SkillRepo
Sign InSign Up
Catalog
openai/notion-knowledge-capture

openai

notion-knowledge-capture

Capture conversations and decisions into structured Notion pages; use when turning chats/notes into wiki entries, how-tos, decisions, or FAQs with proper linking.

global
short-description:Capture conversations into structured Notion pages
0installs0uses—~794
v1.0Saved Apr 5, 2026

Knowledge Capture

Convert conversations and notes into structured, linkable Notion pages for easy reuse.

Quick start

  1. Clarify what to capture (decision, how-to, FAQ, learning, documentation) and target audience.
  2. Identify the right database/template in reference/ (team wiki, how-to, FAQ, decision log, learning, documentation).
  3. Pull any prior context from Notion with Notion:notion-search → Notion:notion-fetch (existing pages to update/link).
  4. Draft the page with Notion:notion-create-pages using the database’s schema; include summary, context, source links, and tags/owners.
  5. Link from hub pages and related records; update status/owners with Notion:notion-update-page as the source evolves.

Workflow

0) If any MCP call fails because Notion MCP is not connected, pause and set it up:

  1. Add the Notion MCP:
    • codex mcp add notion --url https://mcp.notion.com/mcp
  2. Enable remote MCP client:
    • Set [features].rmcp_client = true in config.toml or run codex --enable rmcp_client
  3. Log in with OAuth:
    • codex mcp login notion

After successful login, the user will have to restart codex. You should finish your answer and tell them so when they try again 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.md guides; 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-pages with the correct data_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).
Files17
17 files · 67.8 KB

Select a file to preview

Overall Score

82/100

Grade

B

Good

Safety

85

Quality

88

Clarity

82

Completeness

75

Summary

This skill guides agents to capture conversations, discussions, and decisions into structured Notion pages across multiple content types (how-to guides, FAQs, decision records, wiki entries, learning notes). It provides a 5-step workflow: define content type and audience, locate the appropriate Notion database using reference schemas, extract and structure information, create/update pages with proper properties, and link from hub pages for discoverability.

Static Analysis Findings

1 finding

Patterns detected by deterministic static analysis before AI scoring. Hover over any finding code for detailed information and remediation guidance.

Credential Exposure
SEC-020Direct .env File Access3x in 1 file

Direct .env file access

examples/conversation-to-faq.md.env3x
85% confidenceCWE-538: Sensitive Info in Externally-Accessible File

Detected Capabilities

Notion MCP integration (search, fetch, create pages, update pages)Content type classification (decision, how-to, FAQ, wiki, learning, documentation)Database schema understanding and property mappingMarkdown formatting and structural document creationCross-linking and relation management in NotionMetadata extraction (dates, owners, status, tags)Template-based content structuring

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

capture conversation to docscreate notion page from discussiondocument architecture decisionturn chat into FAQsave meeting notesknowledge base entryteam wiki documentationdecision record

Risk Signals

INFO

References .env file access in example content

examples/conversation-to-faq.md (multiple instances in code blocks)
INFO

MCP setup instructions require OAuth login to external service

SKILL.md Workflow section 0
WARNING

Skill accesses Notion workspace and databases without explicit scoping

SKILL.md steps 2-4
INFO

External domain reference: mcp.notion.com

SKILL.md and agents/openai.yaml

Referenced Domains

External domains referenced in skill content, detected by static analysis.

github.comlocalhostmcp.notion.com

Use Cases

  • Convert a technical discussion into a how-to guide for the team wiki
  • Document an architectural decision with alternatives and rationale in a decision log
  • Transform troubleshooting conversation into FAQ entries for self-service resolution
  • Capture project learnings and incident post-mortems for organizational memory
  • Create documentation pages from meeting notes and specifications

Quality Notes

  • ✅ Excellent use case coverage: Six comprehensive examples (decision, how-to, FAQ, wiki, learning, documentation) demonstrate real-world patterns.
  • ✅ Well-structured reference documentation: Each database schema includes properties, usage examples, best practices, and views. This gives agents clear targets and property mappings.
  • ✅ Clear workflow progression: Five-step flow (define → locate → extract → create → link) is logical and actionable. Steps are neither too granular nor too abstract.
  • ✅ Strong example files: conversation-to-faq.md and decision-capture.md are detailed and show the skill in practice with real content examples.
  • ✅ MCP setup guidance: Step 0 of workflow explicitly handles the case where Notion MCP is not connected, preventing agent confusion.
  • ✅ Evaluation files included: JSON evaluation scenarios (conversation-to-wiki, decision-record) provide testable success criteria.
  • ⚠️ Limited error handling guidance: Workflow describes happy path but doesn't explain how to handle cases where the target database doesn't exist or is inaccessible.
  • ⚠️ Missing scope boundaries: Skill does not explicitly state whether agents should ask user permission before creating/updating in shared workspaces or whether there are database scope restrictions.
  • ⚠️ No guidance on updating vs. creating: Step 4 mentions 'if updating an existing page, fetch then edit via notion-update-page' but doesn't explain decision criteria for when to update vs. create new.
  • ⚠️ Limited guidance on content freshness: Skill doesn't address how to handle duplicate captures or when to merge with existing pages rather than creating new ones.
Model: claude-haiku-4-5-20251001Analyzed: Apr 5, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Add openai/notion-knowledge-capture to your library

Get Started Free

Command Palette

Search for a command to run...