#971 by GitHub stars
laolaoshiren/claude-code-skills-zh
面向中文开发者的 Claude Code Skills / Agents / Plugins 精选与原创技能库|按场景分类|复制即装|持续更新
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/api-tester/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
e7d807ee54ed → 4521b155d36e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → e7d807ee54ed
No earlier version was observed for comparison.
skills/changelog-gen/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
e7d807ee54ed → 4521b155d36e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → e7d807ee54ed
No earlier version was observed for comparison.
skills/db-migrator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
e7d807ee54ed → 4521b155d36e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → e7d807ee54ed
No earlier version was observed for comparison.
skills/dep-auditor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
e7d807ee54ed → 4521b155d36e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → e7d807ee54ed
No earlier version was observed for comparison.
skills/ds-mapper/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
e7d807ee54ed → 4521b155d36e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → e7d807ee54ed
No earlier version was observed for comparison.
skills/env-manager/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
e7d807ee54ed → 4521b155d36e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → e7d807ee54ed
No earlier version was observed for comparison.
skills/error-translator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
e7d807ee54ed → 4521b155d36e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → e7d807ee54ed
No earlier version was observed for comparison.
skills/eslint-fix/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
e7d807ee54ed → 4521b155d36e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → e7d807ee54ed
No earlier version was observed for comparison.
skills/git-workflow/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
e7d807ee54ed → 4521b155d36e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → e7d807ee54ed
No earlier version was observed for comparison.
skills/github-actions-gen/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
e7d807ee54ed → 4521b155d36e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → e7d807ee54ed
No earlier version was observed for comparison.
skills/i18n-helper/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
e7d807ee54ed → 4521b155d36e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → e7d807ee54ed
No earlier version was observed for comparison.
skills/log-analyzer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
e7d807ee54ed → 4521b155d36e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → e7d807ee54ed
No earlier version was observed for comparison.
skills/perf-profiler/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
e7d807ee54ed → 4521b155d36e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → e7d807ee54ed
No earlier version was observed for comparison.
skills/refactor-advisor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
e7d807ee54ed → 4521b155d36e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → e7d807ee54ed
No earlier version was observed for comparison.
skills/security-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
e7d807ee54ed → 4521b155d36e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → e7d807ee54ed
No earlier version was observed for comparison.
skills/skill-curator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
e7d807ee54ed → 4521b155d36e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → e7d807ee54ed
No earlier version was observed for comparison.
skills/test-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
e7d807ee54ed → 4521b155d36e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → e7d807ee54ed
No earlier version was observed for comparison.
skills/zh-code-reviewer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
e7d807ee54ed → 4521b155d36e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → e7d807ee54ed
No earlier version was observed for comparison.
skills/zh-docgen/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
e7d807ee54ed → 4521b155d36e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → e7d807ee54ed
No earlier version was observed for comparison.
skills/zh-readme/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
e7d807ee54ed → 4521b155d36e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → e7d807ee54ed
No earlier version was observed for comparison.
Heat
5.4- Star growth, last 7 daysAhead of 77% of tracked repositories
- Star growth, last 24 hoursAhead of 73% of tracked repositories
- Rank movement, last 7 daysAhead of 7% of tracked repositories
- Commits, last 30 daysAhead of 81% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- api-tester
skills/api-tester - changelog-gen
skills/changelog-gen - db-migrator
skills/db-migrator - dep-auditor
skills/dep-auditor - ds-mapper
skills/ds-mapper - env-manager
skills/env-manager - error-translator
skills/error-translator - eslint-fix
skills/eslint-fix - git-workflow
skills/git-workflow - github-actions-gen
skills/github-actions-gen - i18n-helper
skills/i18n-helper - log-analyzer
skills/log-analyzer - perf-profiler
skills/perf-profiler - refactor-advisor
skills/refactor-advisor - security-audit
skills/security-audit - skill-curator
skills/skill-curator - test-generator
skills/test-generator - zh-code-reviewer
skills/zh-code-reviewer - zh-docgen
skills/zh-docgen - zh-readme
skills/zh-readme
How it works
api-tester
When your agent uses it
依据真实 OpenAPI、路由实现和现有测试生成并验证 API 测试。用于用户要求测试接口、补集成测试、验证 API 契约、生成回归用例或排查接口兼容性时;区分“生成测试”和“执行请求”的授权,不猜测状态码、响应结构或 SLA,不在未确认环境中发送写请求。
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
1,424 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 核心原则
- 工作流程
- 安全边界
- 输出
Files
SKILL.mdcore5,504 bytes
Read SKILL.md
# API 测试助手
## 核心原则
- 只把可核验的 OpenAPI、代码、类型、调用方或现有测试当作契约证据。
- 生成测试不等于执行测试;读取接口定义不等于可以访问真实服务。
- 保护现有数据、凭据和用户修改,优先使用隔离且可清理的测试环境。
## 工作流程
### 1. 读取项目与接口证据
先读取适用的仓库规则、测试说明、Git 状态和项目脚本,再按实际存在情况检查:
View the complete source on GitHubchangelog-gen
When your agent uses it
Changelog 生成器 - 从 Git 历史自动生成 CHANGELOG
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
908 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 触发条件
- 工作流程
- 输出格式
- 注意事项
Files
SKILL.mdcore2,741 bytesSKILL.mdcore2,741 bytes
Read SKILL.md
# Changelog 自动生成
## 触发条件
当用户要求生成 changelog、更新日志、版本记录、release notes 时激活此技能。
## 工作流程
### 第 1 步:获取 Git 历史
```bash
# 先获取最近的 tag,再用 revision range 查询
git describe --tags --abbrev=0
git log --oneline <last-tag>..HEAD
# 或指定范围View the complete source on GitHubdb-migrator
When your agent uses it
数据库迁移助手 - Schema 对比、迁移脚本生成
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
1,086 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 触发条件
- 工作流程
- 迁移模板
- 回滚策略
- 注意事项
Files
SKILL.mdcore3,862 bytesSKILL.mdcore3,862 bytesSKILL.mdcore3,862 bytesSKILL.mdcore3,862 bytesSKILL.mdcore3,862 bytes
Read SKILL.md
# 数据库迁移助手
## 触发条件
当用户要求数据库迁移、生成 migration、schema 变更、数据库升级时激活此技能。
## 工作流程
### 第 1 步:识别框架
扫描项目文件,判断使用的 ORM/迁移框架:
- `alembic.ini` / `alembic/` → Alembic
- `prisma/schema.prisma` → Prisma
- `pom.xml` 含 flyway → Flyway
- `manage.py` + `settings.py` → Django
- `Gemfile` + `db/migrate/` → RailsView the complete source on GitHubdep-auditor
When your agent uses it
审计 Node.js、Python、Go、Rust、JVM、Ruby 项目的依赖漏洞、版本健康度与许可证事实;当用户要求检查 package.json、lockfile、requirements、go.mod、Cargo.toml、pom.xml、Gemfile.lock,或生成不改依赖的中文审计报告时使用
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
1,864 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 核心原则
- 工作流程
- 安全边界
Files
SKILL.mdcore6,937 bytes
Read SKILL.md
# 依赖安全审计
## 核心原则
- 默认只读。用户只要求“检查、审计、报告”时,不修改 manifest、lockfile、源码、CI 或外部服务。
- 以实际解析版本和可追溯 advisory 为证据。不要凭包名、版本年龄或记忆猜测 CVE、修复版本、可达性与许可证。
- 优先使用项目锁定的包管理器和已有审计命令。不要为完成审计而裸跑 `npx`,也不要擅自执行 `pip install`、`go install`、`cargo install` 等下载命令。
- 把“发现问题”“建议修复”“执行修改”分开。任何会改依赖或 lockfile 的动作都需要用户明确授权。
- 许可证部分只陈述事实、适用场景和待确认事项,不作法律结论。
## 工作流程
### 1. 确认范围与授权
View the complete source on GitHubds-mapper
When your agent uses it
项目目录结构地图 - 生成带说明的可视化目录树,快速理解任意代码库
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
583 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 触发条件
- 工作流程
- 输出格式
- 注意事项
Files
SKILL.mdcore2,087 bytes
Read SKILL.md
# 项目目录结构地图(Directory Structure Mapper)
## 触发条件
当用户说「带我看看项目结构」「这个仓库怎么组织的」「目录树」「帮我理解这个代码库」或类似需求时激活此技能。
## 工作流程
1. **扫描根目录** — 使用 Bash `find` 和 `ls` 获取顶层结构
2. **分析关键目录** — 读取关键文件(package.json, Cargo.toml, pyproject.toml, go.mod 等)获取项目元信息
3. **递归扫描** — 深入扫描主要目录,理解各模块职责
4. **生成结构图** — 输出 ASCII 目录树 + 中文注释说明
## 输出格式
View the complete source on GitHubenv-manager
When your agent uses it
环境变量管理器:扫描、校验、同步 .env 文件,生成安全配置模板
What it loads into context
Frontmatter
27 tokensAlways available to the agent
SKILL.md
1,133 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 触发条件
- 工作流程
- 输出格式
- 安全检查清单
- 修改边界
- 常见陷阱
- 框架适配
Files
SKILL.mdcore3,964 bytesSKILL.mdcore3,964 bytes
Read SKILL.md
# 环境变量管理器
## 触发条件
当用户要求管理环境变量、.env 文件、配置同步、Secrets 检查时激活。
## 工作流程
### 1. 扫描项目
- 检测所有 `.env*` 文件(.env / .env.local / .env.development / .env.production)
- 默认只提取变量名、来源文件和是否为空;真实值必须脱敏,不写入报告或终端输出
- 扫描代码中引用的环境变量(`process.env.XXX` / `os.environ['XXX']` / `os.getenv('XXX')`)
- 识别静态扫描中未发现引用的变量(仅作为待人工确认候选)
- 识别已使用但未定义的变量(缺失配置)
View the complete source on GitHuberror-translator
When your agent uses it
编程错误消息翻译专家 — 将英文错误消息翻译成中文,解释原因并提供修复方案
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
1,116 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 触发条件
- 工作流程
- 输出格式
- 支持的常见错误类型
- 常见错误模式示例
- 注意事项
Files
SKILL.mdcore3,973 bytes
Read SKILL.md
# 错误消息翻译专家
## 触发条件
当用户粘贴或遇到编程错误消息(英文),需要翻译和解释时激活此技能。
## 工作流程
1. **识别错误类型**
- 确定编程语言和运行环境(Python/Java/JavaScript/Go/Rust/C/C++ 等)
- 判断错误类型:语法错误、运行时错误、编译错误、框架错误、系统错误
2. **翻译错误消息**
- 将英文错误消息准确翻译为中文
- 保留关键的技术术语(类名、函数名、文件路径)View the complete source on GitHubeslint-fix
When your agent uses it
安全诊断并修复 ESLint error、warning 和配置兼容问题。用于用户要求运行 lint、解释 ESLint 报错、限定范围自动修复或迁移 ESLint 配置时;优先使用项目锁定的包管理器与版本,先预检再修改,不自动下载最新版或批量改写无关源码。
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
915 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 工作流程
- 安全边界
- 输出
Files
SKILL.mdcore3,430 bytes
Read SKILL.md
# ESLint 修复助手
## 工作流程
### 1. 识别项目工具链
读取:
- `package.json` 中的 scripts、`devDependencies` 和 `packageManager`。
- npm、pnpm、Yarn 或 Bun 的 lockfile。
- `eslint.config.*`、`.eslintrc.*`、`.eslintignore`、Prettier 和 TypeScript 配置。
- 适用的仓库规则、Git 状态和用户指定的文件范围。
优先运行仓库已有的 lint script。只有确认 ESLint 已被当前项目锁定并安装时,才使用对应包管理器的本地执行方式。若缺失依赖,先报告;安装包、更新 lockfile 或迁移配置需要单独授权。View the complete source on GitHubgit-workflow
When your agent uses it
安全处理 Git 状态检查、提交信息、commit、分支、push、PR 和 rebase。用于用户要求检查改动、生成或创建提交、管理分支、推送、发起 PR 或整理历史时;严格区分每个动作的授权,并保护工作树中已有和无关的修改。
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
1,087 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 核心原则
- 工作流程
- Rebase 与历史整理边界
- 输出
Files
SKILL.mdcore4,069 bytesSKILL.mdcore4,069 bytesSKILL.mdcore4,069 bytes
Read SKILL.md
# Git 工作流助手
## 核心原则
- 只执行用户明确要求的 Git 动作。生成提交信息不等于暂存或提交;提交不等于推送;创建 PR 不等于合并 PR、关闭 Issue 或发布 Release。
- 把工作树中已有、未跟踪和无关的修改视为用户资产,不覆盖、不回退、不混入本轮提交。
- 优先使用非交互命令。涉及历史重写、冲突选择或远程覆盖时降低自动化程度。
## 工作流程
### 1. 读取仓库规则与状态
先阅读适用的 `AGENTS.md`、`CONTRIBUTING.md`、README、提交规范和 CI 说明,再检查:
View the complete source on GitHubgithub-actions-gen
When your agent uses it
分析真实项目并生成或修订安全、可验证的 GitHub Actions workflow;当用户要求创建 CI、测试矩阵、构建、Release、部署、缓存、Secrets、OIDC、PR 自动化或排查 workflow 配置时使用
What it loads into context
Frontmatter
62 tokensAlways available to the agent
SKILL.md
1,910 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 核心原则
- 工作流程
- 交付格式
- 质量检查清单
Files
SKILL.mdcore7,042 bytes
Read SKILL.md
# GitHub Actions CI/CD 生成器
## 核心原则
- 先读项目,再生成 workflow。不要凭项目名猜测运行时、包管理器、测试命令或部署目标。
- 默认只生成只读 CI。Release、部署、推送镜像、写回仓库和调用外部 webhook 必须先确认目标、凭据、环境保护与回滚方式。
- 将不可信 PR 代码与 Secrets、写权限、自托管 Runner 隔离。不要为方便而改用 `pull_request_target` 执行 PR 代码。
- 把所有 Action 固定到核验过的完整 40 位 commit SHA,并在旁边保留版本注释。不要使用 `@main`、`@master`、`@latest` 或可移动的 `@vN` tag。
- 为每个 job 设置最小 `permissions` 和 `timeout-minutes`;不依赖仓库默认权限。
- 生成后运行真实语法与项目命令验证,不把“配置看起来正确”当作通过。
## 工作流程
### 1. 盘点项目证据View the complete source on GitHubi18n-helper
When your agent uses it
国际化/本地化助手 — 扫描代码中的硬编码文本、生成 i18n 配置、批量翻译
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
757 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 触发条件
- 工作流程
- 输出格式
- 支持的 i18n 框架
- 注意事项
Files
SKILL.mdcore2,356 bytes
Read SKILL.md
# 🌍 i18n-helper — 国际化/本地化助手
## 触发条件
当用户要求以下操作时激活此技能:
- 扫描代码中的硬编码中文/英文文本
- 为项目添加国际化支持(i18n)
- 批量提取和翻译语言文件
- 检查翻译完整性(缺失 key 检测)
## 工作流程
### 1. 项目分析
- 检测项目类型(React/Vue/Angular/Node.js/Python/Java 等)
- 识别已使用的 i18n 框架(react-intl, vue-i18n, i18next, gettext 等)View the complete source on GitHublog-analyzer
When your agent uses it
日志分析助手 — 智能解析日志文件,识别异常模式,定位问题根因
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
749 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 触发条件
- 工作流程
- 支持的日志来源
- 注意事项
Files
SKILL.mdcore2,469 bytes
Read SKILL.md
# 📋 log-analyzer — 日志分析助手
## 触发条件
当用户要求以下操作时激活此技能:
- 分析应用日志文件(.log, .txt, journalctl 输出等)
- 排查线上问题和异常
- 从日志中提取统计信息
- 生成日志分析报告
## 工作流程
### 1. 日志格式识别
自动检测日志格式:
- **结构化**: JSON logs, LogfmtView the complete source on GitHubperf-profiler
When your agent uses it
基于可复现基线和 profiler 证据分析性能问题。用于用户要求定位慢接口、慢任务、慢查询、内存或网络瓶颈,制定优化方案,或验证优化收益时;区分实测结论与静态推断,不虚构耗时和提升比例,生产环境操作需明确授权。
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
960 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 工作流程
- 证据等级
- 安全与授权边界
- 输出
Files
SKILL.mdcore3,682 bytes
Read SKILL.md
# 性能分析助手
## 工作流程
### 1. 明确目标与边界
先确认或从项目中核实:
- 目标指标,如延迟、吞吐量、CPU、内存、查询次数或包体积。
- 可复现的场景、数据规模、运行环境、版本和关键配置。
- 用户允许分析和修改的范围,以及是否可以运行负载或 profiler。
没有明确目标时,先用现有监控、benchmark 或用户现象缩小范围,不把“代码看起来慢”当成瓶颈结论。
View the complete source on GitHubrefactor-advisor
When your agent uses it
重构顾问 - 识别代码坏味道并提供重构方案
What it loads into context
Frontmatter
26 tokensAlways available to the agent
SKILL.md
1,046 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 触发条件
- 工作流程
- 常见坏味道检测
- 输出格式
- 重构路线图
Files
SKILL.mdcore3,247 bytes
Read SKILL.md
# 代码重构顾问
## 触发条件
当用户要求重构代码、优化代码结构、改善代码质量、消除技术债务时激活此技能。
## 工作流程
### 第 1 步:扫描代码库
- 使用 `grep`/`rg` 扫描目标目录,识别潜在坏味道
- 统计文件行数、函数长度、参数数量等指标
- 查找重复代码块(相似度 > 80%)
### 第 2 步:分类坏味道
按严重程度分类发现的问题:View the complete source on GitHubsecurity-audit
When your agent uses it
代码安全审计 - 漏洞扫描、依赖检查、安全最佳实践
What it loads into context
Frontmatter
25 tokensAlways available to the agent
SKILL.md
653 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 触发条件
- 工作流程
- 检查清单
- 输出格式
Files
SKILL.mdcore2,054 bytes
Read SKILL.md
# 代码安全审计
## 触发条件
当用户要求安全检查、漏洞扫描、安全审计、依赖安全检查时激活此技能。
## 工作流程
1. **确定审计范围** — 根据用户指定的目录/文件/代码段进行分析
2. **静态安全扫描** — 按检查清单逐项排查
3. **依赖安全检查** — 检查 package.json / requirements.txt / go.mod 等依赖文件
4. **生成审计报告** — 按严重程度分类输出
## 检查清单
View the complete source on GitHubskill-curator
When your agent uses it
中文 Skill 收录评估器。用于核验 GitHub 上的 Claude Code、Codex、Agent Skills、Plugin、MCP、CLI 或 Agent 工作流是否值得加入精选列表;检查真实资产、安装方式、活跃度、重复项和安全边界,并生成分类、中文描述与可追溯证据。
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
1,638 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 工作流程
- 输出格式
- 收录执行规则
Files
SKILL.mdcore6,037 bytesSKILL.mdcore6,037 bytesSKILL.mdcore6,037 bytes
Read SKILL.md
# Skill 收录评估器
对候选资源进行证据驱动的核验。不要只根据仓库简介、搜索摘要或 Star 做决定。
## 工作流程
### 1. 规范化候选地址
- 接受 GitHub 仓库、仓库子目录、PR、Issue 或用户提供的项目名。
- 从 `tree/`、`blob/` 等子路径提取 `owner/repo`,同时保留指向独立 Skill 的原始子路径。
- 在当前精选列表中搜索仓库名、规范化 URL 和旧名称,判断是新增、重复还是已有条目更新。
- 遇到仓库重命名或转移时,使用最终规范地址,避免继续收录重定向 URL。
```bashView the complete source on GitHubtest-generator
When your agent uses it
依据真实代码契约生成并验证单元测试或集成测试。用于用户要求为函数、类、接口或缺陷补测试、提高覆盖率、生成回归用例或完善测试策略时;先读取现有测试与调用方,不猜测空值、异常或超时行为,不自动安装框架或访问生产依赖。
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
977 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 工作流程
- 安全与授权边界
- 输出
Files
SKILL.mdcore3,786 bytes
Read SKILL.md
# 测试生成器
## 工作流程
### 1. 读取真实契约
检查目标代码及其:
- 类型定义、公开文档、调用方和错误处理路径。
- 现有测试、fixture、测试配置、依赖清单和项目测试命令。
- 输入输出、副作用、状态变化、并发语义和系统边界。
- 适用的仓库规则、Git 状态及本轮允许修改的范围。
区分“代码当前行为”和“产品期望行为”。两者冲突或契约不明确且会改变断言时,先列出证据与待确认假设;不要用测试固化猜测。View the complete source on GitHubzh-code-reviewer
When your agent uses it
中文代码审查专家 - 生成详细的中文代码审查报告
What it loads into context
Frontmatter
24 tokensAlways available to the agent
SKILL.md
371 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 触发条件
- 工作流程
- 输出格式
- 注意事项
Files
SKILL.mdcore1,300 bytes
Read SKILL.md
# 中文代码审查专家
## 触发条件
当用户要求审查代码、code review、代码检查、代码质量评估时激活此技能。
## 工作流程
1. **读取目标文件** — 使用 Glob 和 Read 工具获取要审查的代码
2. **分析代码质量** — 从以下维度评估:
- 代码规范(命名、格式、注释)
- 潜在 Bug(空指针、越界、并发问题)
- 性能问题(N+1 查询、内存泄漏、不必要的循环)
- 安全漏洞(SQL 注入、XSS、硬编码密钥)
- 设计模式(是否合理使用、是否有更好的方案)View the complete source on GitHubzh-docgen
When your agent uses it
中文文档生成器 - 从代码库自动生成中文技术文档
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
284 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 触发条件
- 工作流程
- 输出格式
- 技巧
Files
SKILL.mdcore1,040 bytes
Read SKILL.md
# 中文文档生成器
## 触发条件
当用户要求生成文档、写技术文档、生成 API 文档、项目说明时激活此技能。
## 工作流程
1. **扫描项目结构** — 识别项目类型(Web 应用/CLI 工具/库/服务)
2. **分析代码** — 提取模块、函数、类、接口的签名和注释
3. **生成文档** — 输出以下文档:
### 生成内容
- **项目概述** — 中文简介、技术栈、架构图(Mermaid)
- **快速开始** — 安装、配置、运行步骤View the complete source on GitHubzh-readme
When your agent uses it
中文 README 生成器 - 先分析项目,再生成面向中文开发者的高质量 README
What it loads into context
Frontmatter
29 tokensAlways available to the agent
SKILL.md
1,105 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 触发条件
- 核心原则
- 首屏优化模板
- 推荐结构
- 🚀 快速开始
- 🧭 使用示例
- 📁 项目结构
- ❓ 适用场景
- 🛠<U+FE0F> 开发
- 🤝 贡献
- 📝 License
Files
SKILL.mdcore3,992 bytesSKILL.mdcore3,992 bytesSKILL.mdcore3,992 bytesSKILL.mdcore3,992 bytesSKILL.mdcore3,992 bytes
Read SKILL.md
# 中文 README 生成器
## 触发条件
当用户要求写 README、重写项目介绍、补全文档首页、优化开源仓库展示页时激活此技能。
## 核心原则
1. 先读代码和目录,再写 README;不要只凭项目名猜功能。
2. 面向中文开发者表达,技术名词保留英文,解释用自然中文。
3. 首页要解决三个问题:这是什么、为什么值得用、怎么快速上手。
4. 优先给出真实命令、真实路径、真实示例,少写空泛宣传语。
5. 如果项目已有 README,先保留有效信息,再补全缺失结构。
6. 如果项目包含官网或文档站,README 中必须给出统一、可点击的正式入口链接,避免 README / 官网 / Issue 模板地址不一致。
7. 项目介绍页要尽量补上社交证明信号(如 Star、精选数量、更新时间、代表性场景),帮助访客快速判断是否值得继续浏览。
8. README 首屏必须具备“30 秒价值判断”能力:首句价值主张 + 适合谁用 + 最短安装方式,缺一不可。View the complete source on GitHubSkills included
- api-tester
- changelog-gen
- db-migrator
- dep-auditor
- ds-mapper
- env-manager
- error-translator
- eslint-fix
- git-workflow
- github-actions-gen
- i18n-helper
- log-analyzer
- perf-profiler
- refactor-advisor
- security-audit
- skill-curator
- test-generator
- zh-code-reviewer
- zh-docgen
- zh-readme
Repository facts
- License
- MIT
- Created
- Apr 14, 2026
- Last pushed
- Nov 4, 2026
- Forks
- 114
- Open issues
- 2
- Project activity
- Active
Rank over the last 12 weeks
Now #971 · best #654 · down 173 in 30 days
- #959 on Nov 2
- #961 on Nov 3
- #963 on Nov 4
- #962 on Nov 5
- #965 on Nov 6
- #971 since Nov 7
68 earlier periods
- #667 on Aug 2
- #656 on Aug 8
- #664 on Aug 9
- #686 on Aug 10
- #696 on Aug 11
- #688 on Aug 12
- #683 on Aug 13
- #680 on Aug 14
- #657 on Aug 15
- #673 on Aug 16
- #687 on Aug 17
- #700 on Aug 18
- #681 on Aug 19
- #680 on Aug 20
- #684 on Aug 21
- #654 on Aug 22
- #680 on Aug 23
- #704 on Aug 24
- #709 on Aug 25
- #690 on Aug 26
- #698 on Aug 27
- #721 on Aug 28
- #665 on Aug 29
- #669 on Aug 30
- #705 on Aug 31
- #718 on Sep 1
- #705 on Sep 2
- #711 on Sep 3
- #687 on Sep 4
- #698 on Sep 6
- #713 on Sep 7
- #736 on Sep 8
- #719 on Sep 9
- #727 on Sep 10
- #705 from Sep 11 to Sep 12
- #702 on Sep 13
- #725 on Sep 14
- #717 on Sep 15
- #727 on Sep 16
- #731 on Sep 17
- #713 on Sep 18
- #704 on Sep 20
- #724 on Sep 21
- #741 on Sep 22
- #731 on Sep 23
- #751 on Sep 30
- #723 on Oct 2
- #702 on Oct 3
- #731 on Oct 4
- #736 on Oct 5
- #757 on Oct 7
- #798 on Oct 8
- #765 on Oct 9
- #783 on Oct 13
- #792 on Oct 14
- #782 on Oct 15
- #789 on Oct 16
- #763 on Oct 17
- #752 on Oct 18
- #809 on Oct 20
- #806 on Oct 23
- #768 on Oct 24
- #928 on Oct 25
- #939 on Oct 28
- #945 on Oct 29
- #948 on Oct 30
- #951 on Oct 31
- #953 on Nov 1
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 14 notes
skills/changelog-gen/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/db-migrator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/db-migrator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/db-migrator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/db-migrator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/env-manager/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/git-workflow/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/git-workflow/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skill-curator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skill-curator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/zh-readme/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/zh-readme/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/zh-readme/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/zh-readme/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 2 network referencesin 1 file: skill-curator/SKILL.md:138
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- 11 references to secretsin 1 file: env-manager/SKILL.md:3
- No requests to vote in Hot
Show all 13 signals by file
skills/env-manager/SKILL.md
- Access to secretsline 3
[Credential-related source omitted] - Access to secretsline 16
[Credential-related source omitted] - Access to secretsline 24
[Credential-related source omitted] - Access to secretsline 64
[Credential-related source omitted] - Access to secretsline 65
[Credential-related source omitted] - Access to secretsline 69
[Credential-related source omitted] - Access to secretsline 70
[Credential-related source omitted] - Access to secretsline 101
[Credential-related source omitted] - Access to secretsline 102
[Credential-related source omitted] - Access to secretsline 103
[Credential-related source omitted] - Access to secretsline 104
[Credential-related source omitted]
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 13 facts
- Access to secrets in the frontmatter of the SKILL.mdenv-manager/SKILL.md:3Low confidence
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valueenv-manager/SKILL.md:16Low confidence
- Access to secrets in prose of the SKILL.mdenv-manager/SKILL.md:24Low confidence
- Access to secrets in code of the SKILL.mdenv-manager/SKILL.md:64High confidence
- Access to secrets in code of the SKILL.mdenv-manager/SKILL.md:65High confidence
- Access to secrets in code of the SKILL.mdenv-manager/SKILL.md:69High confidence
- Access to secrets in code of the SKILL.mdenv-manager/SKILL.md:70High confidence
- Access to secrets in prose of the SKILL.mdenv-manager/SKILL.md:101Low confidence
- Access to secrets in prose of the SKILL.mdenv-manager/SKILL.md:102Low confidence
- Access to secrets in prose of the SKILL.mdenv-manager/SKILL.md:103Low confidence
- Access to secrets in prose of the SKILL.mdenv-manager/SKILL.md:104Low confidence
- Network access in code of the SKILL.mdskill-curator/SKILL.md:138High confidence
- Network access in code of the SKILL.mdskill-curator/SKILL.md:139High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/api-tester/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/api-tester/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/api-tester/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/api-tester/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/api-tester/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/api-tester/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/laolaoshiren-claude-code-skills-zh/)