git-commit-message
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseGit Commit Message Generator
Git 提交信息生成器
Auto-generates conventional commit messages from git diffs with tiered format enforcement
基于Git差异自动生成符合约定式提交规范的提交信息,并支持分层格式校验
Purpose
用途
Analyze staged git changes and generate concise, meaningful commit messages following a tiered Conventional Commits specification. This skill examines file modifications, additions, and deletions to infer the type and scope of changes, producing commit messages that match the importance of the change - from detailed documentation for critical features to concise messages for minor updates.
Key Innovation: Three-tier format system that balances thoroughness for critical commits (feat, fix, security) with efficiency for routine changes (docs, chore, style).
分析Git暂存的变更内容,按照分层的Conventional Commits规范生成简洁、有意义的提交信息。本工具会检查文件的修改、新增和删除情况,推断变更的类型和范围,根据变更的重要程度生成匹配的提交信息——从关键功能的详细文档到小更新的简洁描述。
核心创新点:三级格式系统,在关键提交(feat、fix、security)的详尽性与日常变更(docs、chore、style)的高效性之间取得平衡。
When This Skill Activates
触发场景
- When command is invoked
/commit-msg - When invoked from a /
commit-msghook (if installed)prepare-commit-msg - When user requests commit message suggestions
- When analyzing changes before creating a commit
- 调用 命令时
/commit-msg - 通过 /
commit-msg钩子触发(已安装的情况下)prepare-commit-msg - 用户请求提交信息建议时
- 创建提交前分析变更内容时
Core Capabilities
核心能力
1. Diff Analysis
- Parse output
git diff --staged - Identify modified, added, and deleted files
- Analyze code changes (additions, deletions, modifications)
- Detect patterns across multiple files
2. Change Classification
- Determine commit type from changes:
- : New features or functionality
feat - : Bug fixes
fix - : Security fixes or hardening
security - : Code restructuring without behavior change
refactor - : Documentation changes
docs - : Formatting, whitespace, code style
style - : Adding or modifying tests
test - : Build process, dependencies, tooling
chore - : Performance improvements
perf - : CI/CD configuration changes
ci - : Build system changes
build - : Reverting previous commits
revert
3. Scope Detection
- Infer scope from file paths and patterns:
- Directory names (e.g., ,
api,auth)ui - File name patterns (e.g., →
*.test.js)tests - Framework conventions (e.g., ,
components/)services/
- Directory names (e.g.,
4. Message Generation
- Format:
type(scope): description - Enforce tier limits: Tier 1 summary max 50 chars; Tier 2/3 summary max 72 chars (ideal 50)
- Use imperative mood ("add" not "added")
- Focus on "what" and "why", not "how"
- Provide 2-3 alternative suggestions
1. 差异分析
- 解析 输出结果
git diff --staged - 识别修改、新增和删除的文件
- 分析代码变更(新增、删除、修改)
- 检测多文件间的变更模式
2. 变更分类
- 根据变更内容确定提交类型:
- : 新功能或新特性
feat - : 漏洞修复
fix - : 安全修复或加固
security - : 代码重构(不改变功能逻辑)
refactor - : 文档变更
docs - : 格式调整、空白字符、代码风格变更
style - : 添加或修改测试用例
test - : 构建流程、依赖项、工具链变更
chore - : 性能优化
perf - : CI/CD 配置变更
ci - : 构建系统变更
build - : 回滚之前的提交
revert
3. 范围识别
- 根据文件路径和模式推断变更范围:
- 目录名称(如 、
api、auth)ui - 文件名模式(如 →
*.test.js)tests - 框架约定(如 、
components/)services/
- 目录名称(如
4. 信息生成
- 格式:
type(scope): description - 分层长度限制:Tier 1 摘要最多50字符;Tier 2/3 摘要最多72字符(理想长度为50字符)
- 使用祈使语气(用"add"而非"added")
- 聚焦于“做了什么”和“为什么做”,而非“怎么做”
- 提供2-3个备选提交信息
Tier System: Smart Format Enforcement
分层系统:智能格式校验
This skill uses a three-tier format system that matches message detail to commit criticality:
本工具采用三级格式系统,根据提交的重要性匹配信息详细程度:
Tier 1: Critical Commits (feat, fix, perf, security)
Tier 1: 关键提交(feat、fix、perf、security)
Requirements: Detailed documentation with impact statement
Format:
type(scope): summary line (max 50 chars)
- Detailed description point 1
- Detailed description point 2
- Detailed description point 3
This change [impact statement describing user-facing benefit or risk addressed].
Affected files/components:
- path/to/file1
- path/to/file2Why: Features, fixes, and performance changes affect users directly and need thorough documentation for future reference and changelog generation.
要求:包含影响说明的详细文档
格式:
type(scope): 摘要行(最多50字符)
- 详细描述点1
- 详细描述点2
- 详细描述点3
本变更[描述面向用户的收益或解决的风险的影响说明]。
受影响的文件/组件:
- path/to/file1
- path/to/file2设计原因:功能、修复和性能变更直接影响用户,需要详尽的文档以便未来参考和生成变更日志。
Tier 2: Standard Commits (refactor, test, build, ci)
Tier 2: 标准提交(refactor、test、build、ci)
Requirements: Brief context and file list
Format:
type(scope): summary line (max 72 chars)
Brief explanation of what changed and why (1-2 sentences).
Files: path/to/file1, path/to/file2Why: Internal improvements need context for maintainability but don't require extensive documentation.
要求:包含简要上下文和文件列表
格式:
type(scope): 摘要行(最多72字符)
关于变更内容和原因的简要说明(1-2句话)。
文件:path/to/file1, path/to/file2设计原因:内部优化需要上下文以保证可维护性,但无需过度冗长的文档。
Tier 3: Minor Commits (docs, style, chore)
Tier 3: 次要提交(docs、style、chore)
Requirements: Summary line, optional description
Format:
type(scope): summary line (max 72 chars)
[Optional: Additional context if helpful]Why: Documentation and routine maintenance are self-explanatory from the diff; verbose messages add noise.
要求:仅摘要行,可选补充描述
格式:
type(scope): 摘要行(最多72字符)
[可选:如有帮助可添加额外上下文]设计原因:文档和日常维护的变更可通过差异内容直接理解,冗长的信息会增加冗余。
Workflow
工作流程
text
1. Get staged changes (staged only, not working tree):
- git diff --staged --name-status
- git diff --staged --stat
- git diff --staged
2. Load config → frameworks/shared-skills/skills/git-commit-message/config.yaml
3. Analyze changes:
- Count files modified/added/deleted
- Identify primary change type using analysis patterns
- Detect scope from project structure (config.yaml)
- Determine tier (1/2/3) based on commit type
- Extract key modifications
4. Generate commit messages:
- Apply tier-appropriate format
- Primary suggestion (best match)
- Alternative 1 (different scope/angle)
- Alternative 2 (broader/narrower focus)
5. Validate against rules:
- Check forbidden patterns
- Verify required elements present
- Ensure length limits
6. Present to user with explanation and tier infotext
1. 获取暂存的变更内容(仅暂存区,不包含工作区):
- git diff --staged --name-status
- git diff --staged --stat
- git diff --staged
2. 加载配置文件 → frameworks/shared-skills/skills/git-commit-message/config.yaml
3. 分析变更内容:
- 统计修改/新增/删除的文件数量
- 使用分析模式确定主要变更类型
- 根据项目结构(config.yaml)识别变更范围
- 根据提交类型确定分层级别(1/2/3)
- 提取关键修改内容
4. 生成提交信息:
- 应用对应分层的格式要求
- 主推荐信息(最佳匹配)
- 备选信息1(不同范围/角度)
- 备选信息2(更宽泛/更聚焦的描述)
5. 规则校验:
- 检查禁用模式
- 验证必填元素是否存在
- 确保符合长度限制
6. 向用户展示信息及分析说明和分层级别Optional Modes (If Supported By The Caller)
可选模式(需调用方支持)
- : Validate a commit message without generating suggestions (format/type/scope/length/forbidden patterns; then report required Tier 1/2/3 elements if missing).
--validate "<message>" - : Force the tier format (overrides auto-detection).
--tier <1|2|3> - or
--interactive: Ask for confirmation of type, scope, and summary before final output.-i
- : 校验提交信息的格式/类型/范围/长度/禁用模式,无需生成建议;若缺少Tier 1/2/3的必填元素则进行提示。
--validate "<message>" - :强制使用指定分层格式(覆盖自动检测结果)。
--tier <1|2|3> - 或
--interactive:在最终输出前,确认提交类型、范围和摘要内容。-i
Output Format
输出格式
[NOTE] Suggested Commit Messages (based on X files changed)
PRIMARY:
feat(api): add user authentication endpoints
ALTERNATIVES:
1. feat(auth): implement JWT token validation
2. feat: add user authentication system
ANALYSIS:
- 3 files modified in src/api/
- New functions: authenticateUser, generateToken
- Primary change: new feature (authentication)
- Scope detected: api/auth[注意] 建议的提交信息(基于X个文件的变更)
主推荐:
feat(api): add user authentication endpoints
备选信息:
1. feat(auth): implement JWT token validation
2. feat: add user authentication system
分析说明:
- src/api/目录下3个文件被修改
- 新增函数:authenticateUser, generateToken
- 主要变更:新功能(身份认证)
- 识别的范围:api/authConventional Commits Quick Reference
Conventional Commits 快速参考
Type Guidelines:
- : User-facing features or API additions
feat - : Corrects incorrect behavior
fix - : Improves code without changing behavior
refactor - : README, comments, documentation files
docs - : Formatting only (prettier, eslint --fix)
style - : Test files or test utilities
test - : Build scripts, package updates, config
chore - : Measurable performance improvements
perf - : GitHub Actions, CircleCI, build pipelines
ci
Scope Guidelines:
- Use lowercase
- Be specific but not too narrow
- Match your project's module structure
- Omit if changes span multiple unrelated areas
Description Guidelines:
- Start with lowercase verb
- No period at the end
- Be specific and concise
- Focus on user impact for and
featfix
类型指南:
- : 面向用户的功能或API新增
feat - : 修正错误行为
fix - : 优化代码但不改变功能逻辑
refactor - : README、注释、文档文件变更
docs - : 仅格式调整(prettier、eslint --fix)
style - : 测试文件或测试工具变更
test - : 构建脚本、依赖更新、配置变更
chore - : 可量化的性能优化
perf - : GitHub Actions、CircleCI、构建流水线变更
ci
范围指南:
- 使用小写字母
- 具体但不过于狭窄
- 匹配项目的模块结构
- 若变更涉及多个不相关领域则省略范围
描述指南:
- 以小写动词开头
- 结尾不加句号
- 具体且简洁
- 对于和
feat,聚焦于用户影响fix
Edge Cases
边缘场景处理
Multiple unrelated changes:
- Suggest splitting into separate commits
- If forced to combine, use broader scope or omit scope
Breaking changes:
- Append exclamation mark after type/scope (example: feat(api)!: change auth flow)
- Include BREAKING CHANGE in body (handled by user)
WIP or experimental:
- Use or
chore(wip): descriptionfeat(experimental): description
No meaningful changes:
- Detect and warn: "No staged changes detected"
- Suggest commands
git add
多个不相关变更:
- 建议拆分为多个独立提交
- 若必须合并,使用更宽泛的范围或省略范围
破坏性变更:
- 在类型/范围后添加感叹号(示例:feat(api)!: change auth flow)
- 在正文部分包含BREAKING CHANGE说明(由用户自行补充)
进行中或实验性变更:
- 使用 或
chore(wip): descriptionfeat(experimental): description
无有效变更:
- 检测到后提示:"未检测到暂存的变更内容"
- 建议执行命令
git add
Integration Points
集成方式
Pre-commit hook: Triggered before commit (if installed/configured)
Slash command: Manual invocation via
Direct skill call: From other skills or tools
/commit-msg提交前钩子:提交前自动触发(已安装/配置的情况下)
斜杠命令:通过手动调用
直接调用:被其他工具或技能调用
/commit-msgBest Practices
最佳实践
- Analyze context: Look at file paths, function names, import statements
- Prioritize clarity: Prefer obvious descriptions over clever ones
- Respect conventions: Follow project's existing commit patterns if detected
- Avoid hallucination: Only describe what's actually in the diff
- Be concise: 50 chars is ideal, 72 is maximum for first line
- 分析上下文:参考文件路径、函数名、导入语句
- 优先清晰度:选择直白的描述而非花哨的表达
- 遵循约定:若检测到项目已有提交模式则遵循该模式
- 避免虚构:仅描述差异中实际存在的内容
- 保持简洁:第一行理想长度为50字符,最大不超过72字符
Example Analyses
分析示例
Scenario 1: New React component
Files: src/components/UserProfile.tsx, src/components/UserProfile.test.tsx
Changes: +120 lines, component definition, props interface, tests
Message: feat(components): add UserProfile componentScenario 2: Bug fix in API
Files: src/api/auth.ts
Changes: -5 +8 lines, fix token expiration check
Message: fix(auth): correct token expiration validationScenario 3: Documentation update
Files: README.md, docs/api.md
Changes: +45 lines documentation
Message: docs: update API documentation and READMEScenario 4: Dependency update
Files: package.json, package-lock.json
Changes: version bumps for eslint, typescript
Message: chore(deps): update eslint and typescript场景1:新增React组件
文件:src/components/UserProfile.tsx, src/components/UserProfile.test.tsx
变更:新增120行代码,包含组件定义、props接口和测试用例
提交信息:feat(components): add UserProfile component场景2:API漏洞修复
文件:src/api/auth.ts
变更:删除5行,新增8行,修复令牌过期检查逻辑
提交信息:fix(auth): correct token expiration validation场景3:文档更新
文件:README.md, docs/api.md
变更:新增45行文档内容
提交信息:docs: update API documentation and README场景4:依赖更新
文件:package.json, package-lock.json
变更:eslint和typescript版本升级
提交信息:chore(deps): update eslint and typescriptAnalysis Patterns: Smart Type Detection
分析模式:智能类型检测
The skill uses pattern matching to intelligently detect commit types from diffs:
本工具使用模式匹配从差异内容中智能检测提交类型:
feat Detection
feat检测
- New files created (especially in src/, components/, api/)
- New functions/classes exported (,
export function)export class - New API routes (,
app.get, etc.)router.post - New assets/skills (in .claude/, custom-gpt/, etc.)
- Threshold: 20+ lines added typically indicates feature
- 新增文件(尤其是src/、components/、api/目录下)
- 新增导出的函数/类(、
export function)export class - 新增API路由(、
app.get等)router.post - 新增资源/技能(.claude/、custom-gpt/等目录下)
- 阈值:新增20行以上代码通常判定为功能新增
fix Detection
fix检测
- Test file changes (often indicates bug reproduction)
- New conditionals (validation fixes)
- Error handling additions (,
try,catch)throw - Input validation (,
validate,sanitize)check - Commit message hints: Words like "bug", "issue", "error", "crash"
- 测试文件变更(通常表示漏洞复现)
- 新增条件判断(校验逻辑修复)
- 新增错误处理(、
try、catch)throw - 输入校验(、
validate、sanitize)check - 提交信息提示词:包含"bug"、"issue"、"error"、"crash"等词汇
refactor Detection
refactor检测
- Balanced changes (similar additions and deletions)
- Function renames/moves (same logic, different location)
- No new features or fixes
- Test coverage unchanged
- Keywords: "extract", "move", "rename", "reorganize"
- 均衡的变更(新增和删除代码行数相近)
- 函数重命名/移动(逻辑不变,位置变更)
- 无新功能或修复
- 测试覆盖率无变化
- 关键词:"extract"、"move"、"rename"、"reorganize"
docs Detection
docs检测
- File patterns: ,
.md,.txt,README,CHANGELOG/docs/ - Pure documentation changes (no code modifications)
- Mixed code+docs: Prefer code type, note docs in description
- 文件模式:、
.md、.txt、README、CHANGELOG目录/docs/ - 纯文档变更(无代码修改)
- 代码+文档混合变更:优先标记为代码变更类型,在描述中提及文档更新
test Detection
test检测
- File patterns: ,
test.js,spec.ts,__tests__//tests/ - Test framework patterns: ,
describe,it,test,expectassert
- 文件模式:、
test.js、spec.ts、__tests__/目录/tests/ - 测试框架模式:、
describe、it、test、expectassert
style Detection
style检测
- CSS/styling files: ,
.css,.scss,.sass.less - Formatter configs: ,
prettiereslint - Whitespace-only changes
- Keywords: "formatting", "indent", "whitespace"
- CSS/样式文件:、
.css、.scss、.sass.less - 格式化工具配置:、
prettiereslint - 仅空白字符变更
- 关键词:"formatting"、"indent"、"whitespace"
chore Detection
chore检测
- Dependency files: ,
package.json,requirements.txtGemfile - Lock files: ,
package-lock.jsonyarn.lock - Config files: ,
.gitignore.env - Keywords: "dependency", "deps", "upgrade", "bump"
- 依赖文件:、
package.json、requirements.txtGemfile - 锁文件:、
package-lock.jsonyarn.lock - 配置文件:、
.gitignore.env - 关键词:"dependency"、"deps"、"upgrade"、"bump"
Configuration
配置
Project-specific configuration loaded from :
config.yaml- Scope mapping: Maps directory patterns to scope names (e.g., →
frameworks/claude-code-kit/**)claude-kit - Tier rules: Defines which commit types require which tier format
- Forbidden patterns: Blocks commits with generic messages or assistant/tool attribution
- Analysis patterns: Customizes type detection logic for your codebase
- Validation mode: (block),
strict(warn), orwarningdisabled
项目专属配置从加载:
config.yaml- 范围映射:将目录模式映射为范围名称(例如:→
frameworks/claude-code-kit/**)claude-kit - 分层规则:定义不同提交类型对应的分层格式
- 禁用模式:拦截通用模糊信息或工具/助手署名
- 分析模式:针对代码库自定义类型检测逻辑
- 校验模式:(拦截)、
strict(警告)或warning(禁用)disabled
Forbidden Patterns (Validation)
禁用模式(校验规则)
The skill automatically blocks commits with these patterns:
本工具会自动拦截包含以下模式的提交信息:
Generic/Vague Messages
通用/模糊信息
- [FAIL] "Update files" → [OK] "docs: update API reference"
- [FAIL] "Fix stuff" → [OK] "fix(auth): correct token validation"
- [FAIL] "Change code" → [OK] "refactor(utils): simplify date formatting"
- [失败] "Update files" → [正确] "docs: update API reference"
- [失败] "Fix stuff" → [正确] "fix(auth): correct token validation"
- [失败] "Change code" → [正确] "refactor(utils): simplify date formatting"
Assistant/Tool Attribution (Per Repository Policy)
助手/工具署名(遵循仓库政策)
- [FAIL] "Generated with Claude Code"
- [FAIL] "Co-Authored-By: Claude noreply@anthropic.com"
- [FAIL] Any assistant/tool attribution in commit messages
- [失败] "Generated with Claude Code"
- [失败] "Co-Authored-By: Claude noreply@anthropic.com"
- [失败] 提交信息中包含任何助手/工具署名
Work-in-Progress Markers
进行中标记
- [WARNING] "WIP: feature" (warning - should be squashed before merge)
- [WARNING] "temp: quick fix" (warning - should be squashed)
- [警告] "WIP: feature"(警告 - 合并前应压缩提交)
- [警告] "temp: quick fix"(警告 - 合并前应压缩提交)
Missing Type
缺少类型前缀
- [FAIL] Commits without type prefix (feat, fix, docs, etc.)
- [失败] 提交信息无前缀类型(feat、fix、docs等)
Error Handling
错误处理
- No staged changes: Run and guide user to
git statusfilesgit add - Binary files only: Note that commit message should mention file types
- Merge conflicts: Detect and suggest
chore: resolve merge conflicts - Git not available: Graceful failure with helpful error message
- Forbidden pattern detected: Show error with examples and block commit (strict mode)
- Missing required elements: List what's missing based on tier requirements
- Length exceeded: Show character count and suggest shortening
- 无暂存变更:执行并引导用户执行
git status命令git add - 仅二进制文件变更:提示提交信息应提及文件类型
- 合并冲突:检测到后建议使用
chore: resolve merge conflicts - Git不可用:友好提示错误信息
- 检测到禁用模式:显示错误示例并拦截提交(严格模式下)
- 缺少必填元素:根据分层要求列出缺失的内容
- 长度超出限制:显示字符数并建议缩短
Integration with Repository
与仓库的集成
This skill integrates with the AI-Agents repository standards:
- CLAUDE.md reference: Mandatory skill usage before commits
- config.yaml: Project-specific scope mappings and rules
- Pre-commit hook: Automatic activation before git commits
- CONTRIBUTING.md: Commit guidelines for contributors
本工具符合AI-Agents仓库的标准:
- CLAUDE.md参考:提交前必须使用本工具
- config.yaml:项目专属的范围映射和规则
- 提交前钩子:Git提交前自动触发
- CONTRIBUTING.md:为贡献者提供提交指南
Commit Message Template
提交信息模板
assets/template-commit-message.md — Copy-paste template and good/bad examples.
Use it to standardize messages and keep history automation-friendly.
type(scope): summaryassets/template-commit-message.md — 可复制的模板及正反示例。
使用该模板标准化格式的提交信息,使提交历史更易于自动化处理。
type(scope): summarySecurity-Sensitive Commits
安全敏感提交
assets/template-security-commits.md — Guide for handling security-sensitive changes.
assets/template-security-commits.md — 处理安全敏感变更的指南。
Key Sections
核心章节
- Pre-Commit Security Checklist — Secrets detection, prohibited patterns
- Security-Related Commit Types — Security fix, enhancement, configuration
- Accidental Secret Commits — Immediate response, rotation, history cleanup
- Sensitive File Patterns — .gitignore templates, files that should never be committed
- Audit Trail Requirements — CVE, CVSS, CWE metadata for security commits
- 提交前安全检查清单 — 敏感信息检测、禁用模式检查
- 安全相关提交类型 — 安全修复、增强、配置变更
- 意外提交敏感信息的处理 — 立即响应、密钥轮换、历史清理
- 敏感文件模式 — .gitignore模板、禁止提交的文件类型
- 审计追踪要求 — 安全提交需包含CVE、CVSS、CWE元数据
Do / Avoid
应做/避免
GOOD: Do
正确做法
- Run secrets scan before every commit
- Rotate secrets immediately if exposed
- Use environment variables for credentials
- Document security fixes with CVE/CVSS
- Require security team review for auth changes
- Keep .gitignore updated for secret patterns
- 每次提交前运行敏感信息扫描
- 若敏感信息泄露立即轮换密钥
- 使用环境变量存储凭证
- 用CVE/CVSS信息记录安全修复
- 身份认证变更需经安全团队审核
- 持续更新.gitignore以覆盖敏感信息模式
BAD: Avoid
错误做法
- Committing secrets "temporarily"
- Using hardcoded credentials in tests
- Storing real credentials in example files
- Assuming deleted secrets are safe
- Committing before secrets scan completes
- Using generic commit messages for security fixes
- “临时”提交敏感信息
- 在测试中使用真实凭证
- 在示例文件中存储真实凭证
- 认为删除后的敏感信息已安全
- 未完成敏感信息扫描就提交
- 安全修复使用通用模糊的提交信息
Anti-Patterns
反模式
| Anti-Pattern | Problem | Fix |
|---|---|---|
| "Add secrets later" | Secrets committed accidentally | Use env vars from start |
| Secrets in tests | Real credentials in repo | Use mocks/test credentials |
| Force push to hide | History still recoverable | Rotate + document |
| Vague security commits | No audit trail | Include CVE/CVSS |
| No pre-commit scan | Secrets reach remote | Install gitleaks hook |
| 反模式 | 问题 | 修复方案 |
|---|---|---|
| "后续添加敏感信息" | 意外提交敏感信息 | 从项目初期就使用环境变量 |
| 测试中包含敏感信息 | 仓库中存在真实凭证 | 使用模拟/测试凭证 |
| 强制推送隐藏变更 | 历史记录仍可恢复 | 轮换密钥并记录事件 |
| 安全提交信息模糊 | 无审计追踪 | 包含CVE/CVSS信息 |
| 无提交前扫描 | 敏感信息推送到远程仓库 | 安装gitleaks钩子 |
Optional: AI/Automation
可选:AI/自动化
Note: AI suggestions should preserve human intent.
- Commit message suggestions — Draft from diff analysis
- Type detection — Pattern-based commit type inference
- Scope detection — Auto-detect from changed paths
注意:AI生成的建议应保留用户的真实意图。
- 提交信息建议 — 基于差异分析生成草稿
- 类型检测 — 基于模式的提交类型推断
- 范围识别 — 从变更路径自动识别范围
Bounded Claims
边界说明
- AI-generated messages need human review and modification
- Automated type detection may miss context
- Security commits always need human judgment
Version: 2.1.1
Last Updated: 2026-01-26
Repository: AI-Agents (documentation repository)
Conventional Commits Spec: https://www.conventionalcommits.org/
- AI生成的信息需要人工审核和修改
- 自动化类型检测可能会遗漏上下文信息
- 安全相关提交始终需要人工判断
版本: 2.1.1
最后更新: 2026-01-26
仓库: AI-Agents(文档仓库)
Conventional Commits 规范: https://www.conventionalcommits.org/