菜单
Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Automate GitHub release creation and changelog generation from Conventional Commits using changelogithub — includes GitHub release mechanics, tag-based triggers, required permissions, and fetch-depth gotcha. Use when setting up GitHub releases, generating changelogs from commits, using changelogithub, or configuring v* tag triggers and contents:write permissions.
Automate npm package publishing via GitHub Actions for single-package repos and independent monorepo packages, including bumpp version tags, GitHub release notes, trusted publishing, provenance, and package-scoped release tags. Use when setting up or modifying npm publish workflows, npm release pipelines, version bumping, package-scoped monorepo releases, changelogithub release notes, trusted publishing, provenance badges, NPM_TOKEN, or OIDC publishing.
Write readable, maintainable code through disciplined naming, small functions, and clean error handling. Use when the user mentions "code review", "naming conventions", "function too long", "code smells", "readable code", "boy scout rule", "single responsibility", or "unit test quality". Also trigger when reviewing pull requests for readability, refactoring messy functions, debating comment styles, or improving error handling patterns. Covers SRP, comment discipline, formatting, and unit testing. For refactoring techniques, see refactoring-patterns. For architecture, see clean-architecture.
Decide where code lives — the directory tree, module and package boundaries, and the layout inside a file. Use when starting a new project or directory tree, placing a new file/class/function, grouping code into modules or packages, splitting an oversized file or module, naming directories/packages/files, separating source from generated build artifacts, or auditing an existing codebase's structure.
Composition skill which invokes sub-skills for coding tasks. It is a meta-skill that orchestrates the use of other coding-related skills.
Write clear, useful in-code comments and documentation that capture what the code cannot say for itself. Use this skill whenever writing or revising comments, docstrings, interface/API documentation, function or class headers, or inline explanations — and whenever reviewing code for comment quality or being asked to "document," "add comments," "explain in comments," or improve existing comments. Apply it even when the request only mentions writing the code, since fresh code is the moment to document it well.
| name | to-prd |
| description | Turn the current conversation context into a PRD and publish it to the project issue tracker. 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.
A PRD is a Parent Target Issue whose body is a product and implementation plan: krutrimbox discovers it (when it is labeled ready-for-agent and has no parent) and walks the Implementation Issues that the follow-up to-issues workflow creates as its native sub-issues.
Invoke the github-labels skill before publishing so the PRD issue gets the correct GitHub labels.
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 seams at which you're going to test the feature. Existing seams should be preferred to new ones. Use the highest seam possible. If new seams are needed, propose them at the highest point you can. The fewer seams across the codebase, the better - the ideal number is one.
Check with the user that these seams match their expectations.
needs-triage. Do not apply ready-for-agent yet; a Parent Target Issue becomes ready only after the follow-up to-issues workflow has created and linked all its Implementation Issues, at which point to-issues applies ready-for-agent to the PRD.Issue title format — follow Conventional Commits:
type(scope): short imperative description
feat, fix, refactor, perf, docs, test, chore, ci, style, buildauth, cli, api, ui, db) — keep it short and lowercase! after type/scope signals a breaking change: feat!(auth): … or refactor(api)!: …Examples: feat(auth): add OAuth2 login, fix(cli): handle missing config, refactor!(api): remove legacy endpoints
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.
Exception: if a prototype produced a snippet that encodes a decision more precisely than prose can (state machine, reducer, schema, type shape), inline it within the relevant decision and note briefly that it came from a prototype. Trim to the decision-rich parts — not a working demo, just the important bits.
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.