implement-spec
/implement-spec <spec> — 把一份已带验收标准与工作项图的 spec(docs/plans/ 或 /spec 产出)整份实现完整:任务图取前沿并发执行、集成分支收口、/review 审查收尾。TRIGGER: /implement-spec、implement spec、实现整份 spec、spec 并行实现、并行落地
- License 许可
- MIT
- 所属仓库
- rexleimo/aios
- 最近更新
- 2026-11-07
- Stars
- ★ 62
- Forks
- 11
01 前言 Front Matter
- name
- implement-spec
- tags
- [ "aios", "workflow", "delivery", "parallel", "worktree" ]
- scopes
- [ "global", "project" ]
- clients
- [ "codex", "claude", "gemini", "opencode", "hermes", "workbuddy", "pi", "zcode", "qoder" ]
- description
- /implement-spec <spec> — 把一份已带验收标准与工作项图的 spec(docs/plans/ 或 /spec 产出)整份实现完整:任务图取前沿并发执行、集成分支收口、/review 审查收尾。TRIGGER: /implement-spec、implement spec、实现整份 spec、spec 并行实现、并行落地
- repoTargets
- [ "codex", "claude", "gemini", "opencode", "hermes", "workbuddy", "pi", "zcode", "qoder" ]
- defaultInstall
- { "global": true, "project": false }
- installCatalogName
- implement-spec
03 SKILL.md 正文
Implement-Spec(整份 spec → 并行实现 → 收口)
交付链的执行入口:输入一份 spec(含验收标准与工作项),把它整份实现完。不重造调度器——把既有入口按序接起来:/plan(依赖分组)→ aios work(并发派发,需批准)→ /review(审查收尾)。本入口只由用户显式触发,不自动进入。
前置检查(缺一就停,先补齐,不猜)
| 缺什么 | 先补什么 |
|---|---|
| spec 含糊 / 缺验收标准 | /grill 或 /spec |
| 无工作项 / 无依赖分组 | /tickets 或 /plan |
| 工作项文件所有权重叠 | 重划边界;画不清就串行,不硬派 |
执行顺序
- 读 spec 建任务图:工作项是带阻塞关系的任务图,不是步骤列表。取当前前沿(无阻塞、可同时开工的集合)——即
/plan产出的依赖分组;没有就先跑/plan。 - 探索(可选):需要摸代码或查外部资料时,先派只读探索子代理,笔记写到
.aios/(不入库),供实施子代理引用——实施阶段专注写码而非探索。 - 核对可并行性:按
aios-work-dispatch准入条件核对(≥2 个独立工作项、文件所有权不重叠、无严格前后序)。不满足 → 串行逐项/implement。 - 派发实施:
aios work预览 → 人工显式批准 → 后台并发执行;需要隔离与可续的长工作项用aios harness(自带 worktree)。并行工作项各占一个 worktree,开工前确认基于同一集成基点。 - 推进前沿:某项完成并在任务图上解锁新前沿 → 继续派发(保持最大并发);仍被阻塞的不派。
- 集成分支收口:多 worktree 先汇到一条集成分支确认整体一致(回归 + 交叉依赖),再回主线流程。
- 审查收尾:整合结果跑
/review(标准与规格双查);提出的问题一次性修完,重跑验证。 - 清理与报告:清理 worktree;未达验收标准的工作项如实列出,不勾掉。
通讯纪律(子代理之间)
通讯尽量稀疏,主要走上下文指针:spec、工作项、探索笔记、commit。不复制已可由指针取得的信息。
完成判据(缺一不得报完成)
- 每条验收标准都有对应执行证据(真实命令输出),不是勾选框;
/review无未处理项;- 任务图所有工作项收口,或如实列出未完成项与原因;
- worktree 已清理。
与其他入口的边界
- 单工作项 / 小改动:直接
/implement或/single,不走本入口。 - 多个独立工作项的一次性并发:
/team。 - 一个长且可续的目标:
/harness。 - 本入口的语义 = 一份 spec 的完整落地(跨多轮、多工作项)。
04 同仓库更多 Skills
versioning-by-impact
Use when completing a task and deciding whether repository changes require a semantic version bump and changelog entry before commit/push.
verification-loop
Evidence-before-assertions workflow. Use before claiming work is done, before release, and after any behavior change in scripts/skills/MCP.
typesafe-ai
Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives. Its System One models, including Jev, turn natural language and application state into typed judgments and probabilities that code can combine. Use when a feature needs programmable common sense, when brainstorming what AI could make possible in an app, or when an LLM prompt-and-parse step could become a structured decision. Applications include routing, ranking, extraction, verification, and interactive experiences; these are starting points, not the limits. Read live docs and cookbooks to find useful patterns and discover new combinations.
skill-opt-lite
Train and optimize skill documents using the SkillOpt methodology — the agent acts as both target and optimizer, running tasks, reflecting on failures, proposing edits, and validating improvements in a self-contained training loop. TRIGGER: optimize skill, train skill, improve skill, skill training, skill optimization, SkillOpt, skill evolution, skill iteration loop, skill feedback loop, skill tuning.
skill-constraints
Enforce browser automation safety constraints — tool usage order, anti-detection rules, screenshot discipline, and human-in-the-loop checks. Use when setting up or verifying browser/MCP tool operations, NOT for every skill execution.
seo-geo-page-optimization
Use when improving a single page for SEO and AI answer-engine visibility (GEO), especially when you need faster first-screen conversion and clearer traffic funnels.