What does this skill do, and when should you use it?
This skill gathers existing Notion notes, specifications, OKRs, decisions, and action items to prepare meeting agendas and pre-reads. It supports status updates, decision meetings, planning, retrospectives, one-on-ones, and brainstorming. Drafts can be created and updated in Notion with source links, owners, timeboxes, decisions, risks, and preparation requests. Codex research can add sourced industry facts, benchmarks, risks, and best practices. The repository is deprecated, so current Codex skill and plugin examples should be taken from the OpenAI Plugins repository.
Confirms the meeting goal, attendees, timing, and required decisions; searches and fetches relevant Notion pages; selects a template by meeting type; creates an agenda or pre-read page in Notion; adds source links and Codex research; updates the page as plans change; and adds owners and links for follow-up tasks in relevant Notion databases.
- A project lead preparing an approval or decision meeting that depends on historical decisions and specifications in Notion.
- A team manager preparing a recurring status meeting from OKRs, action items, and risks stored in Notion.
- A product or engineering team planning a sprint or project with timeboxed agenda items and assigned owners.
- A manager preparing a one-on-one using previous notes and outstanding follow-ups.
- A team running a retrospective or brainstorming session that needs a structured meeting document.
How do you install this skill?
- Before authorizing Notion writes or updates, show the target pages, proposed content, and sharing scope, and obtain user confirmation.
- Sensitive information from internal pre-reads should not be copied into external agendas by default; access controls, redaction rules, and recovery procedures should be defined.
- Before use, verify that the referenced files, Notion MCP tool names, and remote service are available; the supplied material does not establish stable usability from mainland-China networks.
- Shell / CLI
- Network access
- Local filesystem
- MCP Server
Codex CLINotion MCP
The skill is located at skills/.curated/notion-meeting-intelligence/ in openai/skills. According to the repository instructions, run this in Codex: $skill-installer notion-meeting-intelligence. Restart Codex after installation. The repository is deprecated; current skill and plugin examples should be taken from the OpenAI Plugins repository. The supplied material does not state the license; inspect LICENSE.txt in the individual skill directory.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/openai/skills.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/skills/.curated/notion-meeting-intelligence" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Example trigger: Prepare next week's project decision meeting. Search Notion for the relevant specifications, prior decisions, and action items, then create a Notion page with the goal, agenda, owners, timeboxes, risks, and pre-reading. Provide the objective, desired outcomes or decisions, attendees, duration, date and time, and prior materials. If the Notion MCP is not connected, follow the documented setup commands, complete OAuth login, restart Codex, and then continue.
What are this skill's strengths and limitations?
- Covers the workflow from retrieving Notion context through creating and updating meeting materials.
- Includes formats for status, decision, planning, retrospective, one-on-one, and brainstorming meetings.
- Requires research claims to include source links and separates facts from opinions.
- Supports updates and a brief changelog when meeting plans change.
- Requires the Notion MCP, Notion access, and a Codex environment.
- The repository is deprecated, so its maintenance direction is no longer current.
- The supplied material provides no test suite or platform validation record.
- The repository-level license is unknown; the individual skill's LICENSE.txt must be checked.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Notion Meeting Intelligence this page ✓ OpenAI · Official | 38 · Not recommended | ★ 28k | 4mo ago | — |
| Diligence Meeting Prep ✓ Anthropic · Official | 48 · Use with care | ★ 40k | 1mo ago | Apache-2.0 |
| Client Review Prep ✓ Anthropic · Official | 44 · Not recommended | ★ 40k | 1mo ago | Apache-2.0 |
| Digital Brain Personal OS | 38 · Not recommended | ★ 18k | 13d ago | MIT |
| Contract Evidence Analyzer ✓ Anthropic · Official | 55 · Use with care | ★ 425 | 1mo ago | — |
How did FollowSkills review this skill?
The skill identifies a Notion MCP dependency and describes searching, reading, creating, and updating pages, with some source-link disclosure. It does not clearly define least privilege, per-write confirmation, sensitive-data boundaries, external-sharing controls, or rollback, so points are deducted.
The main workflow and Notion-MCP failure setup path are reasonably understandable, but referenced files are not included in the supplied material, some evaluation scenarios use tools not specified in the main workflow, and no statically verifiable execution results or CI coverage are provided. The score follows the static cap conservatively.
The audience, meeting types, template selection, and expected outputs are fairly clear. However, non-fit boundaries, exclusion triggers, and Chinese-language support are unspecified, and the core function depends on a remote Notion service without evidence of mainland-China network reachability, so points are deducted.
The documentation includes quick start guidance, staged workflow instructions, a dependency manifest, template references, examples, and evaluation files. However, license metadata is unknown, and versioning, changelog, explicit maintenance ownership, and update path are absent; the repository README also states that the repository is deprecated, so points are deducted.
The stated goal and examples for producing meeting pre-reads and agendas are concrete and could reduce manual preparation effort. However, the examples and success criteria do not provide verifiable output evidence, and output quality, research value, and two-document creation still require human review, so the score remains conservative.
The repository includes evaluation descriptions and scenario files, providing limited auditable material. They primarily define expected behavior and success criteria rather than independent execution evidence, and no key-path CI test coverage is shown, so only limited points are warranted.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →