notion-knowledge-capture — Codex skill: what it does, how to install
This skill turns conversations and notes into linked Notion pages for wikis, how-tos, decisions, and FAQs. Use it when chat knowledge needs a reusable structure.
npx skills add openai/plugins --skill notion-knowledge-capture -a codexWhat notion-knowledge-capture does
The skill parses a conversation or notes, identifies the material type, and drafts a structured Notion page. It covers decisions, how-to guides, FAQs, learning notes, and documentation. Pages can include a summary, context, source links, tags, and owners.
It checks reference/ for a suitable database or template, then retrieves related Notion context with Notion:search and Notion:fetch. New pages use Notion:notion-create-pages; existing content is edited with Notion:notion-update-page. The workflow also links pages to hubs and related records. Notion tools must be connected to the workspace first.
Install it when Codex should turn chat output into maintained Notion knowledge. It is a poor fit if the workspace cannot provide the Notion tools.
What it helps with
- record a discussion decision in a decision log
- turn raw notes into a team how-to page
- convert a conversation into a linked FAQ
- connect a new page to related Notion records
Example prompts for the agent
- Turn this discussion into a Notion how-to page and include the source links.
- Use `Notion:search` to find the related page, then update it with the decision.
- Create an FAQ from this conversation using the matching template in `reference/`.
How to install notion-knowledge-capture
1Skills CLI (Vercel)
npx skills add openai/plugins --skill notion-knowledge-capture -a codex2Manually: put the files in place
.agents/skills/notion-knowledge-capture/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add openai/plugins --skill notion-knowledge-capture -a claude-code2Manually: put the files in place
~/.claude/skills/notion-knowledge-capture/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/notion-knowledge-capture/
Manually: put the files in place
.cursor/skills/notion-knowledge-capture/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install openai/plugins notion-knowledge-capture2Manually: put the files in place
.github/skills/notion-knowledge-capture/SKILL.mdPlatform CLI
gemini skills install https://github.com/openai/plugins --path plugins/notion/skills/notion-knowledge-captureManually: put the files in place
.devin/skills/notion-knowledge-capture/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set201
The whole set →Similar
Questions about notion-knowledge-capture
How do I install notion-knowledge-capture in Codex?
Run npx skills add openai/plugins --skill notion-knowledge-capture or npx skills add openai/plugins --skill notion-knowledge-capture -a codex. The skill file is placed at .agents/skills/notion-knowledge-capture/SKILL.md.
What does notion-knowledge-capture do?
It turns conversations and notes into structured Notion pages. The workflow selects a content type, retrieves existing context, creates or updates a page, and links it to related records.
What does notion-knowledge-capture need to work?
Notion tools must be connected to the workspace. The skill uses Notion:search, Notion:fetch, Notion:notion-create-pages, and Notion:notion-update-page.
Source text
SKILL.md · MIT
---
name: notion-knowledge-capture
description: Capture conversations and decisions into structured Notion pages; use when turning chats/notes into wiki entries, how-tos, decisions, or FAQs with proper linking.
metadata:
short-description: Capture conversations into structured Notion pages
---
# 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:search` → `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.
## 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; use `Notion:search` and `Notion:fetch` where sufficient.
- Use one literal search query per `Notion:search` call and include `filters: {}` when no narrower filter is needed. If several query variants are useful, issue separate searches instead of writing `or` or `+` 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 into `fetch`.
- Create pages with an explicit `parent` and a `pages` array. For database-backed pages, fetch the database first and use the returned `collection://...` data source ID.
- To edit existing page content, fetch the current page first, then use `Notion:notion-update-page` with `command: "update_content"`, `properties: {}`, and exact `old_str` / full replacement `new_str` pairs. For property-only edits, use `command: "update_properties"` with `content_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:
1. Enable the bundled Notion app for this plugin or session.
2. Complete the Notion auth flow if prompted.
3. 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.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`).
© Notion · MIT · openai/plugins