sumulige-claude 1.0.5 → 1.0.7

package/.claude/commands/review.md

@@ -0,0 +1,61 @@
+---
+description: Review current changes before committing
+---
+
+Review the current uncommitted or staged changes.
+
+## Step 1: Show Changes
+
+```bash
+git status
+
+# Show unstaged changes
+git diff
+
+# Show staged changes
+git diff --staged
+```
+
+## Step 2: Code Review Checklist
+
+Review the changes for:
+
+### Functionality
+- [ ] Does the change accomplish the intended goal?
+- [ ] Are there any obvious bugs or logic errors?
+- [ ] Are edge cases handled?
+
+### Security
+- [ ] No hardcoded credentials or API keys
+- [ ] No SQL injection, XSS, or other vulnerabilities
+- [ ] Proper input validation
+
+### Code Quality
+- [ ] Code is readable and self-documenting
+- [ ] No unnecessary complexity
+- [ ] Follows DRY (Don't Repeat Yourself)
+- [ ] Proper error handling
+
+### Testing
+- [ ] Tests cover new functionality
+- [ ] No tests are broken
+- [ ] Edge cases are tested
+
+### Performance
+- [ ] No obvious performance issues
+- [ ] No unnecessary database queries or API calls
+- [ ] Proper use of caching (if applicable)
+
+## Step 3: Provide Feedback
+
+For each issue found:
+1. Point out the specific file and line
+2. Explain the issue
+3. Suggest a fix
+
+## Step 4: Summary
+
+Provide an overall assessment:
+- ✅ Ready to commit
+- ⚠️ Minor issues to address
+- ❌ Major issues that need fixing

package/.claude/commands/sessions.md

@@ -0,0 +1,62 @@
+---
+description: Manage and display parallel Claude sessions
+---
+
+Manage and display information about parallel Claude sessions.
+
+## Show Session Status
+
+Display all active parallel sessions:
+
+```bash
+node .claude/hooks/multi-session.cjs --status
+```
+
+## Session Management Best Practices
+
+Based on Boris Cherny's workflow:
+
+### Terminal Sessions (Local)
+- Number your terminal tabs 1-5
+- Use system notifications to know when Claude needs input
+- Run different agents in different tabs:
+  - Tab 1: Conductor (planning/coordination)
+  - Tab 2: Architect (design/architecture)
+  - Tab 3: Builder (implementation)
+  - Tab 4: Reviewer (code review)
+  - Tab 5: Explorer (research)
+
+### Web Sessions (claude.ai/code)
+- Run 5-10 web sessions in parallel with local sessions
+- Use `&` to hand off local sessions to web
+- Use `--teleport` to switch between local and web
+- Start sessions from mobile Claude app for async work
+
+### Session Handoff
+
+To hand off a session to web:
+```bash
+# End local session with summary
+# The session context will be available in claude.ai/code
+```
+
+## View Session History
+
+```bash
+cat .claude/sessions/active-sessions.json
+```
+
+## Clean Old Sessions
+
+Sessions older than 1 hour are automatically cleaned up. To manually clean:
+
+```bash
+rm .claude/sessions/active-sessions.json
+```
+
+## Tips
+
+1. **Use Plan mode** (Shift+Tab twice) for most sessions
+2. **Switch to auto-accept** after approving a plan
+3. **Let sessions run in parallel** - don't wait for one to finish
+4. **Check notifications** to see when sessions need input

package/.claude/commands/skill-create.md

@@ -0,0 +1,131 @@
+---
+description: Create a new skill with template
+---
+
+Create a new skill using the standard template.
+
+## Step 1: Get Skill Information
+
+Ask the user for:
+1. **Skill name** (kebab-case, e.g., `code-reviewer`)
+2. **Description** (one-line summary)
+3. **Category** (development, design, analysis, workflow, etc.)
+4. **Difficulty** (beginner, intermediate, advanced)
+
+## Step 2: Create Skill Directory
+
+Create the skill directory structure:
+
+```bash
+mkdir -p .claude/skills/{skill-name}/{templates,examples}
+```
+
+## Step 3: Generate SKILL.md
+
+Use this template:
+
+```markdown
+# {Skill Name}
+
+> {Description}
+
+**版本**: 1.0.0
+**作者**: AI
+**标签**: [{category}]
+**难度**: {difficulty}
+
+---
+
+## 概述
+
+{Detailed description of what this skill does}
+
+## 适用场景
+
+- {Scenario 1}
+- {Scenario 2}
+- {Scenario 3}
+
+## 触发关键词
+
+```
+{trigger keywords}
+```
+
+## 使用方法
+
+### 基础用法
+
+{Example usage}
+
+## 输出格式
+
+{Output format description}
+
+## 注意事项
+
+- {Note 1}
+- {Note 2}
+
+## 相关技能
+
+- [Related Skill](../related-skill/)
+
+## 更新日志
+
+### 1.0.0 ({current-date})
+- 初始版本
+```
+
+## Step 4: Generate metadata.yaml
+
+```yaml
+name: {skill-name}
+version: 1.0.0
+author: AI
+description: {description}
+
+tags:
+  - {category}
+
+triggers:
+  - {trigger1}
+  - {trigger2}
+
+dependencies: []
+difficulty: {difficulty}
+```
+
+## Step 5: Add to RAG Index
+
+Update `.claude/rag/skill-index.json`:
+
+```json
+{
+  "skills": [
+    {
+      "name": "{skill-name}",
+      "description": "{description}",
+      "keywords": ["{trigger1}", "{trigger2}"],
+      "path": ".claude/skills/{skill-name}/SKILL.md"
+    }
+  ]
+}
+```
+
+## Step 6: Verify
+
+Confirm with user:
+- Skill created at `.claude/skills/{skill-name}/`
+- Added to RAG index
+- Ready to use
+
+## Example
+
+User: "Create a skill called api-tester for testing REST APIs"
+
+→ Create `.claude/skills/api-tester/` with:
+- SKILL.md (filled with API testing content)
+- metadata.yaml
+- templates/request.md
+- examples/basic-test.md

package/.claude/commands/test.md

@@ -0,0 +1,56 @@
+---
+description: Run tests and show coverage report
+---
+
+Run the test suite and provide comprehensive results.
+
+## Step 1: Detect Test Framework
+
+Check what test framework is being used:
+
+```bash
+cat package.json | grep -E '"test"|"jest"|"vitest"|"mocha"|"pytest"'
+```
+
+## Step 2: Run Tests
+
+Run the appropriate test command:
+
+```bash
+# Node.js / JavaScript
+npm test
+
+# Python
+pytest
+
+# Rust
+cargo test
+
+# Go
+go test ./...
+```
+
+## Step 3: Show Coverage
+
+If coverage is available, run:
+
+```bash
+npm run test:coverage
+# or
+pytest --cov
+```
+
+## Step 4: Analyze Results
+
+Provide a summary:
+- Total tests run
+- Pass/fail counts
+- Coverage percentage
+- Any failing tests with details
+
+## Step 5: Fix Failures (if any)
+
+If tests fail, help the user:
+1. Identify the root cause
+2. Fix the issue
+3. Re-run tests to verify

package/.claude/commands/todos.md

@@ -0,0 +1,99 @@
+---
+description: Manage project todos and tasks
+---
+
+Manage project tasks in the development/todos directory.
+
+## Show Task Overview
+
+Display the task overview:
+
+```bash
+cat development/todos/INDEX.md
+```
+
+## Task Operations
+
+### Create a New Task
+
+When user asks to create a task:
+1. Create file in `development/todos/active/`
+2. Use kebab-case for filename (e.g., `user-login.md`)
+3. Use the template format:
+
+```markdown
+# [Task Name]
+
+**状态**: 🚧 进行中
+**优先级**: P0/P1/P2/P3
+**负责人**: AI/Human
+**分支**: `feature/xxx`
+**创建时间**: YYYY-MM-DD
+**预计完成**: YYYY-MM-DD
+
+## 描述
+
+[Task description]
+
+## 子任务
+
+- [ ] Subtask 1
+- [ ] Subtask 2
+
+## 依赖
+
+- [Dependencies]
+
+## 进度
+
+- [x] Planning
+- [ ] In progress
+- [ ] Testing
+- [ ] Review
+
+## 备注
+
+[Notes]
+```
+
+### Update Task Status
+
+To move a task:
+- **Complete**: Move from `active/` to `completed/`
+- **Backlog**: Move from `active/` to `backlog/`
+- **Archive**: Move from `completed/` to `archived/`
+
+### Update Task Progress
+
+Edit the task file and update:
+- Subtask checkboxes
+- Progress checklist
+- Add notes
+
+## Refresh Task Index
+
+After any task changes, refresh the index:
+
+```bash
+node .claude/hooks/todo-manager.cjs --force
+```
+
+## Task Priority Levels
+
+| Priority | Usage |
+|----------|-------|
+| P0 | Critical - blocks release |
+| P1 | High - important for next milestone |
+| P2 | Medium - normal feature work |
+| P3 | Low - nice to have |
+
+## Examples
+
+User says: "Create a task for implementing user authentication"
+→ Create `active/user-authentication.md`
+
+User says: "Mark the login task as complete"
+→ Move `active/login.md` to `completed/login.md`
+
+User says: "Show all active tasks"
+→ List all files in `development/todos/active/`

package/.claude/commands/verify-work.md

@@ -0,0 +1,63 @@
+---
+description: View and manage pending verification tasks
+---
+
+You are helping the user review and verify completed work.
+
+## Check Pending Tasks
+
+First, read the verification log:
+
+```bash
+cat .claude/verify/verify-log.md 2>/dev/null || echo "No verification log found"
+```
+
+And check pending tasks:
+
+```bash
+cat .claude/verify/.pending-verify.json 2>/dev/null || echo "No pending tasks"
+```
+
+## Verification Process
+
+For each pending task, guide the user through:
+
+1. **What was done** - Summarize the action
+2. **How to verify** - Run appropriate verification commands:
+   - For code changes: run tests, linters
+   - For deployments: check staging environment
+   - For commits: verify CI/CD status
+
+## Common Verification Commands
+
+```bash
+# Run tests
+npm test
+
+# Check test coverage
+npm run test:coverage
+
+# Run linter
+npm run lint
+
+# Type check
+npm run type-check
+
+# Build verification
+npm run build
+
+# Check CI status (if using GitHub)
+gh run list --limit 5
+
+# Check PR status
+gh pr status
+```
+
+## Mark as Complete
+
+After verification is successful, ask the user if they want to:
+- Mark the task as verified (remove from pending)
+- Keep it for later verification
+- Add additional verification steps
+
+To mark as complete, edit `.claude/verify/.pending-verify.json` to remove the completed task.

package/.claude/hooks/code-formatter.cjs

@@ -0,0 +1,187 @@
+#!/usr/bin/env node
+/**
+ * Code Formatter Hook - 自动代码格式化
+ *
+ * 根据 Boris Cherny 的最佳实践，Claude 通常能生成格式良好的代码，
+ * 但这个 hook 处理最后 10% 的格式问题，避免 CI 中的格式错误。
+ *
+ * 触发时机：PostToolUse 事件
+ * 支持语言：JavaScript, TypeScript, Python, Rust, Go, JSON, Markdown
+ */
+
+const fs = require('fs');
+const path = require('path');
+const { spawn } = require('child_process');
+
+const PROJECT_DIR = process.env.CLAUDE_PROJECT_DIR || process.cwd();
+
+// 支持的格式化器配置
+const FORMATTERS = {
+  // JavaScript/TypeScript
+  '.js': { cmd: 'prettier', args: ['--write', '--log-level', 'warn'] },
+  '.jsx': { cmd: 'prettier', args: ['--write', '--log-level', 'warn'] },
+  '.ts': { cmd: 'prettier', args: ['--write', '--log-level', 'warn'] },
+  '.tsx': { cmd: 'prettier', args: ['--write', '--log-level', 'warn'] },
+  '.mjs': { cmd: 'prettier', args: ['--write', '--log-level', 'warn'] },
+  '.cjs': { cmd: 'prettier', args: ['--write', '--log-level', 'warn'] },
+
+  // Python
+  '.py': { cmd: 'black', args: ['--quiet'] },
+
+  // Rust
+  '.rs': { cmd: 'rustfmt', args: [] },
+
+  // Go
+  '.go': { cmd: 'gofmt', args: ['-w'] },
+
+  // JSON
+  '.json': { cmd: 'prettier', args: ['--write', '--log-level', 'warn'] },
+
+  // Markdown
+  '.md': { cmd: 'prettier', args: ['--write', '--log-level', 'warn'] },
+
+  // CSS/SCSS
+  '.css': { cmd: 'prettier', args: ['--write', '--log-level', 'warn'] },
+  '.scss': { cmd: 'prettier', args: ['--write', '--log-level', 'warn'] },
+  '.less': { cmd: 'prettier', args: ['--write', '--log-level', 'warn'] },
+
+  // HTML
+  '.html': { cmd: 'prettier', args: ['--write', '--log-level', 'warn'] },
+  '.htm': { cmd: 'prettier', args: ['--write', '--log-level', 'warn'] },
+
+  // YAML
+  '.yaml': { cmd: 'prettier', args: ['--write', '--log-level', 'warn'] },
+  '.yml': { cmd: 'prettier', args: ['--write', '--log-level', 'warn'] },
+};
+
+// 检查命令是否可用
+function isCommandAvailable(cmd) {
+  try {
+    // 首先尝试 which
+    spawn('which', [cmd], { stdio: 'ignore' });
+
+    // 对于 prettier，额外检查 npx
+    if (cmd === 'prettier') {
+      spawn('npx', [cmd, '--version'], { stdio: 'ignore' });
+    }
+    return true;
+  } catch (e) {
+    return false;
+  }
+}
+
+// 获取工具修改的文件
+function getModifiedFiles() {
+  const toolName = process.env.CLAUDE_TOOL_NAME || '';
+  const toolInput = process.env.CLAUDE_TOOL_INPUT || '';
+
+  // 从工具输入中提取文件路径
+  const filePaths = [];
+
+  // Edit 工具
+  if (toolName === 'Edit') {
+    // Edit 工具的文件路径在 file_path 参数中
+    const match = toolInput.match(/"filePath":\s*"([^"]+)"/);
+    if (match) {
+      filePaths.push(match[1]);
+    }
+  }
+
+  // Write 工具
+  if (toolName === 'Write') {
+    const match = toolInput.match(/"file_path":\s*"([^"]+)"/);
+    if (match) {
+      filePaths.push(match[1]);
+    }
+  }
+
+  // NotebookEdit 工具
+  if (toolName === 'NotebookEdit') {
+    const match = toolInput.match(/"notebook_path":\s*"([^"]+)"/);
+    if (match) {
+      filePaths.push(match[1]);
+    }
+  }
+
+  return filePaths;
+}
+
+// 格式化文件
+function formatFile(filePath) {
+  const ext = path.extname(filePath);
+
+  // 跳过不需要格式化的目录
+  const skipDirs = ['node_modules', '.git', 'dist', 'build', 'target', 'vendor', '.venv'];
+  if (skipDirs.some(dir => filePath.includes(`/${dir}/`) || filePath.includes(`\\${dir}\\`))) {
+    return null;
+  }
+
+  const formatter = FORMATTERS[ext];
+  if (!formatter) {
+    return null;
+  }
+
+  // 检查格式化器是否可用
+  if (!isCommandAvailable(formatter.cmd)) {
+    return null;
+  }
+
+  // 检查文件是否存在
+  if (!fs.existsSync(filePath)) {
+    return null;
+  }
+
+  try {
+    // 对于 prettier，使用 npx 来支持本地安装
+    const cmd = formatter.cmd === 'prettier' ? 'npx' : formatter.cmd;
+    const args = formatter.cmd === 'prettier'
+      ? ['prettier', ...formatter.args, filePath]
+      : [...formatter.args, filePath];
+
+    // 运行格式化器
+    spawn(cmd, args, {
+      stdio: 'ignore',
+      cwd: PROJECT_DIR,
+      detached: true
+    }).unref();
+    return { file: filePath, formatter: formatter.cmd };
+  } catch (e) {
+    return null;
+  }
+}
+
+// 主函数
+function main() {
+  try {
+    const eventType = process.env.CLAUDE_EVENT_TYPE || '';
+
+    // 只在 PostToolUse 事件时运行
+    if (eventType !== 'PostToolUse') {
+      process.exit(0);
+    }
+
+    const modifiedFiles = getModifiedFiles();
+
+    if (modifiedFiles.length === 0) {
+      process.exit(0);
+    }
+
+    // 格式化所有修改的文件
+    const formatted = modifiedFiles
+      .map(formatFile)
+      .filter(result => result !== null);
+
+    // 输出格式化结果（可选，用于调试）
+    if (formatted.length > 0 && process.env.DEBUG_FORMATTER) {
+      console.log(`\n🎨 [格式化] 已格式化 ${formatted.length} 个文件:`);
+      formatted.forEach(f => console.log(`   - ${f.file} (${f.formatter})`));
+    }
+
+  } catch (e) {
+    // 完全静默，不输出任何错误
+  }
+
+  process.exit(0);
+}
+
+main();