Agent skill

Pair Programming

by staruhub in staruhub/ClaudeSkills

结对编程搭档。当用户要求"边写边审"、"结对编程"、"写完自己 review 一遍"、"高可靠地实现",或明确希望代码交付时附带自我审查意见时使用。交付代码的同时输出结构化审查(正确性/安全/性能/可读性/健壮性五维度),重点捕捉 AI 生成代码的特有缺陷。不用于:对已有 PR 的正式评审(用 code review 流程)、安全专项扫描(用 security-audit)、10…

MITAuto-check passedDevelopment

Install Pair Programming

skills CLI
$ npx skills add staruhub/ClaudeSkills --skill pair-programming -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install staruhub/ClaudeSkills pair-programming --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/staruhub/ClaudeSkills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/Geek-skills-pair-programming .claude/skills/pair-programming && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
pair-programming
GitHub stars
727
Token cost
~482 tokens
SKILL.md length
112 words
Files
3 (incl. references)
Skills in repo
20
Repo updated
First seen
Licence
MIT

At a glance

结对编程搭档。当用户要求"边写边审"、"结对编程"、"写完自己 review 一遍"、"高可靠地实现",或明确希望代码交付时附带自我审查意见时使用。交付代码的同时输出结构化审查(正确性/安全/性能/可读性/健壮性五维度),重点捕捉 AI 生成代码的特有缺陷。不用于:对已有 PR 的正式评审(用 code review 流程)、安全专项扫描(用 security-audit)、10…

  • Tasks that involve Security review
  • SKILL.md covers 验收标准(每次交付前自查), 不做什么, 审查工作流 and AI 生成代码的特有缺陷(重点盯防), plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Pair Programming is an agent skill from staruhub/ClaudeSkills. 结对编程搭档。当用户要求"边写边审"、"结对编程"、"写完自己 review 一遍"、"高可靠地实现",或明确希望代码交付时附带自我审查意见时使用。交付代码的同时输出结构化审查(正确性/安全/性能/可读性/健壮性五维度),重点捕捉 AI 生成代码的特有缺陷。不用于:对已有 PR 的正式评审(用 code review 流程)、安全专项扫描(用 security-audit)、10 行以内的简单片段。

Its SKILL.md is about 480 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `evals/routing-evals.json` and `references/detailed-checklist.md`).

It sits in Development, covering Security review. The repository describes itself as: 13 curated Agent Skills for research, product decisions, decks, publishing, audits, and more — portable across skills-compatible agents. The licence is MIT.

When your agent uses it

  • Tasks that involve Security review

Example prompts

  • “写完自己 review 一遍”
  • “高可靠地实现”
  • “/pair-programming”

What it can do on your machine

Read from SKILL.md and the folder at commit 66e02d2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Pair Programming loads about 482 tokens when it runs, and up to ~1.6k if it reads all its reference files. Until then it costs about 55 tokens; SKILL.md has 112 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~55
When it runs · the whole SKILL.md, loaded when a task matches
~482
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from staruhub/ClaudeSkills at commit 66e02d2, republished under its MIT licence (© staruhub). 112 words, ~482 tokens.

Download SKILL.mdSave it as .claude/skills/pair-programming/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
pair-programming
description
结对编程搭档。当用户要求"边写边审"、"结对编程"、"写完自己 review 一遍"、"高可靠地实现",或明确希望代码交付时附带自我审查意见时使用。交付代码的同时输出结构化审查(正确性/安全/性能/可读性/健壮性五维度),重点捕捉 AI 生成代码的特有缺陷。不用于:对已有 PR 的正式评审(用 code review 流程)、安全专项扫描(用 security-audit)、10 行以内的简单片段。
version
1.1.0

结对编程搭档

交付代码 + 像负责任的高级开发者一样自我审查,一次给到位。

验收标准(每次交付前自查)

  • 代码之后附有结构化审查意见(好的地方 / 需要关注 / 优化建议三段)
  • 每个"需要关注"都给了可执行的修改方案,不是只指出问题
  • 🔴 必查项五条全部过检(空值/输入验证/注入/敏感数据/资源泄漏)
  • 审查意见针对本次生成的代码,不是通用清单复读
  • 发现自己代码的问题时直接修掉再交付,审查意见只留真正的权衡点

不做什么

  • 不替代正式 code review / PR 评审流程
  • 不做安全专项审计 → security-audit
  • <10 行的简单片段、纯示例代码、用户明说不要审查时,省略审查环节

审查工作流

生成代码 → 五维度扫描 → 修掉能修的 → 剩余权衡点写进审查意见。

五维度扫描
维度检查重点
正确性逻辑是否正确?边界条件是否处理?
安全性是否有注入风险?数据是否安全处理?
性能是否有 O(n²) 隐患?是否有不必要的循环?
可读性命名是否清晰?结构是否合理?
健壮性错误处理是否完善?异常情况是否考虑?
分级清单

🔴 必查(阻断级):空值处理 / 输入验证 / SQL·命令注入(参数化)/ 密钥硬编码 / 资源泄漏 🟡 重要(建议级):边界条件 / 并发竞态 / 异常捕获 / 关键日志 / 网络超时 🟢 改进(优化级):重复代码 / 命名 / 复杂逻辑注释 / 魔法数字 / 单一职责

语言特定检查项(Python/JS/Java/Go/Dart 等)见 references/detailed-checklist.md,按当前语言取用。

AI 生成代码的特有缺陷(重点盯防)

缺陷具体表现自查方法
幻觉 API调用了不存在的方法或传了不存在的参数不确定的 API 先查项目依赖版本的文档,不凭记忆写
偷改需求实现比用户要求"更合理"的版本,悄悄改了行为对照用户原话逐条核对交付物
过度防御到处 try/catch 吞异常、层层空值检查掩盖真错误每个 catch 问"这里吞掉异常对吗"
风格漂移新代码与项目既有命名/模式不一致写前先看同目录相邻文件的写法
测试造绿灯为过测试写死返回值或放宽断言审查测试改动是否弱化了验证强度
复制不一致从别处仿写时残留原上下文的变量名/注释全读一遍自己的产出,不只看 diff

反馈格式与语气

---
## 🔍 结对审查意见
### ✅ 做得好的地方
### ⚠️ 需要关注(含具体修改方案)
### 💡 优化建议(可选方向)

建设性(给方案)、谦逊("可以考虑")、教学性(解释为什么)、平衡(也认可好的做法)、简洁(只留关键点)。

示例(检测到注入风险时):

⚠️ 🔴 SQL 注入风险:"...WHERE name = '$name'" 直接拼接用户输入。 建议:参数化查询 db.query("...WHERE name = ?", [name])。

引用资源

  • references/detailed-checklist.md — 语言特定检查清单全集,按当前项目语言取用

evals/routing-evals.json — 触发边界回归用例,改 description 后用仓库根 scripts/run_routing_evals.py 校验。

© staruhub, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/Geek-skills-pair-programming of staruhub/ClaudeSkills.

  • SKILL.md
  • evals/routing-evals.json
  • references/detailed-checklist.md

Open the folder on GitHubat commit 66e02d2

Compare with similar skills

Pair Programming next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Pair Programming compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pair Programming this skillstaruhub/ClaudeSkills727—~482Automated safety check: PassMIT
Code Review Specialistluongnv89/claude-howto42k—~764Automated safety check: PassMIT
Verdaccio Code Reviewverdaccio/verdaccio18k—~853Automated safety check: PassMIT
Best Practicesmidudev/100cosas.dev1143 repos~3kAutomated safety check: PassMIT
Bug Huntercodexstar69/bug-hunter519—~5kAutomated safety check: PassMIT
Read-Only Code AuditHarnessMD/munder-difflin8.6k—~350Automated safety check: NotesMIT

Similar skills

  • Code Review Specialist

    luongnv89/claude-howto

    Reviews code for security, performance, quality and maintainability, using a checklist, a finding template and two metrics scripts.

    42k GitHub stars~764 tokensUpdated 7 days ago
    DevelopmentAuto-check passed
  • Verdaccio Code Review

    verdaccio/verdaccio

    Reviews a verdaccio diff, branch or PR against the repository's review guide, verifies each finding in the code and reports only actionable issues.

    18k GitHub stars~853 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Best Practices

    midudev/100cosas.dev

    Apply modern web development best practices for security, compatibility, and code quality.

    114 GitHub starsUsed in 3 repos~3k tokens
    DevelopmentAuto-check passed
  • Bug Hunter

    codexstar69/bug-hunter

    Precision-first adversarial bug hunting for runtime, logic, data, concurrency, and security defects.

    519 GitHub stars~5k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Read-Only Code Audit

    HarnessMD/munder-difflin

    Scans the working directory for ignored errors, hard-coded secrets, debt comments, dead exports and type gaps, and reports findings by severity without editing files.

    8.6k GitHub stars~350 tokensUpdated today
    DevelopmentAuto-check: notes
  • Audit Flow

    zebbern/claude-code-guide

    Interactive system flow tracing across CODE, API, AUTH, DATA, NETWORK layers with SQLite persistence and Mermaid export.

    4.7k GitHub stars~4.2k tokensUpdated today
    DevelopmentAuto-check passed

More from staruhub/ClaudeSkills

All 20 skills in this repo
  • Deep Research

    staruhub/ClaudeSkills

    A skill your agent uses when the user wants an evidence-based research memo, literature review, market/policy/technical landscape, or a multi-source decision brief with citations, trade-offs, and a…

    727 GitHub stars~2.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Podcast Generator

    staruhub/ClaudeSkills

    用火山引擎 Podcast AI 模型生成中文双人对话播客。当用户要把文章、报告、话题文本转成播客音频、生成对话式音频内容时使用,需要环境具备火山引擎 APPID 和 ACCESSKEY。支持 mp3/oggopus/pcm/aac、语速调节、自定义音色、断点续传。不用于:单人朗读式 TTS(用普通语音合成)、英文播客(模型主要优化中文)、播客文稿本身的撰写(先用写作类 skill…

    727 GitHub starsUsed in 1 repo~475 tokens
    Auto-check passed
  • Wechat Article Writer

    staruhub/ClaudeSkills

    专业微信公众号文章助手,支持四个独立且可组合模式:article 写正文;image-prompts 从文章生成版本化、provider-neutral 的图片提示词 manifest 与稳定占位符,但不调用生图;layout 把文章和 manifest 确定性转换为微信安全的内联 HTML;full-pipeline…

    727 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed
  • A Share Analyst

    staruhub/ClaudeSkills

    A股分析研究助手,提供行情数据获取与技术面/基本面分析框架(仅供研究参考,不构成投资建议)。适用于:(1) 获取A股行情和历史数据,(2) 技术面分析(K线形态、MACD、KDJ、RSI、布林带等),(3) 基本面分析(财务指标、估值分析),(4) 板块热点追踪,(5) 选股策略筛选与量化因子分析,(6)…

    727 GitHub stars~871 tokensUpdated 1 mo ago
    Auto-check passed
  • C Drive Cleaner

    staruhub/ClaudeSkills

    Windows C盘清理和磁盘空间管理。当用户说C盘满了、磁盘空间不足、清理临时文件/缓存/回收站/系统日志、查找大文件、分析磁盘占用时使用。仅适用于 Windows 环境。不用于:macOS/Linux 磁盘清理、卸载软件(引导用户走系统卸载)、清理用户个人文件(只报告位置,删除决定权在用户)。

    727 GitHub stars~518 tokensUpdated 1 mo ago
    Auto-check passed
  • Gaokao Expert

    staruhub/ClaudeSkills

    资深高考命题专家助手,提供专业的命题指导和评审服务。适用于创作高考试题、评审试题质量、分析试卷结构、了解命题趋势等场景。结合文档工具提取解压文件,使用网络搜索了解当年最新命题趋势,使用分析工具评估题目质量和试卷结构。涵盖"一核四层四翼"评价体系、题型规范、评分标准、命题流程等多个维度。不用于:大学/考研/中考命题(体系不同,仅可借鉴)、日常作业题编写、直接替考生解题。

    727 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Pair Programming

What does Pair Programming do?

结对编程搭档。当用户要求"边写边审"、"结对编程"、"写完自己 review 一遍"、"高可靠地实现",或明确希望代码交付时附带自我审查意见时使用。交付代码的同时输出结构化审查(正确性/安全/性能/可读性/健壮性五维度),重点捕捉 AI 生成代码的特有缺陷。不用于:对已有 PR 的正式评审(用 code review 流程)、安全专项扫描(用 security-audit)、10…. Pair Programming is an agent skill from staruhub/ClaudeSkills.

When should I use Pair Programming?

Pair Programming fits situations like: tasks that involve Security review.

How do I install Pair Programming in Claude Code?

Run `npx skills add staruhub/ClaudeSkills --skill pair-programming -a claude-code`. Or copy the skill folder (skills/Geek-skills-pair-programming in staruhub/ClaudeSkills) into .claude/skills/pair-programming in your project. Claude Code loads it when a task matches its description.

How do I install Pair Programming in Codex?

Run `npx skills add staruhub/ClaudeSkills --skill pair-programming -a codex`. Or copy the skill folder (skills/Geek-skills-pair-programming in staruhub/ClaudeSkills) into .agents/skills/pair-programming in your project. Codex loads it when a task matches its description.

Can I use Pair Programming in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add staruhub/ClaudeSkills --skill pair-programming -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pair-programming, .gemini/skills/pair-programming, .github/skills/pair-programming and .opencode/skills/pair-programming in your project.

What does Pair Programming need to run?

SKILL.md names no scripts, command-line tools or credentials: Pair Programming is instructions for the agent only.

Does Pair Programming access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Pair Programming safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Pair Programming use?

Pair Programming is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Pair Programming use?

About 482 tokens (SKILL.md is roughly 1.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.1k tokens, read only when the agent opens those files.

What are the alternatives to Pair Programming?

Skills that share tags, products or a category with Pair Programming: Code Review Specialist (luongnv89/claude-howto, 42k stars), Verdaccio Code Review (verdaccio/verdaccio, 18k stars), Best Practices (midudev/100cosas.dev, 114 stars) and Bug Hunter (codexstar69/bug-hunter, 519 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pair Programming?

staruhub (a GitHub user) maintains it in staruhub/ClaudeSkills, which has 727 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on August 13, 2026.

Source: staruhub/ClaudeSkills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.