Enforce team coding standards and design documentation before any code modification. Blocks code writing until design docs are created, registers business terms, and validates code against configurable rules (Alibaba Java, Effective Dart, universal conventions). Tracks violations, logs daily work, and generates structured commit messages.
Use before writing or reviewing any business code in Java (Spring Boot/Spring Cloud), Python (FastAPI/Django/Flask), Dart (Flutter/Serverpod/Shelf), React, or Vue. MUST be invoked after design/pre-implementation orientation and before the first source-code edit to decide the target layer, feature module, reusable atomic capability, and maintainability boundaries. Enforces DDD-lite layering, feature-based structure, one-way dependencies, clear code structure, low coupling, high cohesion, and prevents business logic from being written directly in Controller/UI/Page.
Use BEFORE answering single-service backend questions about table relations / ER / SQL / state transitions / atomic capabilities or project-level technical pain points (subprocess, concurrency, perf, external deps); BEFORE Write/Edit any .md describing such content (anywhere — docs/, ai-docs/, scenarios/, work-log/). Auto-append candidates to `_candidates.md` after investigation discovers reusable facts, or when same tech concern raised ≥3 rounds in one session. Knowledge graph ownership = investigated service, not cwd. Detailed triggers (7 BLOCKING conditions) and scope boundaries listed in `## BLOCKING 强触发清单` section of SKILL.md body.
You MUST invoke this skill the moment a user reports a bug, describes an error/exception, asks you to investigate or analyze a problem, or mentions writing a bug analysis document. Trigger phrases include: 'there is a bug', 'this is broken', 'why is X happening', 'investigate this issue', 'analyze the root cause', 'we have an OOM/NPE/timeout', 'help me debug'. Invoke BEFORE starting any investigation, root cause analysis, or creating any file under docs/bug/. Pairs with doc-index-required — always invoke that skill too.
当用户要求「架构检查」「lint」「检测架构违规」时触发;当对 Flutter 项目的 presentation/domain/data/infrastructure 层代码执行 Edit/Write 后自动触发一次轻量检查。
Use when applying any bug fix, alignment correction, redundant-code removal, OR adding missing logic to align with upstream/cloud during integration/联调 phase. Trigger when: (1) design-doc-required has routed the change to 「第四·五步:轻量修订流水」 branch, (2) user describes the change as 'fix bug', 'align with cloud/upstream', 'add missing piece', '修 bug', '对齐云端', '删冗余', '修正实现', '改回正确逻辑', '补上漏掉的逻辑', '补缺漏', or (3) about to Edit/Write source code with intent of replacing existing erroneous logic OR adding alignment code that was missed in previous iterations. **注释红线不在本 skill 定义** — 唯一规则源是 coding-standards-common §5.4 + §5.4.1(common 触发顺序早于本 skill,不会漏)。本 skill 只承担 bug 修复期独有的应用层指引:v1.17 方向反转的历史背景、推荐写法 dart 代码示例、摆放位置、适用范围矩阵、遇到存量 [DEPRECATED]/[ADDED] 注释顺手清理的边界、红色警告对照表。
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
30 秒 TL;DR:Claude Code 插件,把"AI 协作开发"从"凭运气"变成"按流程"——26 个 skill + 5 个 hook 强制执行从需求分析 → 设计文档 → 代码定位 → 架构门禁 → 编码规范 → 提交规范 → 知识沉淀的完整链路。让 AI 改代码前先想清楚,改完后留下可追溯的痕迹。
它解决什么问题:
design-doc-required + pre-implementation-code-orientation 门禁architecture-ddd-lite-fullstack 的"业务分支 = 新 focused service"铁律bugfix-coding-style 禁止变更日志注释hooks/check-git-commit-skill.js 拦截大改、强制走五步流程装完插件后,在 Claude Code 中开一个项目,试这个流程感受规则生效:
你: "帮我加一个订单退款接口"
Claude: (触发 design-doc-required) 我需要先和你确认设计...
(生成 ai-docs/{project}/design/订单退款/订单退款-current.md)
你: 确认设计
Claude: (触发 pre-implementation-code-orientation) 我会先 Read 这些关键文件...
(触发 architecture-ddd-lite-fullstack) 落点判定:RefundService 新建...
(触发 coding-standards-common) 命名 / 函数原子 / 注释三档自检...
(开始写代码)
你: 提交
Claude: (触发 git-commit-standards 五步流程) 生成规范 commit
如果你看到 AI 跳过其中任何一步(比如想直接改代码而没有设计文档),说明 hook 或 skill 触发被绕过——可以提:"你跳过了 design-doc-required",AI 会立刻回到该 skill。
更详细的链路图见 docs/skill-flow.md;完整 skill 索引见 CLAUDE.md。
团队 Claude Code 开发规范插件,包含:
hooks/check-git-commit-skill.js 看 staged diff,小改 ≤2 文件 ∧ ≤30 行 ∧ 仅 M 修改时直接放行让模型写 commit message,大改才强制走 skill 五步;git push 不门禁)ai-docs/{project}/{type}/{topic}/{filename},按类型 + 主题归档,无日期/agent 目录层;v1.20 起用户目录知识库与项目 docs/ 索引等同,必须经 Phase-A/B 查重和登记)docs/work-log/{YYYY-MM-DD}.md,同主题合并、工时累计叠加)hooks/scan-reverse-index.js 扫描 Java/Dart/TS 枚举与 SQL 字面量产出 states 初版;增量维护规则:变更枚举/字段/事件/API 同回合必须回写)| 仓库 | 地址 | 说明 |
|---|---|---|
| GitLab(主仓) | https://gitlab.kpay-group.com/zhangk/kpay-team-standards.git | 日常维护与分发 |
| GitHub(镜像) | https://github.com/exception-coder/team-standards | 仅作镜像备份 |
team-standards/
.claude-plugin/ Claude Code 插件元数据与 marketplace 配置
.codex-plugin/ Codex 插件元数据
skills/ 各个 Skill 的规则、模板和辅助资料
hooks/ 可选 Hook 脚本,用于更强的写入前校验
docs/ 插件维护文档、skill-flow 链路图和决策日志(历史由 git 管理,不保留文件快照)
AGENTS.md Codex 入口规范,定义主动触发规则和 Skill 索引
CLAUDE.md Claude 入口规范,定义主动触发规则和 Skill 索引
README.md 对外安装、使用、维护说明
| 路径 | 作用 | 维护要点 |
|---|---|---|
.claude-plugin/ | Claude Code 插件声明目录,包含插件版本、展示信息和 marketplace 条目 | 发布前必须同步递增 plugin.json 与 marketplace.json 的 version |
.codex-plugin/ | Codex 插件声明目录,包含 Codex 侧插件元数据 | 维护 Codex 分发时同步递增 plugin.json 的 version |
skills/ | 插件核心目录,每个子目录是一个独立 Skill,至少包含 SKILL.md | 新增或修改 Skill 后,同步更新 AGENTS.md、CLAUDE.md、README 的 Skills 表和 docs/skill-flow.md |
hooks/ | 强制拦截脚本目录:check-git-commit-skill.js 默认启用(拦截未调用 git-commit-standards skill 的大改 git commit);check-dto-annotation.js 默认启用(拦截 wire DTO 用 @freezed 或裸 @JsonSerializable() 的违规);check-design-doc.js v1.26 起默认启用(项目级设计文档存在性兜底——源码 Edit/Write 前在项目 docs/design/ + 用户目录 ai-docs/{project}/design/ 任一位置找不到 .md 则阻断;TEAM_STANDARDS_DESIGN_DOC_HOOK=off 一次性绕过) | 新增 hook 时同步更新 hooks.json、CLAUDE.md/AGENTS.md 辅助资源表 |
docs/ | 维护文档目录,记录 Skill 链路、配置机制和决策型变更背景 | 链路结构变化时直接更新 skill-flow.md,历史由 git log 承担,不再创建文件式快照(v21.1 起反转) |
npx claudepluginhub exception-coder/team-standards --plugin team-standardsFeature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.