What does this skill do, and when should you use it?
This skill converts a Notion product specification or feature brief into connected implementation artifacts. It searches for and reads the specification, extracts requirements, acceptance criteria, constraints, priorities, and ambiguities, then creates a plan and tasks in Notion. It also links the specification, plan, and tasks and keeps status information current. It is best suited to teams already managing product and engineering work in Notion and requires a working Notion MCP connection.
Searches for a specification through Notion and fetches the selected page; parses requirements and ambiguities using bundled reference guidance; creates a quick or full implementation plan in Notion; locates and confirms the task database schema; creates tasks with objectives, acceptance criteria, dependencies, and resources; links the specification, plan, and tasks; and updates Notion pages to track status, checklists, blockers, decisions, progress updates, and milestones.
- A product manager has a Notion PRD and needs it broken into implementation phases and delivery tasks.
- An engineering lead needs dependencies, risks, and success criteria for a multi-phase feature or migration.
- A product team wants its Notion specification, execution plan, and task database connected for traceability.
- A delivery team needs recurring status updates and milestone summaries during implementation.
How do you install this skill?
- Before execution, confirm the exact Notion pages, database properties, relations, and write scope that will be created or modified.
- The Notion MCP, OAuth, and target-workspace permissions are hard dependencies; the core workflow may be unusable if connectivity or mainland-China reachability fails.
- Do not treat example plans, task counts, dates, or technical choices as actual execution results; verify them against the real specification and database schema.
- Add guidance for sensitive-data handling, least privilege, failure recovery, rollback, and version maintenance.
- Shell / CLI
- Network access
- Local filesystem
- MCP Server
Notion MCPCodex CLI
The skill is located at skills/.curated/notion-spec-to-implementation. The README says to install curated skills in Codex with $skill-installer notion-spec-to-implementation, then restart Codex. The source does not document another installation method or any cost.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/openai/skills.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/skills/.curated/notion-spec-to-implementation" ~/.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?
Once installed, send your agent any of these to trigger it:
- Turn the user settings redesign spec in Notion into an implementation plan and tasks, then track progress.
Connect Notion MCP, then ask Codex to process a Notion specification, for example: “Turn the user settings redesign spec in Notion into an implementation plan and tasks, then track progress.” The skill searches first; if multiple pages match, the user must choose one. If Notion MCP is unavailable, follow the skill’s setup instructions to add the MCP, enable the remote MCP client, complete OAuth login, and restart Codex.
What are this skill's strengths and limitations?
- Covers specification reading, planning, task creation, linking, and progress tracking in one workflow.
- Explicitly links specifications, plans, and tasks for delivery traceability.
- Supports different planning depth for simple changes and multi-phase work.
- Provides guidance for task sizing, properties, acceptance criteria, dependencies, and milestone updates.
- Requires Notion MCP connectivity and authentication.
- Assumes the team uses Notion pages and a task database.
- The source provides no test suite, platform validation results, or standalone skill license evidence.
- The repository README marks the repository as deprecated and directs users to the OpenAI Plugins repository for current examples.
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 Spec-to-Delivery Planner this page ✓ OpenAI · Official | 43 · Not recommended | ★ 28k | 4mo ago | — |
| Product Architect | 54 · Use with care | ★ 115 | 1mo ago | MIT |
| Kanban AI | 52 · Use with care | ★ 25 | 7mo ago | Apache-2.0 |
| vibe-check Product Planning Coach | 62 · Recommended | ★ 619 | 3mo ago | MIT |
| Obsidian CLI Assistant | 46 · Use with care | ★ 50k | 1mo ago | MIT |
How did FollowSkills review this skill?
The skill makes its Notion MCP dependency and OAuth-based page creation/update flow visible, with a reasonably apparent data path. However, it does not require user confirmation before external writes, and it omits sensitive-spec handling, least-privilege guidance, rollback, and recovery procedures. Official OpenAI provenance supports attribution only and does not add safety points.
The workflow is internally coherent and includes ambiguity handling plus feedback for an unconnected Notion MCP. However, several referenced files are not supplied, tool parameters and database schemas are environment-dependent, and there is no statically verifiable execution evidence or comprehensive abnormal-input handling, so the static ceiling requires a conservative deduction.
The audience, inputs, and primary scenarios are reasonably clear, covering PRDs, features, migrations, and UI specifications. Boundaries for non-fit cases and trigger exclusions are missing, Chinese-language behavior and mainland-China reachability are unspecified, and the core capability depends entirely on the Notion MCP, so points are deducted.
The skill has clear sections, progressive workflow steps, reference and example directories, and evaluation scenarios. Installation guidance, versioning, changelog, maintenance ownership, update path, and skill-specific license information are incomplete; the shared repository README also marks the repository deprecated, warranting a deduction.
The skill provides directly reusable structures for specification parsing, phased planning, task decomposition, linking, and progress tracking, giving it meaningful workflow value. However, the claimed creation outcomes are declarative examples rather than verified executions, and database compatibility, task sizing, correctness, and completeness still require substantial human review, so points are deducted.
Committed evaluation scenarios, expected behaviors, success criteria, and several end-to-end examples provide limited auditable evidence. There is no real CI, key-path test suite, execution log, or independent corroboration, and the example outcomes cannot be independently reproduced from the supplied static files, so points are deducted.
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 →