菜单
Run the full story review cycle — engineering lens (sizing, sequencing, codebase fit) followed by QA lens (test strategy, risk, acceptance criteria). Use after stories have been drafted from a design conversation, before implementation begins.
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
| name | review-stories |
| description | Run the full story review cycle — engineering lens (sizing, sequencing, codebase fit) followed by QA lens (test strategy, risk, acceptance criteria). Use after stories have been drafted from a design conversation, before implementation begins. |
| disable-model-invocation | true |
Run two reviews in sequence and combine their output into a single revised story set.
The two underlying skills (dev-story-review and qa-story-review) are explicit-only and can be invoked individually for iteration. This skill chains them in the order their content assumes — the QA skill expects to read the engineering review.
Invoke the dev-story-review skill against the story files (or directory) under review. Capture its output verbatim.
The engineering review covers:
Invoke the qa-story-review skill against the same story files and the engineering review from Step 1. The QA skill's own process explicitly says: "Read the stories and any principal engineer review." It builds on the engineering output rather than re-deriving it.
The QA review covers:
Return, in this order:
Test-first bug-fix workflow — write a failing regression test before any code change, fix minimally, then verify. Use when fixing a defect in this codebase.
Extract delivery stories from a design conversation or document. Strip the conversation of noise, Example Map each decision, sequence by dependency and walking skeleton, write feature README and story files using the project template.
Reviews proposed implementation stories as a senior/principal engineer. Use after an initial product/technical discussion has produced one or more draft stories, before implementation begins. Focuses on story slicing, codebase evidence, technical design, sequencing, refactoring, assumptions, and implementation risk.
Editorial review and writing process for documents that humans will read - PR descriptions, READMEs, design docs, commit bodies, RFCs. Recursively drills from surface text to essence by asking what we're trying to say and why; includes a style guide of mechanical rules. Use when the user asks to review, sharpen, edit, or write a doc.
Rigorous agent-driven story implementation workflow — explore, plan, then test-first per module with qa-test-planner, code-reviewer, and refactoring-enforcer gates. Use when implementing a feature/story file from features/.
Reviews implementation stories from a QA/test strategy perspective. Use after stories have been shaped by product and engineering. Focuses on valuable tests, regression risk, testability, acceptance criteria, fixtures, automation, and how tests should be run.
