Analyze
Document-driven agent pipeline for software R&D: analyze → plan → review → develop → test. Portable skills for Cursor, Claude Code & Codex.
npx -y skills add Colacn/agent-pipeline --skill analyzeAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use this skill when the user needs intent clarification, ambiguity resolution, or structured analysis without implementation advice. It asks clarifying questions when uncertain and analyzes only user-provided information after confirmation; use PRD-style packaging only when explicitly requested.
SKILL.md
2.8 KB, as published. Nobody here has run it
Analyze
入口：analyze 为本 Skill 名；部分 IDE（如 Cursor）可用子代理名 analyst 作隔离上下文入口，SOP 仍以本文件为准。见 references/guide-skill-subagent.md。
Instructions
- 完整执行规范见
references/execution-playbook.md（优先通读）。走流水线时：有外部依据则scripts/bootstrap-run.sh+ ingest/record-urls；否则首次落盘前 bootstrap。 - 路由决策（首轮）：按
references/workflow-grading.md判定 L0–L3；L1 轻量可不建runs/；L2+ 或显式流水线入口须 bootstrap。 - 按 execution-playbook「输入源与解析范围」收拢信息；定稿前按
references/assumptions-protocol.md显式列出假设与可测验收。 - 不确定时走「轮次 A — 待澄清」；确认后「轮次 B — 分析交付」。
- 流水线内口径歧义：阻塞项未清不进 plan。
- 写入仓库前按项目约定征得用户同意（若适用）。
- 流水线硬门禁：
references/workflow-pipeline.md（项目AGENTS.md若有则叠加）。 - 内容边界：
analyze.requirements.md只写要什么 + 验收 + 范围；技术细节交给 plan skill。 - 需求清单体例：极短标题 + 编号要点；不堆平台词。
Scripts
在业务仓库根目录执行；全局安装时路径为 ~/.agents/skills/analyze/scripts/ 或各 IDE 映射目录。
On-demand references
references/assumptions-protocol.md— 假设显式化、边界三档references/playbook-map.md— 流程与边界references/handoff-checklist.md— 需求包交接references/execution-playbook.md— 完整 SOPreferences/workflow-light-task.md— L1 轻量通道
When not to use
- 用户要写代码、出方案（见
develop/planskill）。 - 用户要评审、拍板（见
reviewskill）。