{"id":"1bd192ec-c058-4fb4-aa2e-437e2f5573a4","entityType":"agent","slug":"clawhub-axelhu-superpowers-writing-plans","name":"Writing Plans","canonicalUrl":"https://www.xpersona.co/agent/clawhub-axelhu-superpowers-writing-plans","canonicalPath":"/agent/clawhub-axelhu-superpowers-writing-plans","generatedAt":"2026-10-09T21:00:33.688Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T17:57:15.398Z","emptyReason":null},"description":"Use when you have a spec or requirements for a multi-step task, before touching code - guides writing comprehensive implementation plans with bite-sized task... Skill: Writing Plans Owner: axelhu Summary: Use when you have a spec or requirements for a multi-step task, before touching code - guides writing comprehensive implementation plans with bite-sized task... Tags: latest:1.0.1 Version history: v1.0.1 | 2026-03-26T09:05:26.564Z | user OpenClaw-adapted skill for Superpowers development methodology. v1.0.0 | 2026-03-26T06:25:13.982Z | user Initial release: OpenClaw-adapted","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 2.2K downloads reported by the source. Last updated 10/9/2026.","installCommand":"clawhub skill install s172yaxxd2drm0sc92554g9aq983hegj:superpowers-writing-plans","sourceUrl":"https://clawhub.ai/axelhu/superpowers-writing-plans","homepage":"https://clawhub.ai/axelhu/skills/superpowers-writing-plans","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/axelhu/superpowers-writing-plans","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/axelhu/skills/superpowers-writing-plans","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":55,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Use when you have a spec or requirements for a multi-step task, before touching code - guides writing comprehensive implementation plans with bite-sized task..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T17:57:15.398Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T17:57:15.398Z","emptyReason":null},"stars":null,"forks":null,"downloads":2169,"packageName":null,"latestVersion":"1.0.1","tractionLabel":"2.2K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T17:57:15.397Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T17:57:15.398Z","lastCrawledAt":"2026-10-09T17:57:15.397Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-10T17:57:15.397Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.1","createdAt":"2026-03-26T09:05:26.564Z","changelog":"OpenClaw-adapted skill for Superpowers development methodology.","fileCount":3,"zipByteSize":4469},{"version":"1.0.0","createdAt":"2026-03-26T06:25:13.982Z","changelog":"Initial release: OpenClaw-adapted skill.","fileCount":2,"zipByteSize":3312}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s172yaxxd2drm0sc92554g9aq983hegj:superpowers-writing-plans","setupComplexity":"low","setupSteps":["Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-axelhu-superpowers-writing-plans/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-axelhu-superpowers-writing-plans/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-axelhu-superpowers-writing-plans/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-axelhu-superpowers-writing-plans/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-axelhu-superpowers-writing-plans/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-axelhu-superpowers-writing-plans/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T21:00:33.688Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-axelhu-superpowers-writing-plans/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-axelhu-superpowers-writing-plans/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-axelhu-superpowers-writing-plans/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-axelhu-superpowers-writing-plans/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-09T17:57:15.398Z","emptyReason":null},"readme":"Skill: Writing Plans\n\nOwner: axelhu\n\nSummary: Use when you have a spec or requirements for a multi-step task, before touching code - guides writing comprehensive implementation plans with bite-sized task...\n\nTags: latest:1.0.1\n\nVersion history:\n\nv1.0.1 | 2026-03-26T09:05:26.564Z | user\n\nOpenClaw-adapted skill for Superpowers development methodology.\n\nv1.0.0 | 2026-03-26T06:25:13.982Z | user\n\nInitial release: OpenClaw-adapted skill.\n\nArchive index:\n\nArchive v1.0.1: 3 files, 4469 bytes\n\nFiles: skill-card.md (2028b), SKILL.md (5615b), _meta.json (144b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: superpowers-writing-plans\ndescription: Use when you have a spec or requirements for a multi-step task, before touching code - guides writing comprehensive implementation plans with bite-sized tasks, TDD, and DRY/YAGNI principles\n---\n\n# Superpowers Writing Plans - 写实现计划\n\n## 概述\n\n写全面的实现计划，假设执行者对代码库零上下文、品味可疑。记录他们需要知道的一切：每个任务要修改的文件、代码、可能需要检查的测试和文档、如何测试。给出完整计划为小粒度任务。DRY。YAGNI。TDD。频繁 commit。\n\n假设执行者是个有技能的开发者，但几乎不了解我们的工具集或问题领域。假设他们不太懂好的测试设计。\n\n**开始时宣布：** \"我正在用 writing-plans 技能创建实现计划。\"\n\n**上下文：** 这应该在专门的工作目录中运行（由 brainstorming 技能创建）。\n\n**保存计划到：** `docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md`\n\n## 范围检查\n\n如果规格涵盖多个独立子系统，应该在 brainstorming 阶段已分解为子项目规格。如果没有，建议分解为独立计划——每个子系统一个。每个计划应产生可工作、可测试的软件。\n\n## 文件结构\n\n在定义任务之前，映射哪些文件将被创建或修改，每个文件负责什么。这是分解决策被锁定的地方。\n\n- 用清晰边界和定义好接口的设计单元。每个文件应该有一个明确职责。\n- 你能放进脑子里的代码你推理得最好，编辑也更可靠。偏好更小、专注的文件，不要大的什么都做的文件。\n- 一起变更的文件应该放一起。按职责拆分，不是按技术层。\n- 现有代码库中，遵循已有模式。如果代码库用大文件，不要单方面重构——但如果修改的文件已经长得太大，在计划中包含拆分是合理的。\n\n这个结构指导任务分解。每个任务应该产生能独立理解的有意义的变更。\n\n## 小粒度任务\n\n**每步是一个动作（2-5 分钟）：**\n- \"写失败的测试\" — 一步\n- \"运行确保它失败\" — 一步\n- \"写最少代码让测试通过\" — 一步\n- \"运行确保测试通过\" — 一步\n- \"Commit\" — 一步\n\n## 计划文档头部\n\n**每个计划必须以此头部开始：**\n\n```markdown\n# [功能名] 实现计划\n\n**目标：** [一句话描述构建内容]\n\n**架构：** [2-3 句话描述方法]\n\n**技术栈：** [关键技术和库]\n\n---\n```\n\n## 任务结构\n\n```markdown\n### 任务 N：[组件名]\n\n**文件：**\n- 创建：`exact/path/to/file.py`\n- 修改：`exact/path/to/existing.py:123-145`\n- 测试：`tests/exact/path/to/test.py`\n\n- [ ] **步骤 1：写失败的测试**\n\n```python\ndef test_specific_behavior():\n    result = function(input)\n    assert result == expected\n```\n\n- [ ] **步骤 2：运行测试验证它失败**\n\n运行：`pytest tests/path/test.py::test_name -v`\n预期：FAIL，错误信息 \"function not defined\"\n\n- [ ] **步骤 3：写最少的实现代码**\n\n```python\ndef function(input):\n    return expected\n```\n\n- [ ] **步骤 4：运行测试验证它通过**\n\n运行：`pytest tests/path/test.py::test_name -v`\n预期：PASS\n\n- [ ] **步骤 5：Commit**\n\n```bash\ngit add tests/path/test.py src/path/file.py\ngit commit -m \"feat: add specific feature\"\n```\n```\n\n## 无占位符\n\n每步必须包含执行者需要的实际内容。以下是**计划失败**——永远不要写：\n- \"TBD\"、\"TODO\"、\"稍后实现\"、\"填细节\"\n- \"添加适当的错误处理\"/\"添加验证\"/\"处理边界情况\"\n- \"为上述写测试\"（没有实际测试代码）\n- \"类似于任务 N\"（重复代码——执行者可能按顺序读任务）\n- 描述做什么而不展示怎么做的步骤（代码步骤必须有代码块）\n- 引用任何任务中未定义的类型、函数或方法\n\n## 自审\n\n写完完整计划后，用新眼光看规格并检查计划：\n\n**1. 规格覆盖：** 浏览规格每个部分/需求。能指向实现它的任务吗？列出任何缺口。\n\n**2. 占位符扫描：** 在计划中搜索红旗——上述\"无占位符\"部分的任何模式。修复它们。\n\n**3. 类型一致性：** 在后续任务中使用的类型、方法签名和属性名与前面定义的一致吗？任务 3 中的 `clearLayers()` 和任务 7 中的 `clearFullLayers()` 是 bug。\n\n发现问题，内联修复。不需要重新审查——修复并继续。如果发现规格需求没有任务，加任务。\n\n## 工作目录说明（OpenClaw 适配）\n\nSuperpowers 原版使用 git worktree 做隔离工作区。在 OpenClaw 环境中：\n- 使用 git branch 创建特性分支\n- 在分支上工作，完成后 merge 或 PR\n- 保持工作目录整洁，与主分支隔离\n\n**工作流程：**\n```bash\n# 从当前分支创建特性分支\ngit checkout -b feature/<feature-name>\n\n# 实现（按计划任务）\n# ...\n\n# 完成时\ngit checkout main && git merge feature/<feature-name>\n```\n\n## 执行移交\n\n保存计划后，提供执行选择：\n\n**\"计划写完保存到 `docs/superpowers/plans/<filename>.md`。两种执行选项：**\n\n**1. 子 Agent 驱动（推荐）** — 我为每个任务 dispatch 新的 subagent，任务间审查，快速迭代\n\n**2. 顺序执行** — 在本 session 按批次执行任务，有审查检查点\n\n**选择哪种？\"**\n\n**如果选择子 Agent 驱动：**\n- 需要 `superpowers-subagent-dev` 技能\n- 每个任务新鲜 subagent + 两阶段审查\n\n**如果选择顺序执行：**\n- 在本 session 按计划任务顺序执行\n- 每个任务后运行验证\n- 完成后调用 `superpowers-finishing-branch` 清理\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn7bcaearb90wwcjbr9gpv32s5831k39\",\n  \"slug\": \"superpowers-writing-plans\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1774515926564\n}\n\nFile v1.0.1:skill-card.md\n\n## Description:\n\nUse when you have a spec or requirements for a multi-step task, before touching code - guides writing comprehensive implementation plans with bite-sized tasks, TDD, and DRY/YAGNI principles.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[axelhu](https://clawhub.ai/user/axelhu)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and engineering agents use this skill to turn a multi-step implementation spec into a detailed Markdown plan before code changes begin. The plan is expected to include file responsibilities, small test-driven tasks, concrete commands, commits, and handoff options.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill can produce implementation plans that include git branch, merge, commit, or subagent workflow steps.\n\nMitigation: Review the generated plan before allowing follow-on implementation, especially version-control and subagent steps.\n\nRisk: The operating instructions are written in Chinese, which may be unsuitable for teams or agents that require English-language instructions.\n\nMitigation: Install only where Chinese-language operating instructions are acceptable, or translate and review the skill before use.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/axelhu/skills/superpowers-writing-plans)\n\n## Skill Output:\n\n**Output Type(s):** [Markdown, Shell commands, Guidance]\n\n**Output Format:** [Markdown plan with task checklists and inline code blocks]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Plans are saved under docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md and should be reviewed before implementation.]\n\n## Skill Version(s):\n\n1.0.1 (source: server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.0.0: 2 files, 3312 bytes\n\nFiles: SKILL.md (5615b), _meta.json (144b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: superpowers-writing-plans\ndescription: Use when you have a spec or requirements for a multi-step task, before touching code - guides writing comprehensive implementation plans with bite-sized tasks, TDD, and DRY/YAGNI principles\n---\n\n# Superpowers Writing Plans - 写实现计划\n\n## 概述\n\n写全面的实现计划，假设执行者对代码库零上下文、品味可疑。记录他们需要知道的一切：每个任务要修改的文件、代码、可能需要检查的测试和文档、如何测试。给出完整计划为小粒度任务。DRY。YAGNI。TDD。频繁 commit。\n\n假设执行者是个有技能的开发者，但几乎不了解我们的工具集或问题领域。假设他们不太懂好的测试设计。\n\n**开始时宣布：** \"我正在用 writing-plans 技能创建实现计划。\"\n\n**上下文：** 这应该在专门的工作目录中运行（由 brainstorming 技能创建）。\n\n**保存计划到：** `docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md`\n\n## 范围检查\n\n如果规格涵盖多个独立子系统，应该在 brainstorming 阶段已分解为子项目规格。如果没有，建议分解为独立计划——每个子系统一个。每个计划应产生可工作、可测试的软件。\n\n## 文件结构\n\n在定义任务之前，映射哪些文件将被创建或修改，每个文件负责什么。这是分解决策被锁定的地方。\n\n- 用清晰边界和定义好接口的设计单元。每个文件应该有一个明确职责。\n- 你能放进脑子里的代码你推理得最好，编辑也更可靠。偏好更小、专注的文件，不要大的什么都做的文件。\n- 一起变更的文件应该放一起。按职责拆分，不是按技术层。\n- 现有代码库中，遵循已有模式。如果代码库用大文件，不要单方面重构——但如果修改的文件已经长得太大，在计划中包含拆分是合理的。\n\n这个结构指导任务分解。每个任务应该产生能独立理解的有意义的变更。\n\n## 小粒度任务\n\n**每步是一个动作（2-5 分钟）：**\n- \"写失败的测试\" — 一步\n- \"运行确保它失败\" — 一步\n- \"写最少代码让测试通过\" — 一步\n- \"运行确保测试通过\" — 一步\n- \"Commit\" — 一步\n\n## 计划文档头部\n\n**每个计划必须以此头部开始：**\n\n```markdown\n# [功能名] 实现计划\n\n**目标：** [一句话描述构建内容]\n\n**架构：** [2-3 句话描述方法]\n\n**技术栈：** [关键技术和库]\n\n---\n```\n\n## 任务结构\n\n```markdown\n### 任务 N：[组件名]\n\n**文件：**\n- 创建：`exact/path/to/file.py`\n- 修改：`exact/path/to/existing.py:123-145`\n- 测试：`tests/exact/path/to/test.py`\n\n- [ ] **步骤 1：写失败的测试**\n\n```python\ndef test_specific_behavior():\n    result = function(input)\n    assert result == expected\n```\n\n- [ ] **步骤 2：运行测试验证它失败**\n\n运行：`pytest tests/path/test.py::test_name -v`\n预期：FAIL，错误信息 \"function not defined\"\n\n- [ ] **步骤 3：写最少的实现代码**\n\n```python\ndef function(input):\n    return expected\n```\n\n- [ ] **步骤 4：运行测试验证它通过**\n\n运行：`pytest tests/path/test.py::test_name -v`\n预期：PASS\n\n- [ ] **步骤 5：Commit**\n\n```bash\ngit add tests/path/test.py src/path/file.py\ngit commit -m \"feat: add specific feature\"\n```\n```\n\n## 无占位符\n\n每步必须包含执行者需要的实际内容。以下是**计划失败**——永远不要写：\n- \"TBD\"、\"TODO\"、\"稍后实现\"、\"填细节\"\n- \"添加适当的错误处理\"/\"添加验证\"/\"处理边界情况\"\n- \"为上述写测试\"（没有实际测试代码）\n- \"类似于任务 N\"（重复代码——执行者可能按顺序读任务）\n- 描述做什么而不展示怎么做的步骤（代码步骤必须有代码块）\n- 引用任何任务中未定义的类型、函数或方法\n\n## 自审\n\n写完完整计划后，用新眼光看规格并检查计划：\n\n**1. 规格覆盖：** 浏览规格每个部分/需求。能指向实现它的任务吗？列出任何缺口。\n\n**2. 占位符扫描：** 在计划中搜索红旗——上述\"无占位符\"部分的任何模式。修复它们。\n\n**3. 类型一致性：** 在后续任务中使用的类型、方法签名和属性名与前面定义的一致吗？任务 3 中的 `clearLayers()` 和任务 7 中的 `clearFullLayers()` 是 bug。\n\n发现问题，内联修复。不需要重新审查——修复并继续。如果发现规格需求没有任务，加任务。\n\n## 工作目录说明（OpenClaw 适配）\n\nSuperpowers 原版使用 git worktree 做隔离工作区。在 OpenClaw 环境中：\n- 使用 git branch 创建特性分支\n- 在分支上工作，完成后 merge 或 PR\n- 保持工作目录整洁，与主分支隔离\n\n**工作流程：**\n```bash\n# 从当前分支创建特性分支\ngit checkout -b feature/<feature-name>\n\n# 实现（按计划任务）\n# ...\n\n# 完成时\ngit checkout main && git merge feature/<feature-name>\n```\n\n## 执行移交\n\n保存计划后，提供执行选择：\n\n**\"计划写完保存到 `docs/superpowers/plans/<filename>.md`。两种执行选项：**\n\n**1. 子 Agent 驱动（推荐）** — 我为每个任务 dispatch 新的 subagent，任务间审查，快速迭代\n\n**2. 顺序执行** — 在本 session 按批次执行任务，有审查检查点\n\n**选择哪种？\"**\n\n**如果选择子 Agent 驱动：**\n- 需要 `superpowers-subagent-dev` 技能\n- 每个任务新鲜 subagent + 两阶段审查\n\n**如果选择顺序执行：**\n- 在本 session 按计划任务顺序执行\n- 每个任务后运行验证\n- 完成后调用 `superpowers-finishing-branch` 清理\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn7bcaearb90wwcjbr9gpv32s5831k39\",\n  \"slug\": \"superpowers-writing-plans\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1774506313982\n}","readmeExcerpt":"Skill: Writing Plans Owner: axelhu Summary: Use when you have a spec or requirements for a multi-step task, before touching code - guides writing comprehensive implementation plans with bite-sized task... Tags: latest:1.0.1 Version history: v1.0.1 | 2026-03-26T09:05:26.564Z | user OpenClaw-adapted skill for Superpowers development methodology. v1.0.0 | 2026-03-26T06:25:13.982Z | user Initial release: OpenClaw-adapted","codeSnippets":[],"executableExamples":[{"language":"markdown","snippet":"# [功能名] 实现计划\n\n**目标：** [一句话描述构建内容]\n\n**架构：** [2-3 句话描述方法]\n\n**技术栈：** [关键技术和库]\n\n---"},{"language":"markdown","snippet":"### 任务 N：[组件名]\n\n**文件：**\n- 创建：`exact/path/to/file.py`\n- 修改：`exact/path/to/existing.py:123-145`\n- 测试：`tests/exact/path/to/test.py`\n\n- [ ] **步骤 1：写失败的测试**"},{"language":"text","snippet":"- [ ] **步骤 2：运行测试验证它失败**\n\n运行：`pytest tests/path/test.py::test_name -v`\n预期：FAIL，错误信息 \"function not defined\"\n\n- [ ] **步骤 3：写最少的实现代码**"},{"language":"text","snippet":"- [ ] **步骤 4：运行测试验证它通过**\n\n运行：`pytest tests/path/test.py::test_name -v`\n预期：PASS\n\n- [ ] **步骤 5：Commit**"},{"language":"bash","snippet":"# 从当前分支创建特性分支\ngit checkout -b feature/<feature-name>\n\n# 实现（按计划任务）\n# ...\n\n# 完成时\ngit checkout main && git merge feature/<feature-name>"},{"language":"markdown","snippet":"# [功能名] 实现计划\n\n**目标：** [一句话描述构建内容]\n\n**架构：** [2-3 句话描述方法]\n\n**技术栈：** [关键技术和库]\n\n---"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: superpowers-writing-plans\ndescription: Use when you have a spec or requirements for a multi-step task, before touching code - guides writing comprehensive implementation plans with bite-sized tasks, TDD, and DRY/YAGNI principles\n---\n\n# Superpowers Writing Plans - 写实现计划\n\n## 概述\n\n写全面的实现计划，假设执行者对代码库零上下文、品味可疑。记录他们需要知道的一切：每个任务要修改的文件、代码、可能需要检查的测试和文档、如何测试。给出完整计划为小粒度任务。DRY。YAGNI。TDD。频繁 commit。\n\n假设执行者是个有技能的开发者，但几乎不了解我们的工具集或问题领域。假设他们不太懂好的测试设计。\n\n**开始时宣布：** \"我正在用 writing-plans 技能创建实现计划。\"\n\n**上下文：** 这应该在专门的工作目录中运行（由 brainstorming 技能创建）。\n\n**保存计划到：** `docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md`\n\n## 范围检查\n\n如果规格涵盖多个独立子系统，应该在 brainstorming 阶段已分解为子项目规格。如果没有，建议分解为独立计划——每个子系统一个。每个计划应产生可工作、可测试的软件。\n\n## 文件结构\n\n在定义任务之前，映射哪些文件将被创建或修改，每个文件负责什么。这是分解决策被锁定的地方。\n\n- 用清晰边界和定义好接口的设计单元。每个文件应该有一个明确职责。\n- 你能放进脑子里的代码你推理得最好，编辑也更可靠。偏好更小、专注的文件，不要大的什么都做的文件。\n- 一起变更的文件应该放一起。按职责拆分，不是按技术层。\n- 现有代码库中，遵循已有模式。如果代码库用大文件，不要单方面重构——但如果修改的文件已经长得太大，在计划中包含拆分是合理的。\n\n这个结构指导任务分解。每个任务应该产生能独立理解的有意义的变更。\n\n## 小粒度任务\n\n**每步是一个动作（2-5 分钟）：**\n- \"写失败的测试\" — 一步\n- \"运行确保它失败\" — 一步\n- \"写最少代码让测试通过\" — 一步\n- \"运行确保测试通过\" — 一步\n- \"Commit\" — 一步\n\n## 计划文档头部\n\n**每个计划必须以此头部开始：**\n\n```markdown\n# [功能名] 实现计划\n\n**目标：** [一句话描述构建内容]\n\n**架构：** [2-3 句话描述方法]\n\n**技术栈：** [关键技术和库]\n\n---\n```\n\n## 任务结构\n\n```markdown\n### 任务 N：[组件名]\n\n**文件：**\n- 创建：`exact/path/to/file.py`\n- 修改：`exact/path/to/existing.py:123-145`\n- 测试：`tests/exact/path/to/test.py`\n\n- [ ] **步骤 1：写失败的测试**\n\n```python\ndef test_specific_behavior():\n    result = function(input)\n    assert result == expected\n```\n\n- [ ] **步骤 2：运行测试验证它失败**\n\n运行：`pytest tests/path/test.py::test_name -v`\n预期：FAIL，错误信息 \"function not defined\"\n\n- [ ] **步骤 3：写最少的实现代码**\n\n```python\ndef function(input):\n    return expected\n```\n\n- [ ] **步骤 4：运行测试验证它通过**\n\n运行：`pytest tests/path/test.py::test_name -v`\n预期：PASS\n\n- [ ] **步骤 5：Commit**\n\n```bash\ngit add tests/path/test.py src/path/file.py\ngit commit -m \"feat: add specific feature\"\n```\n```\n\n## 无占位符\n\n每步必须包含执行者需要的实际内容。以下是**计划失败**——永远不要写：\n- \"TBD\"、\"TODO\"、\"稍后实现\"、\"填细节\"\n- \"添加适当的错误处理\"/\"添加验证\"/\"处理边界情况\"\n- \"为上述写测试\"（没有实际测试代码）\n- \"类似于任务 N\"（重复代码——执行者可能按顺序读任务）\n- 描述做什么而不展示怎么做的步骤（代码步骤必须有代码块）\n- 引用任何任务中未定义的类型、函数或方法\n\n## 自审\n\n写完完整计划后，用新眼光看规格并检查计划：\n\n**1. 规格覆盖：** 浏览规格每个部分/需求。能指向实现它的任务吗？列出任何缺口。\n\n**2. 占位符扫描：** 在计划中搜索红旗——上述\"无占位符\"部分的任何模式。修复它们。\n\n**3. 类型一致性：** 在后续任务中使用的类型、方法签名和属性名与前面定义的一致吗？任务 3 中的 `clearLayers()` 和任务 7 中的 `clearFullLayers()` 是 bug。\n\n发现问题，内联修复。不需要重新审查——修复并继续。如果发现规格需求没有任务，加任务。\n\n## 工作目录说明（OpenClaw 适配）\n\nSuperpowers 原版使用 git worktree 做隔离工作区。在 OpenClaw 环境中：\n- 使用 git branch 创建特性分支\n- 在分支上工作，完成后 merge 或 PR\n- 保持工作目录整洁，与主分支隔离\n\n**工作流程：**\n```bash\n# 从当前分支创建特性分支\ngit checkout -b feature/<feature-name>\n\n# 实现（按计划任务）\n# ...\n\n# 完成时\ngit checkout main && git merge feature/<feature-name>\n```\n\n## 执行移交\n\n保存计划后，提供执行选择：\n\n**\"计划写完保存到 `docs/superpowers/plans/<filename>.md`。两种执行选项：**\n\n**1. 子 Agent 驱动（推荐）** — 我为每个任务 dispatch 新的 subagent，任务间审查，快速迭代\n\n**2. 顺序执行** — 在本 session 按批次执行任务，有审查检查点\n\n**选择哪种？\"**\n\n**如果选择子 Agent 驱动：**\n- 需要 `superpowers-subagent-dev` 技能\n- 每个任务新鲜 subagent + 两阶段审查\n\n**如果选择顺序执行：**\n- 在本 session 按计划任务顺序执行\n- 每个任务后运行验证"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7bcaearb90wwcjbr9gpv32s5831k39\",\n  \"slug\": \"superpowers-writing-plans\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1774515926564\n}"},{"path":"skill-card.md","content":"## Description:\n\nUse when you have a spec or requirements for a multi-step task, before touching code - guides writing comprehensive implementation plans with bite-sized tasks, TDD, and DRY/YAGNI principles.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[axelhu](https://clawhub.ai/user/axelhu)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and engineering agents use this skill to turn a multi-step implementation spec into a detailed Markdown plan before code changes begin. The plan is expected to include file responsibilities, small test-driven tasks, concrete commands, commits, and handoff options.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill can produce implementation plans that include git branch, merge, commit, or subagent workflow steps.\n\nMitigation: Review the generated plan before allowing follow-on implementation, especially version-control and subagent steps.\n\nRisk: The operating instructions are written in Chinese, which may be unsuitable for teams or agents that require English-language instructions.\n\nMitigation: Install only where Chinese-language operating instructions are acceptable, or translate and review the skill before use.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/axelhu/skills/superpowers-writing-plans)\n\n## Skill Output:\n\n**Output Type(s):** [Markdown, Shell commands, Guidance]\n\n**Output Format:** [Markdown plan with task checklists and inline code blocks]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Plans are saved under docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md and should be reviewed before implementation.]\n\n## Skill Version(s):\n\n1.0.1 (source: server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Use when you have a spec or requirements for a multi-step task, before touching code - guides writing comprehensive implementation plans with bite-sized task... Skill: Writing Plans Owner: axelhu Summary: Use when you have a spec or requirements for a multi-step task, before touching code - guides writing comprehensive implementation plans with bite-sized task... Tags: latest:1.0.1 Version history: v1.0.1 | 2026-03-26T09:05:26.564Z | user OpenClaw-adapted skill for Superpowers development methodology. v1.0.0 | 2026-03-26T06:25:13.982Z | user Initial release: OpenClaw-adapted","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":790,"uniquenessScore":55,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T17:57:15.398Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-09T17:57:15.398Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T21:00:33.688Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}