[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77JTYBEXB485Y7MXTXBX0B7":3,"skill-same:01M77JTYBEXB485Y7MXTXBX0B7":48},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M77JTYBEXB485Y7MXTXBX0B7","iterate-planning",null,"基于 Ralph Loops 三阶段工作流理念，适配 OpenClaw 架构。\n需求迭代工作流：需求讨论 → 计划拆解 → 迭代执行。\n触发条件：用户说\"讨论需求\"、\"开始计划\"、\"迭代执行\"、\"需求访谈\"","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fi\u002Fiterate-planning\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: iterate-planning\ndescription: |\n  基于 Ralph Loops 三阶段工作流理念，适配 OpenClaw 架构。\n  需求迭代工作流：需求讨论 → 计划拆解 → 迭代执行。\n  触发条件：用户说\"讨论需求\"、\"开始计划\"、\"迭代执行\"、\"需求访谈\"\n  \n---\n\n# 需求迭代工作流 (Iterate Planning)\n\n基于 Ralph Loops 三阶段工作流，适配 OpenClaw 原生实现。\n\n## 核心哲学\n\n> Human roles shift from \"telling the agent what to do\" to \"engineering conditions where good outcomes emerge naturally through iteration.\"\n\n三个原则：\n- **Context is scarce** — 保持每次迭代精简\n- **Plans are disposable** — 漂移的计划重新生成比修复更划算\n- **Backpressure beats direction** — 工程化环境让错误的输出自动被拒绝\n\n## 三阶段工作流\n\n```\n┌─────────────────────────────────────────────────────────────────────┐\n│ Phase 1: 需求访谈                                                      │\n│ 结构化对话 → 识别JTBD → 拆分Topics → 产出 specs\u002F*.md                    │\n├─────────────────────────────────────────────────────────────────────┤\n│ Phase 2: 计划                                                          │\n│ Gap分析(specs vs code) → 产出 IMPLEMENTATION_PLAN.md                  │\n├─────────────────────────────────────────────────────────────────────┤\n│ Phase 3: 迭代执行                                                      │\n│ 每次一个任务 → 全新上下文 → 验证 → 提交 → 下一任务                        │\n└─────────────────────────────────────────────────────────────────────┘\n```\n\n---\n\n## Phase 1: 需求访谈\n\n**目标**：在动手写代码之前，真正理解要做什么。\n\n**触发**：用户说\"讨论需求\"、\"需求访谈\"、\"帮我理清需求\"\n\n**流程**：\n1. 使用 `templates\u002Frequirements-interview.md` 模板进行结构化访谈\n2. 识别 JTBD（Jobs to Be Done）— 用户真正要解决的Outcome，不是功能列表\n3. 把 JTBD 拆分成 Topics of Concern（每个 topic 一个独立维度）\n4. 用\"一个句子，不带and\"测试 — 能说出来的是一个topic，说不出来的是多个\n5. 每个 Topic 写一份 `specs\u002Ftopic-xxx.md`\n\n**完成标志**：\n- 每个 Topic 都有 `specs\u002F*.md`\n- 每个 spec 包含：需求描述、验收标准、边界情况\n\n**交付物**：\n```\nproject\u002F\n└── specs\u002F\n    ├── topic-a.md\n    ├── topic-b.md\n    └── ...\n```\n\n---\n\n## Phase 2: 计划\n\n**目标**：生成可执行的任务清单，不写代码。\n\n**触发**：需求完备后，用户说\"开始计划\"、\"可以拆任务了\"\n\n**流程**：\n1. 读取 `specs\u002F*.md` 所有需求\n2. 如有现有代码，研究 codebase\n3. 对比 specs vs code（Gap Analysis）\n4. 生成 `IMPLEMENTATION_PLAN.md`（带优先级的任务列表）\n\n**模板**：`templates\u002Fplanning-prompt.md`\n\n**完成标志**：\n- `IMPLEMENTATION_PLAN.md` 存在\n- 每个任务有优先级标注\n- 任务列表完整覆盖所有 specs\n\n**交付物**：\n```\nproject\u002F\n├── specs\u002F\n├── IMPLEMENTATION_PLAN.md\n└── ...\n```\n\n---\n\n## Phase 3: 迭代执行\n\n**目标**：每次做一个任务，全新上下文，保持 agent 在\"聪明区域\"。\n\n**触发**：计划完备后，用户说\"开始执行\"、\"迭代构建\"\n\n**核心洞察**：\n- **一次一任务** — 保持上下文精简，agent 保持高效\n- **全新上下文** — 每次迭代从头开始，之前的错误不累积\n- **验证 + 提交** — 每个任务完成后必须验证才能提交\n\n**流程**：\n1. 读取 `IMPLEMENTATION_PLAN.md`\n2. 选最高优先级任务\n3. 研究 codebase（不要假设未实现）\n4. 执行任务\n5. 运行验证（backpressure）\n6. 更新 plan（标记完成）\n7. 提交 commit\n8. 循环直到 plan 完成\n\n**模板**：`templates\u002Fbuild-prompt.md`\n\n**完成标志**：\n- `IMPLEMENTATION_PLAN.md` 所有任务标记 done\n- 每次迭代有对应 commit\n\n---\n\n## 触发词指南\n\n| 用户说 | Agent 动作 |\n|--------|-----------|\n| \"讨论需求\"、\"需求访谈\" | 启动 Phase 1 需求访谈 |\n| \"开始计划\"、\"可以拆任务了\" | 启动 Phase 2 计划生成 |\n| \"开始执行\"、\"迭代构建\" | 启动 Phase 3 迭代执行 |\n| \"Ralph Loop\"、\"迭代\" | 询问用户要哪个 phase |\n\n---\n\n## 文件结构\n\n```\niterate-planning\u002F\n├── SKILL.md                    # 本文件\n├── AGENTS.md                   # 操作员指南\n└── templates\u002F\n    ├── requirements-interview.md  # 需求访谈模板\n    ├── planning-prompt.md          # 计划生成提示词\n    └── build-prompt.md            # 构建执行提示词\n```\n\n---\n\n## 为什么有效\n\n| 问题 | 解法 |\n|------|------|\n| 需求不清晰就动手 | Phase 1 强制结构化访谈 |\n| 计划赶不上变化 | Plans are disposable — 重新生成比修复更划算 |\n| 上下文膨胀导致幻觉 | 一次一任务，全新上下文 |\n| 错误累积难以追溯 | 每次验证 + 提交，自然 checkpoint |\n","# 需求迭代工作流 (Iterate Planning)\n\n基于 Ralph Loops 三阶段工作流，适配 OpenClaw 原生实现。\n\n## 核心哲学\n\n> Human roles shift from \"telling the agent what to do\" to \"engineering conditions where good outcomes emerge naturally through iteration.\"\n\n三个原则：\n- **Context is scarce** — 保持每次迭代精简\n- **Plans are disposable** — 漂移的计划重新生成比修复更划算\n- **Backpressure beats direction** — 工程化环境让错误的输出自动被拒绝\n\n## 三阶段工作流\n\n```\n┌─────────────────────────────────────────────────────────────────────┐\n│ Phase 1: 需求访谈                                                      │\n│ 结构化对话 → 识别JTBD → 拆分Topics → 产出 specs\u002F*.md                    │\n├─────────────────────────────────────────────────────────────────────┤\n│ Phase 2: 计划                                                          │\n│ Gap分析(specs vs code) → 产出 IMPLEMENTATION_PLAN.md                  │\n├─────────────────────────────────────────────────────────────────────┤\n│ Phase 3: 迭代执行                                                      │\n│ 每次一个任务 → 全新上下文 → 验证 → 提交 → 下一任务                        │\n└─────────────────────────────────────────────────────────────────────┘\n```\n\n---\n\n## Phase 1: 需求访谈\n\n**目标**：在动手写代码之前，真正理解要做什么。\n\n**触发**：用户说\"讨论需求\"、\"需求访谈\"、\"帮我理清需求\"\n\n**流程**：\n1. 使用 `templates\u002Frequirements-interview.md` 模板进行结构化访谈\n2. 识别 JTBD（Jobs to Be Done）— 用户真正要解决的Outcome，不是功能列表\n3. 把 JTBD 拆分成 Topics of Concern（每个 topic 一个独立维度）\n4. 用\"一个句子，不带and\"测试 — 能说出来的是一个topic，说不出来的是多个\n5. 每个 Topic 写一份 `specs\u002Ftopic-xxx.md`\n\n**完成标志**：\n- 每个 Topic 都有 `specs\u002F*.md`\n- 每个 spec 包含：需求描述、验收标准、边界情况\n\n**交付物**：\n```\nproject\u002F\n└── specs\u002F\n    ├── topic-a.md\n    ├── topic-b.md\n    └── ...\n```\n\n---\n\n## Phase 2: 计划\n\n**目标**：生成可执行的任务清单，不写代码。\n\n**触发**：需求完备后，用户说\"开始计划\"、\"可以拆任务了\"\n\n**流程**：\n1. 读取 `specs\u002F*.md` 所有需求\n2. 如有现有代码，研究 codebase\n3. 对比 specs vs code（Gap Analysis）\n4. 生成 `IMPLEMENTATION_PLAN.md`（带优先级的任务列表）\n\n**模板**：`templates\u002Fplanning-prompt.md`\n\n**完成标志**：\n- `IMPLEMENTATION_PLAN.md` 存在\n- 每个任务有优先级标注\n- 任务列表完整覆盖所有 specs\n\n**交付物**：\n```\nproject\u002F\n├── specs\u002F\n├── IMPLEMENTATION_PLAN.md\n└── ...\n```\n\n---\n\n## Phase 3: 迭代执行\n\n**目标**：每次做一个任务，全新上下文，保持 agent 在\"聪明区域\"。\n\n**触发**：计划完备后，用户说\"开始执行\"、\"迭代构建\"\n\n**核心洞察**：\n- **一次一任务** — 保持上下文精简，agent 保持高效\n- **全新上下文** — 每次迭代从头开始，之前的错误不累积\n- **验证 + 提交** — 每个任务完成后必须验证才能提交\n\n**流程**：\n1. 读取 `IMPLEMENTATION_PLAN.md`\n2. 选最高优先级任务\n3. 研究 codebase（不要假设未实现）\n4. 执行任务\n5. 运行验证（backpressure）\n6. 更新 plan（标记完成）\n7. 提交 commit\n8. 循环直到 plan 完成\n\n**模板**：`templates\u002Fbuild-prompt.md`\n\n**完成标志**：\n- `IMPLEMENTATION_PLAN.md` 所有任务标记 done\n- 每次迭代有对应 commit\n\n---\n\n## 触发词指南\n\n| 用户说 | Agent 动作 |\n|--------|-----------|\n| \"讨论需求\"、\"需求访谈\" | 启动 Phase 1 需求访谈 |\n| \"开始计划\"、\"可以拆任务了\" | 启动 Phase 2 计划生成 |\n| \"开始执行\"、\"迭代构建\" | 启动 Phase 3 迭代执行 |\n| \"Ralph Loop\"、\"迭代\" | 询问用户要哪个 phase |\n\n---\n\n## 文件结构\n\n```\niterate-planning\u002F\n├── SKILL.md                    # 本文件\n├── AGENTS.md                   # 操作员指南\n└── templates\u002F\n    ├── requirements-interview.md  # 需求访谈模板\n    ├── planning-prompt.md          # 计划生成提示词\n    └── build-prompt.md            # 构建执行提示词\n```\n\n---\n\n## 为什么有效\n\n| 问题 | 解法 |\n|------|------|\n| 需求不清晰就动手 | Phase 1 强制结构化访谈 |\n| 计划赶不上变化 | Plans are disposable — 重新生成比修复更划算 |\n| 上下文膨胀导致幻觉 | 一次一任务，全新上下文 |\n| 错误累积难以追溯 | 每次验证 + 提交，自然 checkpoint |\n",{"name":5,"description":24},"基于 Ralph Loops 三阶段工作流理念，适配 OpenClaw 架构。\n需求迭代工作流：需求讨论 → 计划拆解 → 迭代执行。\n触发条件：用户说\"讨论需求\"、\"开始计划\"、\"迭代执行\"、\"需求访谈\"\n","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fi\u002Fiterate-planning",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill iterate-planning",{"tool":40,"command":41},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill iterate-planning",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill iterate-planning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fi\u002Fiterate-planning\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]