claude_pm_workflows
CLAUDE.md1 starsChanged 5 months agoNo licenceView on GitHub
此文件由 Claude Code 在工作空间根目录自动加载到主对话上下文。每次启动新对话*必读。 本文件是骨架模板*:项目专属经验(LOCKED 段)初始为空,由 /init-project 梳理后逐步填入。 主对话开场先快速判断本工作空间是否已初始化: "检测到这是一套全新的流水线骨架,还没接入任何项目。在开始之前,我需要你提供一些*前置准备信息*: > 1. 代码仓库地址(git URL)+ 凭据方式(SSH / token / 已配好) > 2. 拉取分支(我从哪条分支拉只读快照,例 main 或 release/*) > 3. 是否需要*双向分支隔离(拉一条分支、推另一条,只推交付包;不需要就直接推 / 不推)…
- Reads credentials
In this repository23 other files it gives its agents.
- acceptance-regressionSkill
- api-contract-testSkill
- browser-acceptanceSkill
- capture-test-evidenceSkill
- dev-gray-deep-verifySkill
- extract-graphSkill
- extract-visual-baselineSkill
- generate-research-deliverableSkill
- generate-test-caseSkill
- log-change-requestSkill
- log-diff-entrySkill
- periodic-reviewSkill
- pm-prd-writerSkill
- pm-regression-deliverSkill
- pre-parallel-checkSkill
- promote-deliverableSkill
- publish-baselineSkill
- query-knowledgeSkill
- regression-checkSkill
- run-acceptance-suiteSkill
- single-page-acceptanceSkill
- sync-research-codeSkill
- write-fix-promptSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

