Publisher: Notion / OpenAI plugin catalog · Editorial profile by AI Tools Ratings · Review method
What task is this skill designed for?
Decompose a small feature specification into a plan, dependencies and tasks with observable acceptance criteria.
What input and output should you expect?
Input: The approved specification, known constraints, target task database and its schema. Provide team assignments or dates only when they have actually been agreed.
Output: A proposed requirement-to-task mapping and linked implementation plan. Creating tasks does not establish that code has been written or that a requirement has passed.
What does it need to run?
A Codex session with the Notion plugin/app connected and access to the selected pages. Database-backed work also needs the actual database schema; the available search, fetch and writing tools depend on the workspace.
Published in the Notion plugin within OpenAI’s Codex plugin examples. Requires a connected Notion app and the tools available to the current workspace.
How should you approach installation?
- Review the pinned skill and the references for the intended task.
- Enable the Notion plugin/app and authorize the relevant workspace; confirm available tools and destination permissions.
- Try the sample prompt with synthetic pages, review the output and approve the destination before allowing shared-page changes.
Installation guide: discovery, dependencies and runtime checks
What files, accounts or data can it access?
Reads accessible Notion pages and supplied material through the connected app. The workflow can create or update pages and database records when authorized. Confirm the destination and sharing scope; use synthetic material for the first draft and keep confidential details out of supplemental web searches.
What does the skill cost?
No separate skill price is stated in the reviewed source. Codex usage, Notion workspace features and any connected research service have their own charges and access limits.
What are its limits and alternatives?
A specification can omit edge cases and conflict with current behavior. Keep a clarification list and distinguish assumptions from approved scope. Task-size suggestions are planning heuristics rather than delivery estimates.
Use Linear-oriented workflows when execution already lives in Linear. Use Notion Research Documentation for evidence synthesis; this workflow is for turning agreed requirements into reviewable work.
What could you ask in a small trial?
Try this with a small sample:
Turn this synthetic feature spec into a draft plan. Map every requirement to a task and acceptance check, identify dependency order, and list missing decisions. Do not create tasks or invent estimates until the draft is approved.
How would you verify the result?
- Every requirement maps to a task or an explicit deferred decision.
- Acceptance checks describe observable behavior, including failure cases.
- Task creation uses the selected database and does not duplicate existing work.
Use a baseline and record acceptance evidence before treating a successful task as a reliable workflow.
Which source and license were checked?
Read the reviewed SKILL.md at its pinned commit · Complete reviewed folder
Repository and current publisher guidance
Checked:
MIT — identified in the reviewed Notion skill folder. Connected services have their own terms. License evidence
Version details and review scope
Source: openai/plugins/plugins/notion/skills/notion-spec-to-implementation
Reviewed commit: 0722921d5542fc593105c27bd52630babd8b8c2a
SKILL.md SHA-256: 43b304aaff38fbd4fd5d81efcefb2fd92f5450649eba8b02a2371edb4599cf3f
Source-document review. This profile covers the source workflow, stated dependencies and license evidence. See our editorial methodology for how we distinguish source reviews and hands-on evaluations.