Full pipeline: evaluation -> spec -> implementation -> review -> QA
中文简介正在准备中。当前显示原文说明。
QA + bugfix cycle until it passes
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Runs a QA validation cycle followed by bugfix until all criteria pass clean. Useful for validating implementations without the full build-feature pipeline.
/qa-cycle
Before invoking the QA agent, run the project verification commands. The specific commands are in the "CLI commands" section of CLAUDE.md:
npm test) — record result and outputnpm run lint) — record result and outputInvoke the QA agent using Task tool with model: "sonnet" (execution tier):
.claude/agents/qa.md to assume the QA roleIf QA reports bugs (including test/lint failures), invoke the Bugfix agent using Task tool with model: "sonnet" (execution tier):
.claude/agents/bugfix.md to assume the Bugfix roleReturn to Step 1 (automated verification) to re-validate after the bugfix. Maximum 3 verification-QA-bugfix cycles to prevent infinite loops.
Present the result:
User: /qa-cycle
QA (sonnet) — Cycle 1: 2 of 5 criteria pass. Bug: form validation missing on email field.
Bugfix (sonnet) — Added email regex validation to UserForm component.
QA (sonnet) — Cycle 2: 5 of 5 criteria pass. 0 bugs.
Result: Approved.
When spawning QA or Bugfix agents via the Task tool, always use subagent_type: "general-purpose". Guild agent role names are NOT valid Claude Code subagent_types.
Example:
Task tool with:
subagent_type: "general-purpose"
model: "sonnet"
prompt: "Read .claude/agents/qa.md and assume that role. Then: [task description]"
The model parameter is resolved from the step's model-tier: qa-validate and bugfix use execution→"sonnet".
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Full pipeline: evaluation -> spec -> implementation -> review -> QA
中文简介正在准备中。当前显示原文说明。
Convenes multiple agents to debate an important decision
中文简介正在准备中。当前显示原文说明。
Create a pull request from the current branch with structured summary
中文简介正在准备中。当前显示原文说明。
Discipline skill — systematic debugging process. Use when encountering any bug, debug issue, test failure, broken function, or unexpected behavior, before proposing fixes.
中文简介正在准备中。当前显示原文说明。
Enriches CLAUDE.md by exploring the project and specializes agents to the real stack
中文简介正在准备中。当前显示原文说明。
Incremental re-specialization — re-scans the project and updates only auto-generated zones in CLAUDE.md and agents
中文简介正在准备中。当前显示原文说明。