[Feature Name] Implementation Plan【免费下载链接】superpowersAn agentic skills framework software development methodology that works.项目地址: https://gitcode.com/GitHub_Trending/su/superpowersFor agentic workers:REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (- [ ]) syntax for tracking.Goal:[One sentence describing what this builds]Architecture:[2-3 sentences about approach]Tech Stack:[Key technologies/libraries]Global Constraints[The specs project-wide requirements — version floors, dependency limits, naming and copy rules, platform requirements — one line each, with exact values copied verbatim from the spec. Every tasks requirements implicitly include this section.]要点说明 - **面向 Agent 的工作者声明**头部第二行是写给执行 Agent 的强制指令——必须使用 subagent-driven-development推荐或 executing-plans 子技能逐任务实现且步骤使用 - [ ] checkbox 语法跟踪进度。 - **Goal / Architecture / Tech Stack**分别用一句话、2-3 句、若干条目说明构建目标、方案思路与关键技术栈。 - **Global Constraints全局约束**这是 spec 中项目级要求的逐行誊写——版本下限、依赖限制、命名与文案规则、平台要求——每行一条**精确值必须从 spec 原样照抄**。该节的所有内容被每个任务**隐式包含**即每个任务都受其约束。 对照仓库真实文件即可验证这一规范。[2026-03-11-zero-dep-brainstorm-server.md](https://link.gitcode.com/i/d70e58f5a3409c09cf67af6ffadb17e9) 的头部为 markdown # Zero-Dependency Brainstorm Server Implementation Plan **For agentic workers:** REQUIRED: Use superpowers:subagent-driven-development (if subagents available) or superpowers:executing-plans to implement this plan. Steps use checkbox (- [ ]) syntax for tracking. **Goal:** Replace the brainstorm servers vendored node_modules with a single zero-dependency server.js using Node built-ins. **Architecture:** Single file with WebSocket protocol (RFC 6455 text frames), HTTP server (http module), and file watching (fs.watch). Exports protocol functions for unit testing when required as a module. **Tech Stack:** Node.js built-ins only: http, crypto, fs, path **Spec:** docs/superpowers/specs/2026-03-11-zero-dep-brainstorm-server-design.md2026-04-06-worktree-rototill.md 的 Architecture 一句则典型体现了计划文档可以修改技能文件本身的元特性These are markdown skill instruction files, not application code — tests are agent behavior tests using the testing-skills-with-subagents TDD framework.——该计划对技能文件本身做 TDD测试是基于 testing-skills-with-subagents 框架 的 Agent 行为测试见 tests/claude-code/ 下的测试脚本。七、任务结构模板Task Structure计划中的每个任务采用统一模板。以下完整继承自 SKILL.md### Task N: [Component Name] **Files:** - Create: exact/path/to/file.py - Modify: exact/path/to/existing.py:123-145 - Test: tests/exact/path/to/test.py **Interfaces:** - Consumes: [what this task uses from earlier tasks — exact signatures] - Produces: [what later tasks rely on — exact function names, parameter and return types. A tasks implementer sees only their own task; this block is how they learn the names and types neighboring tasks use.] - [ ] **Step 1: Write the failing test** python def test_specific_behavior(): result function(input) assert result expected - [ ] **Step 2: Run test to verify it fails** Run: pytest tests/path/test.py::test_name -v Expected: FAIL with function not defined - [ ] **Step 3: Write minimal implementation** python def function(input): return expected - [ ] **Step 4: Run test to verify it passes** Run: pytest tests/path/test.py::test_name -v Expected: PASS - [ ] **Step 5: Commit** bash git add tests/path/test.py src/path/file.py git commit -m feat: add specific feature 模板各部分的工程设计意图Files 块精确到文件路径Create / Modify / Test 三类Modify 甚至精确到行号范围如existing.py:123-145。零上下文的执行者不需要找一找直接按路径定位。Interfaces 块这是任务间的契约。由于 subagent 驱动模式下任务的实现者只能看到自己的任务Interfaces 块是相邻任务之间传递精确函数名、参数与返回类型的唯一通道。Consumes 声明本任务从更早任务消费什么精确签名Produces 声明后续任务依赖什么。Step 2 的 Expected: FAIL失败测试必须先确认失败这是 TDD 的关键校验——防止写出恒真测试或误判环境。Step 5 的 Commit每个任务以提交收尾保证频繁提交、每个任务在 git 历史中可独立追踪。subagent-driven-development 的评审包正是基于 commit 区间BASE..HEAD生成的。八、No Placeholders占位符是计划的失败SKILL.md 用plan failures计划失败这一措辞列出永远不得写入的模式TBD、TODO、implement later、fill in detailsAdd appropriate error handling / add validation / handle edge cases——笼统的加错误处理/校验/边界处理Write tests for the above不给真实测试代码Similar to Task N要求把代码重复写出来——工程师可能不按顺序读任务只描述做什么、不展示怎么做的步骤代码步骤必须配代码块引用任何任务中都不存在的类型、函数或方法。Similar to Task N 一条尤其值得注意它针对的正是 subagent 执行模式下每个任务只看到自己任务文本的现实因此跨任务的参见引用会被视为缺陷。九、Self-Review写完计划后的三步自查计划写完后要以全新视角对照 spec 检查。技能强调这是你自己运行的清单不是派发 subagent 去做的与后面第六节的外部评审形成内外两道门。Spec coverage规格覆盖通读 spec 的每个章节/要求能否指出实现它的任务列出缺口。Placeholder scan占位符扫描在计划中搜索上一节列出的红旗模式发现即修复。Type consistency类型一致性后续任务中使用的类型、方法签名、属性名是否与早期任务中的定义一致技能给的例子很直观Task 3 里叫clearLayers()Task 7 里变成clearFullLayers()就是 bug。发现问题就原地修复无需重新评审——just fix and move on。如果发现 spec 要求没有对应任务就补上该任务。十、计划评审plan-document-reviewer-prompt除了自查writing-plans 技能目录还附带一份 plan-document-reviewer-prompt.md 模板用于在完整计划写完后派发计划评审 subagentgeneral-purpose。该模板规定评审者核对四个维度维度检查内容Completeness完整性TODO、占位符、未完成的任务、缺失的步骤Spec Alignment规格对齐计划覆盖 spec 要求、无重大范围蔓延Task Decomposition任务分解任务边界清晰、步骤可操作Buildability可构建性工程师能否照着计划走而不卡住模板同时给出校准规则Calibration只标记会在实现中造成真实问题的缺陷——实现者构建出错误的东西或卡住才算问题措辞、风格偏好、锦上添花建议不算。原则上除非存在严重缺口——缺失 spec 要求、步骤自相矛盾、占位内容、任务模糊到无法执行——否则予以批准。输出格式固定为## Plan Review **Status:** Approved | Issues Found **Issues (if any):** - [Task X, Step Y]: [specific issue] - [why it matters for implementation] **Recommendations (advisory, do not block approval):** - [suggestions for improvement]【免费下载链接】superpowersAn agentic skills framework software development methodology that works.项目地址: https://gitcode.com/GitHub_Trending/su/superpowers创作声明：本文部分内容由AI辅助生成（AIGC），仅供参考