Claude Skills by ccoalm

在一个仓库跑「AGENTS.md 契约覆盖」gate——扫出根目录和每个源码目录是否都有 AGENTS.md,可一键补 stub 并接 CI 卡关。确定性脚本运行器,不做交付分类。触发:"查/跑 AGENTS 覆盖"、"查/跑/补 agent 覆盖地图"、"agent 契约覆盖"、"扫一下哪些目录缺 AGENTS.md"、"每个目录都有 agent 契约了吗"、"补缺失的 AGENTS.md"、"契约覆盖 gate"、"给这个仓初始化契约覆盖"、"装 AGENTS 的 pre-commit / CI 卡关"、"check AGENTS.md coverage"、"agents coverage"、"scaffold missing AGENTS.md"、"bootstrap agents coverage"、"do all dirs have an agent contract"。Skip:问「何时/是否」该更新契约或分层策略本身 → `product-rd-workflow` 的 spec/repo-contract sync gate;只是写某一个 AGENTS.md 的内容...

Use when designing, implementing, reviewing, debugging, testing, or shipping mobile app client features across Flutter, React Native, native Android, and native iOS, including navigation, state, API integration, offline/cache, platform capabilities, accessibility, performance, app build/release, and rendered device verification. Product-agnostic; use miniapp-product-dev for mini-programs, web-react-dev for React web, product-ui-ux-design for UI/UX, backend skills for services, and testing-str...

Use when an implementation needs an independent CLI reviewer or adversarial challenger, routing across Claude Code, Kimi, OpenCode, or Codex according to local availability, model-family independence, and the user's client order; also covers Claude-only bounded consultation and requests such as code review, Claude review, Kimi review, OpenCode review, second opinion, 找茬, 唱反调, or 第二意见. Skip 某个改动/提交还有没有价值、值不值得修这类交付裁决 → product-rd-workflow：本技能执行评审、找缺陷与风险，不裁决交付价值。

bug / 报错 / test 挂了 / 线上问题 / 复现 / 找根因 / debug → diagnose first-hand failure evidence, isolate cause, verify before fixing, add regression proof, and route prevention. Also use for AI-proposed causes or fixes.

风险定级 / 要不要灰度 / 需要哪些 gate / 双人 review / 架构评审 / 安全审计 / 安全评审 / 威胁建模 / security audit / threat model / OWASP / pentest review / risky → classify a feature, fix, or change by risk tags (incl. a security-review gate) and name required design, arch, dev, test, review, security, launch, and rollout gates.

Design, review, or explain a new product's Go backend/microservice architecture using Kitex or similar RPC, Hertz or similar HTTP gateway, protobuf IDL, MySQL/GORM storage, Redis cache/locks/limits, service discovery, dynamic config, message queues, observability, DI, and code generation. Also owns multi-tenant isolation, event-driven/Kafka, and data-platform (sharding/replicas/HA) architecture. Product-agnostic; no dependence on existing codebase paths, service names, or legacy repos. Prefer...

Use when implementing, modifying, scaffolding, generating, or testing a new product's Go microservice, backend feature, or standalone Go CLI/tooling binary using protobuf IDL, Kitex or similar RPC, Hertz or similar HTTP, Wire/DI, MySQL/GORM-style DAL, Redis, MQ, dynamic config, code generation, and focused tests. For reproduction, isolation, or root-cause debugging, use defect-diagnosis first; this skill owns the Go implementation/fix. Triggers also include "用 Go 写一个服务", "Go 后端怎么搞", "Kitex 接口...

grill-me / 访谈 / 拷问 / 压力测试方案 / stress-test a plan — lightweight one-question-at-a-time interview to challenge a plan, design, API shape, data model, or feature direction before implementation. Skip code-level YAGNI/delete/adversarial review of written code → `product-rd-workflow`'s independent-review gate; full delivery/spec/plan authoring → product-rd-workflow; tests → testing-strategy; implementation → stack/dev skill; process lesson extraction → skill-extraction-workflow.

Use when designing, implementing, reviewing, debugging, or operating LLM, agent, RAG, prompt, model-routing, streaming, evaluation, replay, shadow, token-cost, or batch inference features across backend products. Product-agnostic; do not depend on prior codebase names, paths, providers, or business domains. Triggers also include "接 LLM", "大模型怎么调", "提示词怎么写", "RAG 怎么实现", "LLM 智能体 / 工具调用怎么搭", "模型评测".

小程序 / Taro / 微信小程序 / 支付宝小程序 / 抖音小程序 / 小程序上线审核 → implement, debug, test, and ship mini-program client features: pages, state, API integration, auth, sharing, platform capabilities, review, and device verification. Triggers also include \"重构这个小程序页面/组件(局部)\", \"refactor a mini-program page/component\".

并行 agent / 子 agent / 分发任务 / delegate / fan out → execute a clear plan with AI agents. Use for decomposing independent slices, isolating contexts, staging review, and verifying agent output; not for a single linear local edit.

Skip 优先判定：一查便知的单点事实问题 → 直接回答不套流程；请求点名了候选让选、或用裁决措辞要结论（选哪个 / 要不要上 X / 该不该做 / 可不可行）→ 先 `product-rd-workflow`（它可回调本技能产调研底稿）；纯主题/领域/写作准备调研留在本技能；拷问已有方案 → `grill-me`；bug 根因 → `defect-diagnosis`；复盘沉淀 → `skill-extraction-workflow`。触发：调研一个主题 / 深度调研 / 多视角研究 / 帮我研究一下 X / 写作前调研 / 领域·组织研究（不喂决策）/ research a topic → run a structured research loop（视角枚举 → 矛盾图 → 合成简报 → 自评）with evidence-grounding discipline, instead of one-question surface answers.

Use when implementing, modifying, scaffolding, or testing Node.js backend and service code, including HTTP/RPC handlers, workers, jobs, standalone Node.js CLI/tooling, runtime configuration, TypeScript/JavaScript module setup, async cancellation, streams, graceful shutdown, and Node-specific test mechanics. Triggers include "用 Node.js 写接口", "Node 后端实现", "用 Node.js 写个命令行工具", "重构 Node 服务里的某文件/某类(局部)", "refactor a file/class within a Node.js service", "Fastify/Express/NestJS 服务", "node:test 怎么写"...

Use when designing, reviewing, debugging, or shipping observability — service logs, metrics, distributed tracing, log/trace correlation, dashboards, alerts, on-call routing（值班/排班 SOP、P0/P1 打断；发布值班/回滚除外）, SLI/SLO, error budgets — for a backend product. Owns the cross-cutting evidence layer — what signals must exist, what fields must propagate, what middleware must auto-wire, what verification proves a change is observable in production. Hand off mesh/routing/mTLS to `platform-service-connectiv...

发布 / 灰度 / canary / rollback / rollout / 环境泳道 / promotion gate → design or review how a change moves from build to traffic and back safely, including rollout strategy, approval, rollback, secrets, config, and deploy control planes. Skip when the ask is the production release lifecycle — 上线范围确认 / 合并 main / 打 tag / 生产构建 / 发布后 reset → release-coordination; release document substance → release-doc-writer.

服务互通 / service mesh / service discovery / mTLS / retry / timeout / circuit breaker / lane routing → design or debug how one request safely reaches another service across environments, mesh, clients, HTTP/RPC, and queues.

加功能 / 新需求 / 技术方案 / 方案评估 / 技术选型 / 可行性评估 / 工作量评估 / 多阶段重构 / 推倒重来 / 重新开发 / 完全重新开始 / 清除代码重新开发 / redo-from-scratch / 项目分析 / spec·PRD·需求文档实质内容写错要改对（substance 修正） / 方案评审通过开始实现 / 进入实现阶段 → end-to-end product R&D router for requirement shaping, spec/plan, implementation gates, assessment, redo/refactor, and multi-stack standards.

页面怎么设计 / 交互怎么做 / 设计走查 / 设计验收 / 页面别扭 / 空状态 / 错误提示 / UI polish → own product UI/UX decisions: layout, interaction, visual craft, states, accessibility, design-system consistency, and launch acceptance.

Python 后端架构 / FastAPI 项目结构 / Celery worker 拆分 / Python 微服务边界 / 多租户隔离怎么设计 / 消费 Kafka·消息队列与事件驱动架构 / 数据平台（分库分表·读写分离·备份恢复） / 服务分层重构 / Python 服务重构 → design or review Python backend, service, worker, package, API contract, data ownership, reliability, async/job, and runtime boundaries. Prefer this for architecture/boundary decisions; use python-service-dev for implementation work and localized refactor (某文件/某类); multi-stage / cross-module refactor delivery re-enters product-rd-workflow.

用 Python 写接口 / FastAPI / Django model / Celery 任务 / pytest → implement, modify, scaffold, test, and wire Python backend services, workers, packages, standalone CLI/tooling, migrations, Redis, queues, config, observability, and clients. Triggers also include "用 Python 写个命令行工具", "重构 Python 服务里的某文件/某类(局部)", "refactor a file/class within a Python service". For reproduction, isolation, or root-cause debugging, use defect-diagnosis first; for architecture/layering decisions or a service-wide refact...

发版 / 生产发布 / prod release / 上线范围确认 / 合并 main / 打 tag / 生产构建 / 发布后 reset / 按已确认的上线范围产出测试范围提示（提测范围、这次要回归哪些面）→ coordinate release scope, docs, MR/tag gates, pipeline evidence, rollout handoff, watchers, reset. 从已确认发布范围派生的测试范围提示归本技能——它是发布交接物；完整测试层级/矩阵/CI gate 设计 → testing-strategy。

提测文档 / 上线文档 / 发布文档 / test handoff / release doc / launch notes / 补上线范围 / 发布证据 → write, fill, or review test-handoff and release-document substance from Git/config/deploy/verification evidence without owning release orchestration, merge authorization, or production mutation.

现状盘点 / 当前能力梳理 / 现有流程、页面、API、数据、运营规则盘点 / as-is audit / current state inventory —— 交付物是**现状清单本身**：现在怎么运作、已有哪些能力与例外、事实来源与 freshness、缺口和冲突，含按 commit 固定的代码现状取证。Skip 要的是意图、用户故事、验收标准、问题池（「到底要什么」）→ requirement-intent；要的是本轮改哪些、不改哪些、切几版（变更边界）→ requirement-scope；问线上是否已启用 → platform-observability；代码/项目质量评估 → product-rd-workflow；bug 根因 → defect-diagnosis。

写 PRD / 需求文档 / 产品需求文档 / 需求说明 / user story 文档 / 验收标准文档 / 产品需求正文 —— 在 lifecycle 判定 PRD Ready 之后，把已关闭的需求组装成人读的 PRD。Skip 需求实质不清 → requirement-intent；缺现状事实 → requirement-baseline；范围/版本切片/开放决策未关闭 → requirement-scope；Agent/Machine 技术规格 → llm-inference-integration；其评测与测试层 → testing-strategy；只是润色措辞 → tighten-doc。

产品需求沟通 / 需求讨论完善 / 产品需求澄清 / 澄清 PRD / 需求对齐会 / 需求讨论会后整理 / 用户故事 / 验收标准 / 产品意图 / 需求不清楚 / clarify requirement / requirement discussion —— 交付物是「这需求到底要什么」：意图、目标用户、成功标准、用户路径、意图级非目标、功能点验收点、拷问问题池、决策关闭 backlog。Skip 要的是现状清单（现有流程·页面·API·数据·运营规则怎么运作、已有什么能力、缺口在哪）→ requirement-baseline；要的是变更边界（in/out、受影响对象、依赖、版本切片、appetite）→ requirement-scope；要成文 PRD → requirement-doc-writer；一问一答拷问 → grill-me；已有 spec/PRD 实质内容写错要改对（substance 修正，非澄清）、多阶段交付计划 → product-rd-workflow。

改动范围 / 影响范围 / scope / 需求拆分 / MVP 边界 / 非目标 / 版本切片 / 变更影响 / appetite / timebox —— 交付物是**变更边界**：in/out scope、受影响对象、依赖、MVP 与后续切片、appetite 与砍项、每个切片的验收范围。前提是方向已定。Skip 方向还没定、要先弄清「到底要什么」→ requirement-intent；要的是现状清单（现在怎么运作、有什么能力）→ requirement-baseline；风险定级与要哪些 gate → feature-risk-router；实现/发布计划 → product-rd-workflow；测试范围 → testing-strategy。

复盘 / 沉淀 / 总结经验 / 补进技能 / 技能缺陷 / 流程优化 / would other teammates hit this / will we forget next time / teamwide recurrence / extract skill / post-mortem / 深度 review·审计技能仓库 / 对标外部技能包找 gap（benchmark superpowers·gstack 等） / 核查全局安装点（~/.config/opencode 等）旧快照是否遮蔽本仓技能 / 本仓（ccl-skills 等共享技能仓）OpenCode 项目配置·命令治理 → turn reusable lessons into durable CCL skills.

CLI/terminal/console/PTY/ANSI/keyboard/TUI design, implementation, review, debugging, testing, or shipping. Owns the command/subcommand/flag/help contract (owned here even when nothing is rendered), with defaults/output/exit/action/confirmation/progress/recovery, plus layout, input, accessibility, and real-terminal evidence. Triggers include "命令行/TUI 界面怎么做", "CLI 界面怎么写", "refactor a terminal command / TUI view". Skip only parser/library/tooling internals owned by a language skill ("用 Python 写...

Create and maintain structured test cases from requirements or code, including initializing or reusing the Feishu Bitable, canonical fields, import, update, status sync, and deprecation. Use for 写测试用例, 写测试用例文档, test-case documents, TC, source-to-TC generation, 初始化测试用例多维表格, 测试用例放飞书, and 导入/更新/同步/废弃测试用例. Skip executable test code, coverage, CI gates, mocks, and regression verification → testing-strategy; broader feature delivery → product-rd-workflow.

怎么测 / 测试方案 / 测试覆盖 / 先写测试用例（可执行测试代码/覆盖） / test cases first for test code / 写测试 / 写测试代码 / 补测试 / 补测试用例（未指向文档/Bitable/source-to-TC 时按可执行测试覆盖处理） / mock / 单元测试 / 集成测试 / E2E / 回归 / CI gate → choose test layers, scenarios, fixtures, mocks, regression coverage, smoke, verification evidence, and runner-config policy. Skip structured test-case documents, Feishu/Bitable TC sync, or source-to-TC generation → test-artifact-management. Skip 具体的 runner 调用（pytest / go test 命令与参数怎么写）→ 该技术栈 dev 技能；覆盖阈值与 CI gate...

润色文档 / 精简文档 / 改下文档 / AI 味太重 / 废话太多 / polish / make shorter / remove AI tone；**该画时序图还是状态机 / 这里要不要配图 / 图画完了总觉得不对劲说不上哪不对 / 缺图例 / 连线没标签 / 全是表格要不要补图 / 图里字看不清** → finalize wording after substance is settled: clarify, shorten, restructure lightly, preserve decisions, and keep comments safe. Proactively draft a no-owner deliverable doc（「写一份分享/给同事的文档」）. 图与表的**表示形式**（图种由主张形态推出、记法硬约束、版式契约、对比度、可跑的检查器）归本技能，**系统边界与架构决策本身仍归架构技能**。Skip while a sibling owns the substance（定稿仍回本技能）: spec/PRD/标准 → product-rd-wor...

Use when designing, implementing, reviewing, debugging, testing, or shipping React web client features, including component structure, routing, state ownership, API/data fetching, forms, browser behavior, accessibility, performance, build/deploy, and rendered browser verification. Product-agnostic; use miniapp-product-dev for WeChat/Alipay/Douyin/Baidu mini-programs, app-cross-platform-dev for Flutter/React Native/Android/iOS apps, product-ui-ux-design for UI/UX rules, backend skills for serv...

开工前先在独立 git worktree 里再改代码——**绝不在 main（主检出/main 分支）上开发**，任何迭代/功能/哪怕一行修改都先建分支+worktree（并发只是让这条更刚性，单人单线同样适用）；worktree 集成回目标分支后立即清理 worktree+本地分支+远端分支（让位见收尾节）。Never develop on the main checkout/branch — always create a dedicated worktree first (concurrency only makes it stricter, not a precondition); also covers teardown/cleanup when a worktree is integrated. 触发：凡要动代码，动手前先过本技能 Step 0（由 owner 在其实现阶段调用，本技能不抢交付入口）、并行做两个版本、改 ccl-skills 等共享仓库、被隔离闸 deny、worktree 干完要清理时。Skip when：交付级的重新开发/推倒重来/清除代码重来（"...