一键导入
product-management
Issue writing, board hygiene, and product management practices for Zenhub-based workflows
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
Issue writing, board hygiene, and product management practices for Zenhub-based workflows
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
Continue working on an OpenSpec change by creating the next artifact. Use when the user wants to progress their change, create the next artifact, or continue their workflow.
Fast-forward through OpenSpec artifact creation. Use when the user wants to quickly create all artifacts needed for implementation without stepping through each one individually.
Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.
How to write specs, name capabilities, and structure requirements. Load this when creating or reviewing proposals, specs, or capability lists.
How to invoke the openspec CLI. Load this BEFORE running any openspec commands.
Principles and patterns for writing agent definitions
| name | product-management |
| description | Issue writing, board hygiene, and product management practices for Zenhub-based workflows |
Guidelines for writing issues, maintaining board health, and managing product work in Zenhub.
Every issue should follow this structure:
| Section | Purpose | Required |
|---|---|---|
| Goal | 1-2 sentences: what and why | Yes |
| User Stories | Behavior from user/developer perspective | Yes |
| Acceptance Criteria | Observable outcomes (not implementation steps) | Yes |
| Technical Notes | Implementation hints, code pointers, related context | No |
Write issues as user stories, not implementation instructions. Stories survive technical shifts; "Write this function" becomes stale the moment the architecture changes.
Bad:
Good:
Titles should describe the outcome, not the implementation:
| Bad | Good |
|---|---|
| Wire Tools to Agents | Connect agent capabilities to the orchestration system |
| Rewrite Orca agent prompt for dispatch system | Update entry agent prompt for plan-based workflow |
| Add structured output instructions | Specialists report results in a consistent format |
Criteria should be testable observations, not code tasks:
| Bad | Good |
|---|---|
| Call planningService.approve() on user confirm | Approved plans hand off to execution |
| Mock question.ask() in test harness | Tests run in CI and cover critical paths |
| Inject JSON schema into agent prompts | Parsing succeeds without excessive retries |
Implementation details belong in a separate Technical Notes section at the bottom of the issue. This includes:
This separation means the story stays meaningful even if the implementation approach changes.
Merge when two issues describe the same work from different angles. Update the surviving issue's scope to cover both, and close the other with a reference.
Re-scope when work has naturally shifted between issues. Common pattern: narrow one issue's scope and expand another's to match where the work actually landed.
Blocking relationships are historical dependency records:
The epic body should contain:
When sub-issues are completed:
When issues are merged or re-scoped:
When reviewing the board, check for: