@pzy560117/codex-harness 0.1.2 → 0.1.4

package/package-source/docs/codex-harness-engineering/templates/package-assets/skills/clickhouse-io/SKILL.md

@@ -1,429 +0,0 @@
----
-name: clickhouse-io
-description: ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.
----
-
-# ClickHouse Analytics Patterns
-
-ClickHouse-specific patterns for high-performance analytics and data engineering.
-
-## Overview
-
-ClickHouse is a column-oriented database management system (DBMS) for online analytical processing (OLAP). It's optimized for fast analytical queries on large datasets.
-
-**Key Features:**
-- Column-oriented storage
-- Data compression
-- Parallel query execution
-- Distributed queries
-- Real-time analytics
-
-## Table Design Patterns
-
-### MergeTree Engine (Most Common)
-
-```sql
-CREATE TABLE markets_analytics (
-    date Date,
-    market_id String,
-    market_name String,
-    volume UInt64,
-    trades UInt32,
-    unique_traders UInt32,
-    avg_trade_size Float64,
-    created_at DateTime
-) ENGINE = MergeTree()
-PARTITION BY toYYYYMM(date)
-ORDER BY (date, market_id)
-SETTINGS index_granularity = 8192;
-```
-
-### ReplacingMergeTree (Deduplication)
-
-```sql
--- For data that may have duplicates (e.g., from multiple sources)
-CREATE TABLE user_events (
-    event_id String,
-    user_id String,
-    event_type String,
-    timestamp DateTime,
-    properties String
-) ENGINE = ReplacingMergeTree()
-PARTITION BY toYYYYMM(timestamp)
-ORDER BY (user_id, event_id, timestamp)
-PRIMARY KEY (user_id, event_id);
-```
-
-### AggregatingMergeTree (Pre-aggregation)
-
-```sql
--- For maintaining aggregated metrics
-CREATE TABLE market_stats_hourly (
-    hour DateTime,
-    market_id String,
-    total_volume AggregateFunction(sum, UInt64),
-    total_trades AggregateFunction(count, UInt32),
-    unique_users AggregateFunction(uniq, String)
-) ENGINE = AggregatingMergeTree()
-PARTITION BY toYYYYMM(hour)
-ORDER BY (hour, market_id);
-
--- Query aggregated data
-SELECT
-    hour,
-    market_id,
-    sumMerge(total_volume) AS volume,
-    countMerge(total_trades) AS trades,
-    uniqMerge(unique_users) AS users
-FROM market_stats_hourly
-WHERE hour >= toStartOfHour(now() - INTERVAL 24 HOUR)
-GROUP BY hour, market_id
-ORDER BY hour DESC;
-```
-
-## Query Optimization Patterns
-
-### Efficient Filtering
-
-```sql
--- ✅ GOOD: Use indexed columns first
-SELECT *
-FROM markets_analytics
-WHERE date >= '2025-01-01'
-  AND market_id = 'market-123'
-  AND volume > 1000
-ORDER BY date DESC
-LIMIT 100;
-
--- ❌ BAD: Filter on non-indexed columns first
-SELECT *
-FROM markets_analytics
-WHERE volume > 1000
-  AND market_name LIKE '%election%'
-  AND date >= '2025-01-01';
-```
-
-### Aggregations
-
-```sql
--- ✅ GOOD: Use ClickHouse-specific aggregation functions
-SELECT
-    toStartOfDay(created_at) AS day,
-    market_id,
-    sum(volume) AS total_volume,
-    count() AS total_trades,
-    uniq(trader_id) AS unique_traders,
-    avg(trade_size) AS avg_size
-FROM trades
-WHERE created_at >= today() - INTERVAL 7 DAY
-GROUP BY day, market_id
-ORDER BY day DESC, total_volume DESC;
-
--- ✅ Use quantile for percentiles (more efficient than percentile)
-SELECT
-    quantile(0.50)(trade_size) AS median,
-    quantile(0.95)(trade_size) AS p95,
-    quantile(0.99)(trade_size) AS p99
-FROM trades
-WHERE created_at >= now() - INTERVAL 1 HOUR;
-```
-
-### Window Functions
-
-```sql
--- Calculate running totals
-SELECT
-    date,
-    market_id,
-    volume,
-    sum(volume) OVER (
-        PARTITION BY market_id
-        ORDER BY date
-        ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW
-    ) AS cumulative_volume
-FROM markets_analytics
-WHERE date >= today() - INTERVAL 30 DAY
-ORDER BY market_id, date;
-```
-
-## Data Insertion Patterns
-
-### Bulk Insert (Recommended)
-
-```typescript
-import { ClickHouse } from 'clickhouse'
-
-const clickhouse = new ClickHouse({
-  url: process.env.CLICKHOUSE_URL,
-  port: 8123,
-  basicAuth: {
-    username: process.env.CLICKHOUSE_USER,
-    password: process.env.CLICKHOUSE_PASSWORD
-  }
-})
-
-// ✅ Batch insert (efficient)
-async function bulkInsertTrades(trades: Trade[]) {
-  const values = trades.map(trade => `(
-    '${trade.id}',
-    '${trade.market_id}',
-    '${trade.user_id}',
-    ${trade.amount},
-    '${trade.timestamp.toISOString()}'
-  )`).join(',')
-
-  await clickhouse.query(`
-    INSERT INTO trades (id, market_id, user_id, amount, timestamp)
-    VALUES ${values}
-  `).toPromise()
-}
-
-// ❌ Individual inserts (slow)
-async function insertTrade(trade: Trade) {
-  // Don't do this in a loop!
-  await clickhouse.query(`
-    INSERT INTO trades VALUES ('${trade.id}', ...)
-  `).toPromise()
-}
-```
-
-### Streaming Insert
-
-```typescript
-// For continuous data ingestion
-import { createWriteStream } from 'fs'
-import { pipeline } from 'stream/promises'
-
-async function streamInserts() {
-  const stream = clickhouse.insert('trades').stream()
-
-  for await (const batch of dataSource) {
-    stream.write(batch)
-  }
-
-  await stream.end()
-}
-```
-
-## Materialized Views
-
-### Real-time Aggregations
-
-```sql
--- Create materialized view for hourly stats
-CREATE MATERIALIZED VIEW market_stats_hourly_mv
-TO market_stats_hourly
-AS SELECT
-    toStartOfHour(timestamp) AS hour,
-    market_id,
-    sumState(amount) AS total_volume,
-    countState() AS total_trades,
-    uniqState(user_id) AS unique_users
-FROM trades
-GROUP BY hour, market_id;
-
--- Query the materialized view
-SELECT
-    hour,
-    market_id,
-    sumMerge(total_volume) AS volume,
-    countMerge(total_trades) AS trades,
-    uniqMerge(unique_users) AS users
-FROM market_stats_hourly
-WHERE hour >= now() - INTERVAL 24 HOUR
-GROUP BY hour, market_id;
-```
-
-## Performance Monitoring
-
-### Query Performance
-
-```sql
--- Check slow queries
-SELECT
-    query_id,
-    user,
-    query,
-    query_duration_ms,
-    read_rows,
-    read_bytes,
-    memory_usage
-FROM system.query_log
-WHERE type = 'QueryFinish'
-  AND query_duration_ms > 1000
-  AND event_time >= now() - INTERVAL 1 HOUR
-ORDER BY query_duration_ms DESC
-LIMIT 10;
-```
-
-### Table Statistics
-
-```sql
--- Check table sizes
-SELECT
-    database,
-    table,
-    formatReadableSize(sum(bytes)) AS size,
-    sum(rows) AS rows,
-    max(modification_time) AS latest_modification
-FROM system.parts
-WHERE active
-GROUP BY database, table
-ORDER BY sum(bytes) DESC;
-```
-
-## Common Analytics Queries
-
-### Time Series Analysis
-
-```sql
--- Daily active users
-SELECT
-    toDate(timestamp) AS date,
-    uniq(user_id) AS daily_active_users
-FROM events
-WHERE timestamp >= today() - INTERVAL 30 DAY
-GROUP BY date
-ORDER BY date;
-
--- Retention analysis
-SELECT
-    signup_date,
-    countIf(days_since_signup = 0) AS day_0,
-    countIf(days_since_signup = 1) AS day_1,
-    countIf(days_since_signup = 7) AS day_7,
-    countIf(days_since_signup = 30) AS day_30
-FROM (
-    SELECT
-        user_id,
-        min(toDate(timestamp)) AS signup_date,
-        toDate(timestamp) AS activity_date,
-        dateDiff('day', signup_date, activity_date) AS days_since_signup
-    FROM events
-    GROUP BY user_id, activity_date
-)
-GROUP BY signup_date
-ORDER BY signup_date DESC;
-```
-
-### Funnel Analysis
-
-```sql
--- Conversion funnel
-SELECT
-    countIf(step = 'viewed_market') AS viewed,
-    countIf(step = 'clicked_trade') AS clicked,
-    countIf(step = 'completed_trade') AS completed,
-    round(clicked / viewed * 100, 2) AS view_to_click_rate,
-    round(completed / clicked * 100, 2) AS click_to_completion_rate
-FROM (
-    SELECT
-        user_id,
-        session_id,
-        event_type AS step
-    FROM events
-    WHERE event_date = today()
-)
-GROUP BY session_id;
-```
-
-### Cohort Analysis
-
-```sql
--- User cohorts by signup month
-SELECT
-    toStartOfMonth(signup_date) AS cohort,
-    toStartOfMonth(activity_date) AS month,
-    dateDiff('month', cohort, month) AS months_since_signup,
-    count(DISTINCT user_id) AS active_users
-FROM (
-    SELECT
-        user_id,
-        min(toDate(timestamp)) OVER (PARTITION BY user_id) AS signup_date,
-        toDate(timestamp) AS activity_date
-    FROM events
-)
-GROUP BY cohort, month, months_since_signup
-ORDER BY cohort, months_since_signup;
-```
-
-## Data Pipeline Patterns
-
-### ETL Pattern
-
-```typescript
-// Extract, Transform, Load
-async function etlPipeline() {
-  // 1. Extract from source
-  const rawData = await extractFromPostgres()
-
-  // 2. Transform
-  const transformed = rawData.map(row => ({
-    date: new Date(row.created_at).toISOString().split('T')[0],
-    market_id: row.market_slug,
-    volume: parseFloat(row.total_volume),
-    trades: parseInt(row.trade_count)
-  }))
-
-  // 3. Load to ClickHouse
-  await bulkInsertToClickHouse(transformed)
-}
-
-// Run periodically
-setInterval(etlPipeline, 60 * 60 * 1000)  // Every hour
-```
-
-### Change Data Capture (CDC)
-
-```typescript
-// Listen to PostgreSQL changes and sync to ClickHouse
-import { Client } from 'pg'
-
-const pgClient = new Client({ connectionString: process.env.DATABASE_URL })
-
-pgClient.query('LISTEN market_updates')
-
-pgClient.on('notification', async (msg) => {
-  const update = JSON.parse(msg.payload)
-
-  await clickhouse.insert('market_updates', [
-    {
-      market_id: update.id,
-      event_type: update.operation,  // INSERT, UPDATE, DELETE
-      timestamp: new Date(),
-      data: JSON.stringify(update.new_data)
-    }
-  ])
-})
-```
-
-## Best Practices
-
-### 1. Partitioning Strategy
-- Partition by time (usually month or day)
-- Avoid too many partitions (performance impact)
-- Use DATE type for partition key
-
-### 2. Ordering Key
-- Put most frequently filtered columns first
-- Consider cardinality (high cardinality first)
-- Order impacts compression
-
-### 3. Data Types
-- Use smallest appropriate type (UInt32 vs UInt64)
-- Use LowCardinality for repeated strings
-- Use Enum for categorical data
-
-### 4. Avoid
-- SELECT * (specify columns)
-- FINAL (merge data before query instead)
-- Too many JOINs (denormalize for analytics)
-- Small frequent inserts (batch instead)
-
-### 5. Monitoring
-- Track query performance
-- Monitor disk usage
-- Check merge operations
-- Review slow query log
-
-**Remember**: ClickHouse excels at analytical workloads. Design tables for your query patterns, batch inserts, and leverage materialized views for real-time aggregations.

package/package-source/docs/codex-harness-engineering/templates/package-assets/skills/code-review/SKILL.md

@@ -1,171 +0,0 @@
----
-name: code-review
-description: Code Review Skill
----
-
-# Code Review Skill
-
-代码审查清单和 PR 规范。
-
-## PR 提交规范
-
-### PR 标题格式
-```
-<type>(<scope>): <description>
-
-示例:
-feat(auth): 添加 OAuth2.0 登录功能
-fix(api): 修复用户列表分页问题
-refactor(db): 优化查询性能
-```
-
-### PR 描述模板
-```markdown
-## 变更说明
-简要描述本次变更的内容和目的
-
-## 变更类型
-- [ ] 新功能
-- [ ] Bug 修复
-- [ ] 重构
-- [ ] 性能优化
-- [ ] 文档更新
-
-## 关联 Issue
-Closes #123
-
-## 测试说明
-- [ ] 单元测试通过
-- [ ] 集成测试通过
-- [ ] 手动测试通过
-
-## 截图（如适用）
-UI 变更请附截图
-
-## 检查清单
-- [ ] 代码符合项目规范
-- [ ] 已添加必要的测试
-- [ ] 已更新相关文档
-- [ ] 无敏感信息泄露
-```
-
-## 代码审查清单
-
-### 功能正确性
-- [ ] 代码实现了预期功能
-- [ ] 边界条件处理正确
-- [ ] 错误处理完善
-- [ ] 无明显的逻辑漏洞
-
-### 代码质量
-- [ ] 命名清晰有意义
-- [ ] 函数职责单一
-- [ ] 无重复代码
-- [ ] 复杂逻辑有注释
-- [ ] 无硬编码的魔法数字
-
-### 安全性
-- [ ] 输入验证完整
-- [ ] 无 SQL 注入风险
-- [ ] 无 XSS 风险
-- [ ] 敏感信息已脱敏
-- [ ] 权限检查到位
-
-### 性能
-- [ ] 无 N+1 查询
-- [ ] 无不必要的循环
-- [ ] 大数据量有分页
-- [ ] 耗时操作有缓存或异步
-
-### 可维护性
-- [ ] 代码结构清晰
-- [ ] 依赖关系合理
-- [ ] 易于测试
-- [ ] 易于扩展
-
-## 审查反馈规范
-
-### 评论分类
-```
-[必须] 必须修改才能合并
-[建议] 建议修改，可讨论
-[疑问] 需要解释或讨论
-[赞] 写得好的地方
-```
-
-### 反馈示例
-```
-[必须] 这里存在 SQL 注入风险，请使用参数化查询
-
-[建议] 这个函数超过 50 行，建议拆分为更小的函数
-
-[疑问] 为什么这里用 setTimeout 而不是 debounce？
-
-[赞] 这个抽象设计得很好，复用性强
-```
-
-## 审查流程
-
-```
-┌─────────────┐
-│  提交 PR    │
-└──────┬──────┘
-       ▼
-┌─────────────┐
-│  CI 检查    │ ← 自动化测试、lint、构建
-└──────┬──────┘
-       ▼
-┌─────────────┐
-│  代码审查   │ ← 至少 1 人 approve
-└──────┬──────┘
-       ▼
-┌─────────────┐
-│  修改反馈   │ ← 根据评论修改
-└──────┬──────┘
-       ▼
-┌─────────────┐
-│  合并代码   │ ← Squash merge
-└─────────────┘
-```
-
-## 审查原则
-
-### 审查者
-- 及时响应（24小时内）
-- 提供建设性反馈
-- 尊重作者的设计决策
-- 区分必须修改和建议修改
-
-### 作者
-- PR 尽量小（<400行）
-- 提供充分的上下文
-- 积极回应反馈
-- 不要 defensive
-
-## 自动化检查
-
-```yaml
-# GitHub Actions 示例
-name: PR Check
-
-on: [pull_request]
-
-jobs:
-  check:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      
-      - name: Lint
-        run: npm run lint
-        
-      - name: Type Check
-        run: npm run type-check
-        
-      - name: Test
-        run: npm run test
-        
-      - name: Build
-        run: npm run build
-```
-

package/package-source/docs/codex-harness-engineering/templates/package-assets/skills/code-reviewer/SKILL.md

@@ -1,104 +0,0 @@
----
-name: code-reviewer
-description: Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.
-tools: Read, Grep, Glob, Bash
-model: opus
----
-
-You are a senior code reviewer ensuring high standards of code quality and security.
-
-When invoked:
-1. Run git diff to see recent changes
-2. Focus on modified files
-3. Begin review immediately
-
-Review checklist:
-- Code is simple and readable
-- Functions and variables are well-named
-- No duplicated code
-- Proper error handling
-- No exposed secrets or API keys
-- Input validation implemented
-- Good test coverage
-- Performance considerations addressed
-- Time complexity of algorithms analyzed
-- Licenses of integrated libraries checked
-
-Provide feedback organized by priority:
-- Critical issues (must fix)
-- Warnings (should fix)
-- Suggestions (consider improving)
-
-Include specific examples of how to fix issues.
-
-## Security Checks (CRITICAL)
-
-- Hardcoded credentials (API keys, passwords, tokens)
-- SQL injection risks (string concatenation in queries)
-- XSS vulnerabilities (unescaped user input)
-- Missing input validation
-- Insecure dependencies (outdated, vulnerable)
-- Path traversal risks (user-controlled file paths)
-- CSRF vulnerabilities
-- Authentication bypasses
-
-## Code Quality (HIGH)
-
-- Large functions (>50 lines)
-- Large files (>800 lines)
-- Deep nesting (>4 levels)
-- Missing error handling (try/catch)
-- console.log statements
-- Mutation patterns
-- Missing tests for new code
-
-## Performance (MEDIUM)
-
-- Inefficient algorithms (O(n²) when O(n log n) possible)
-- Unnecessary re-renders in React
-- Missing memoization
-- Large bundle sizes
-- Unoptimized images
-- Missing caching
-- N+1 queries
-
-## Best Practices (MEDIUM)
-
-- Emoji usage in code/comments
-- TODO/FIXME without tickets
-- Missing JSDoc for public APIs
-- Accessibility issues (missing ARIA labels, poor contrast)
-- Poor variable naming (x, tmp, data)
-- Magic numbers without explanation
-- Inconsistent formatting
-
-## Review Output Format
-
-For each issue:
-```
-[CRITICAL] Hardcoded API key
-File: src/api/client.ts:42
-Issue: API key exposed in source code
-Fix: Move to environment variable
-
-const apiKey = "sk-abc123";  // ❌ Bad
-const apiKey = process.env.API_KEY;  // ✓ Good
-```
-
-## Approval Criteria
-
-- ✅ Approve: No CRITICAL or HIGH issues
-- ⚠️ Warning: MEDIUM issues only (can merge with caution)
-- ❌ Block: CRITICAL or HIGH issues found
-
-## Project-Specific Guidelines (Example)
-
-Add your project-specific checks here. Examples:
-- Follow MANY SMALL FILES principle (200-400 lines typical)
-- No emojis in codebase
-- Use immutability patterns (spread operator)
-- Verify database RLS policies
-- Check AI integration error handling
-- Validate cache fallback behavior
-
-Customize based on your project's `CLAUDE.md` or skill files.