Turn an existing conversation and codebase context into a feature specification. Organize user needs, implementation decisions, testing plans, and scope, then publish the specification to the project’s issue tracker with a label marking it ready for agent work.
把当前对话转成 spec 并发布到项目 issue tracker：不做访谈，只综合已经讨论的内容。
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
这个 skill 使用当前 conversation context 和 codebase understanding 产出 spec。不要访谈用户，只综合你已经知道的内容。
Issue tracker 和 triage label vocabulary 应该已经提供给你；如果没有，请让用户运行 /setup-matt-pocock-skills。
如果还没有探索 repo，先探索它以理解 codebase 当前状态。在 spec 中始终使用项目 domain glossary vocabulary，并遵守相关 ADRs。
草拟你准备在哪些 seams 上测试这个 feature。优先使用现有 seams，而不是新增 seams。使用尽可能高层的 seam。如果确实需要新增 seams，尽可能在最高层提出。
Seams 越少越好，理想数量是一个。与用户确认这些 seams 是否符合预期。
ready-for-agent triage label；不需要额外 triage。用户正在面对的问题，从用户视角描述。
问题的解决方案，从用户视角描述。
一份很长的编号 user stories 列表。每条 user story 使用以下格式：
这份 user stories 列表应该非常完整，覆盖 feature 的所有方面。
已作出的 implementation decisions 列表。可以包括：
不要包含具体 file paths 或 code snippets。它们可能很快过时。
例外：如果 prototype 产出的 snippet 比 prose 更精确地编码了某个决策（state machine、reducer、schema、type shape），可以内联到相关 decision 中，并简短说明它来自 prototype。只保留决策密集部分，不要放完整 working demo。
已作出的 testing decisions 列表。包括：
本 spec 范围外事项的描述。
关于 feature 的其他 notes。
</spec-template>No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Find the right skill and sequence for your current development task, from shaping an idea to implementation, debugging, and review. The guide also explains when to prototype, prepare specifications, or move work into a fresh session.
Summarize the current conversation and launch a fresh background agent to continue the work. The handoff includes references to existing artifacts and suggested skills, removes sensitive information, and can emphasize the next session’s intended focus.
Review changes from a chosen Git reference against both project coding standards and issue or specification requirements. Separate parallel reviews report rule violations, possible design problems, missing requirements, and changes beyond the intended scope.
Design modules that expose simple interfaces while hiding substantial behavior. Use shared terms and principles to assess interface complexity, decide where behavior can be swapped, and organize code so callers and tests use the same interface.
Diagnose difficult bugs and performance regressions by first building a repeatable check for the exact symptom. Minimize the reproduction, test ranked hypotheses, apply a fix, and verify the original scenario with regression tests where suitable.
Clarify project terminology and the relationships between business concepts. Check definitions against concrete scenarios and code, update GLOSSARY.md as terms are agreed, and record significant design decisions with their trade-offs when the stated criteria are met.