メニュー
Turn the current conversation context into a local markdown PRD under `.workflows/prd/`. Use when user wants to create a PRD from the current context.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
Create git commits using Conventional Commits. Use when the user asks to commit code, prepare a commit, write a commit message, or standardize commit history with conventional commit types, scopes, breaking-change markers, and safe git workflow checks.
Fetch dependency source code so agents can inspect real implementations, tests, and version-specific behavior. Use when docs or types are insufficient, when debugging library internals, or when tasks require source-backed evidence. Triggers include "fetch source for", "read the source of", "how does X work internally", "get the implementation of", and "opensrc path".
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
Break a plan, spec, or PRD into independently-grabbable local markdown issues under `.workflows/` using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tasks, or break down work into issues.
Prepare publishable SDK package changes for push and PR in better-webhook. Use when changes under packages/* need a Changeset, SDK docs or README updates, full verification, and a release-ready PR summary before code is pushed to GitHub.
| name | to-prd |
| description | Turn the current conversation context into a local markdown PRD under `.workflows/prd/`. Use when user wants to create a PRD from the current context. |
This skill takes the current conversation context and codebase understanding and produces a PRD. Do NOT interview the user — just synthesize what you already know.
Explore the repo to understand the current state of the codebase, if you haven't already. Use the project's domain glossary vocabulary throughout the PRD, and respect any ADRs in the area you're touching.
Sketch out the major modules you will need to build or modify to complete the implementation. Actively look for opportunities to extract deep modules that can be tested in isolation.
A deep module (as opposed to a shallow module) is one which encapsulates a lot of functionality in a simple, testable interface which rarely changes.
Check with the user that these modules match their expectations. Check with the user which modules they want tests written for.
.workflows/prd/.Use this file convention unless the repo already has a stronger .workflows/ convention:
.workflows/prd/YYYY-MM-DD/NNN-short-kebab-title/prd.mdYYYY-MM-DD is today's dateNNN is the next available sequence number within that date foldershort-kebab-title is a concise slug derived from the PRD titleExample: .workflows/prd/2026-05-01/001-user-authentication/prd.md
If implementation tasks are later created from or for this PRD, they should be nested under this PRD folder in tasks/.
The problem that the user is facing, from the user's perspective.
The solution to the problem, from the user's perspective.
A LONG, numbered list of user stories. Each user story should be in the format of:
This list of user stories should be extremely extensive and cover all aspects of the feature.
A list of implementation decisions that were made. This can include:
Do NOT include specific file paths or code snippets. They may end up being outdated very quickly.
A list of testing decisions that were made. Include:
A description of the things that are out of scope for this PRD.
Any further notes about the feature.