For database-backed pages, fetch the database first and use the returnedcollection://...data source ID.To edit existing page content, fetch the current page first, then use
Notion:notion-update-pagewithcommand: "update_content",properties: {}, and exactold_str/ full replacementnew_strpairs. For property-only edits, usecommand: "update_properties"withcontent_updates: []. The current deployed schema expects both top-level fields even when one is unused. Do not invent insertion-only commands.
Workflow
0) If Notion tools are unavailable, pause and ask the user to connect the Notion app:
Enable the bundled Notion app for this plugin or session.
Complete the Notion auth flow if prompted.
Start a new session if the tools still do not appear.
After the app is connected, finish your answer and tell the user to retry so they can continue with Step 1.
1) Define the capture
Ask purpose, audience, freshness, and whether this is new or an update.
Determine content type: decision, how-to, FAQ, concept/wiki entry, learning/note, documentation page.
2) Locate destination
Pick the correct database using
reference/*-database.mdguides; confirm required properties (title, tags, owner, status, date, relations).If multiple candidate databases, ask the user which to use; otherwise, create in the primary wiki/documentation DB.
3) Extract and structure
Extract facts, decisions, actions, and rationale from the conversation.
For decisions, record alternatives, rationale, and outcomes.
For how-tos/docs, capture steps, pre-reqs, links to assets/code, and edge cases.
For FAQs, phrase as Q&A with concise answers and links to deeper docs.
4) Create/update in Notion
Use
Notion:notion-create-pageswith the correctdata_source_id; set properties (title, tags, owner, status, dates, relations).Use templates in
reference/to structure content (section headers, checklists).If updating an existing page, fetch then edit via
Notion:notion-update-page.
5) Link and surface
Add relations/backlinks to hub pages, related specs/docs, and teams.
Add a short summary/changelog for future readers.
If follow-up tasks exist, create tasks in the relevant database and link them.
References and examples
reference/— database schemas and templates (e.g.,team-wiki-database.md,how-to-guide-database.md,faq-database.md,decision-log-database.md,documentation-database.md,learning-database.md,database-best-practices.md).examples/— capture patterns in practice (e.g.,decision-capture.md,how-to-guide.md,conversation-to-faq.md).
Files
- ATTRIBUTION.mdAdded by AutoGineer1.0 KiB
- LICENSE.txt1.0 KiB
- SKILL.md4.4 KiB
- agents/openai.yaml327 B
- assets/notion-small.svg1.5 KiB
- assets/notion.png8.3 KiB
- evaluations/README.md3.4 KiB
- evaluations/conversation-to-wiki.json2.0 KiB
- evaluations/decision-record.json2.1 KiB
- examples/conversation-to-faq.md15.9 KiB
- examples/decision-capture.md3.5 KiB
- examples/how-to-guide.md3.1 KiB
- reference/database-best-practices.md2.4 KiB
- reference/decision-log-database.md2.0 KiB
- reference/documentation-database.md2.3 KiB
- reference/faq-database.md2.0 KiB
- reference/how-to-guide-database.md1.2 KiB
- reference/learning-database.md1.3 KiB
- reference/team-wiki-database.md926 B
examples/how-to-guide.md
Example: How-To Guide from Discussion
User Request: "Save our discussion about deploying to production as a how-to guide"
Workflow
1. Extract Content from Chat
From conversation, identified:
Deployment prerequisites
Step-by-step procedure
Common issues and solutions
Best practices and tips
2. Structure as How-To
Organized into:
Overview & prerequisites
Numbered deployment steps
Verification steps
Troubleshooting section
Related resources
3. Find Location
Notion:search
query: "deployment documentation"
query_type: "internal"
filters: {}Found: Engineering Wiki → Deployment section
4. Create Guide
Notion:notion-create-pages
parent: { page_id: "deployment-section-id" }
pages: [{
properties: {
"title": "How to Deploy to Production"
},
content: "[Structured how-to guide]"
}]Output
# How to Deploy to Production
## Overview
Production deployment using GitHub Actions with zero-downtime rolling updates.
**Time Required**: 15-20 minutes | **Complexity**: Intermediate
## Prerequisites
- [ ] PR approved and merged to main
- [ ] All CI tests passing
- [ ] Database migrations reviewed
- [ ] Feature flags configured
## Deployment Steps
1. **Verify main branch is ready**
```bash
git checkout main && git pullTag release
git tag -a v1.2.3 -m "Release v1.2.3" git push origin v1.2.3Trigger deployment
GitHub Actions auto-starts from tag push
Monitor: https://github.com/org/repo/actions
Database migrations (if needed)
Auto-run in GitHub Actions
Check logs for completion
Verify deployment
Wait for health checks (2-3 min)
Test key endpoints
Check error rates in Datadog
Verification Checklist
[ ] All pods healthy in k8s dashboard
[ ] Error rate < 0.1% in last 10 min
[ ] Response time p95 < 500ms
[ ] Test login flow
[ ] Check Slack #alerts channel
Troubleshooting
Health checks failing
→ Check pod logs: kubectl logs -f deployment/api -n production
Migration errors → Rollback: Revert tag, migrations auto-rollback
High error rate → Emergency rollback: Previous tag auto-deploys via GitHub Actions
Best Practices
Deploy during low-traffic hours (2-4am PST)
Have 2 engineers available
Monitor for 30 min post-deploy
Update #engineering Slack with deploy notice
Related Docs
<mention-page url="...">Rollback Procedure</mention-page>
<mention-page url="...">Database Migration Guide</mention-page>
### 5. Make DiscoverableNotion:fetch id: "engineering-wiki-homepage"
Notion:notion-update-page page_id: "engineering-wiki-homepage" command: "update_content" properties: {} content_updates: [{ old_str: "## How-To Guides", new_str: "## How-To Guides\n- <mention-page url="...">How to Deploy to Production</mention-page>" }]
Added link in Engineering Wiki → How-To Guides section
## Key Success Factors
- Captured tribal knowledge from discussion
- Structured as actionable steps
- Included troubleshooting from experience
- Made discoverable by linking from wiki index
- Added metadata (time, complexity)Requirements and compatibility
Written for: OpenAI Codex
Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta
“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.
Security
No issues found by our static scan· No issues found
A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.
Attribution and licence
- Created by
- Notion Labs, Inc
- Publisher
- OpenAI (Official)
- Distributed by
- OpenAI
- Source
- openai/plugins · plugins/notion/skills/notion-knowledge-capture · commit d420d13
- Licence
- MIT License (redistribution allowed)
- ATTRIBUTION.md (written by AutoGineer)
- Synced
AutoGineer is not affiliated with or endorsed by Notion Labs, Inc or OpenAI.
Download ZIP
The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download notion-knowledge-capture.zip