一键导入
to-prd
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。
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
Reviews a GitHub PR and creates a pending review with editorially gated inline/body findings. Use when the user asks to review a PR or create a draft GitHub review.
Load machine-local rule overrides for a given skill from the shared ~/.agents skills directory.
Create one or more atomic commits from current changes, grouping by logical unit
Create a JIRA ticket interactively — gathers requirements through conversation, proposes the ticket, and creates it after approval
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.
Compact the current conversation into a handoff document for another agent to pick up.
| 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 repository can hold multiple PRDs at once, each in its own directory under .agent-state/prds/<slug>/.
.agent-state/is local-only and not committed to the repo. It is gitignored and exists only on the current machine. PRDs written here are working state for agents — never reference.agent-state/paths from committed artifacts (source code, PR descriptions, commit messages, issues, RFCs, or repo docs). If the PRD needs to be shared, publish it to the issue tracker or a docs system; don't link to the local path.
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.
Generate a short kebab-case slug from the PRD's problem statement (e.g. multi-prd-support, account-balance-widget). The slug is the directory name under .agent-state/prds/.
Then check .agent-state/prds/ for a collision:
.agent-state/prds/<slug>/ and write the PRD there.issue-*.md files, confirm with the user before overwriting.<slug>-2, <slug>-3, …) and use that.<repository-root>/.agent-state/prds/<slug>/PRD.md using the template below.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.