coding-agent
关于
The coding-agent skill delegates complex coding tasks to external agents like Claude Code via shell commands. It's designed for multi-step development work including feature building, PR reviews, and large-scale refactoring in separate projects. Use it for iterative coding requiring file exploration, but avoid for simple edits or reading existing code.
快速安装
Claude Code
推荐npx skills add swarmclawai/swarmclaw -a claude-code/plugin add https://github.com/swarmclawai/swarmclawgit clone https://github.com/swarmclawai/swarmclaw.git ~/.claude/skills/coding-agent在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
Coding Agent
Delegate coding tasks to external coding agents via shell tools.
Agent Execution Modes
Claude Code (recommended)
Use --print --permission-mode bypassPermissions for non-interactive execution:
cd /path/to/project && claude --permission-mode bypassPermissions --print 'Your task here'
For background execution, use the shell tool's background mode.
Do NOT use PTY mode with Claude Code — --print mode keeps full tool access and avoids interactive confirmation dialogs.
Codex
Codex requires a git repository and PTY mode:
# Quick one-shot (auto-approves changes)
cd /path/to/project && codex exec --full-auto 'Build a dark mode toggle'
# Codex refuses to run outside a git directory. For scratch work:
SCRATCH=$(mktemp -d) && cd $SCRATCH && git init && codex exec "Your prompt"
Pi Coding Agent
# Install: npm install -g @mariozechner/pi-coding-agent
cd /path/to/project && pi 'Your task'
# Non-interactive mode
pi -p 'Summarize src/'
# Different provider/model
pi --provider openai --model gpt-4o-mini -p 'Your task'
OpenCode
cd /path/to/project && opencode run 'Your task'
PR Reviews
Clone to a temp folder or use git worktree — never review PRs in the SwarmClaw project directory:
# Clone to temp for safe review
REVIEW_DIR=$(mktemp -d)
git clone https://github.com/user/repo.git $REVIEW_DIR
cd $REVIEW_DIR && gh pr checkout 130
codex review --base origin/main
# Or use git worktree
git worktree add /tmp/pr-130-review pr-130-branch
cd /tmp/pr-130-review && codex review --base main
Parallel Issue Fixing
Use git worktrees to fix multiple issues in parallel:
# Create worktrees
git worktree add -b fix/issue-78 /tmp/issue-78 main
git worktree add -b fix/issue-99 /tmp/issue-99 main
# Launch agents (use background shell execution)
cd /tmp/issue-78 && codex --yolo 'Fix issue #78: <description>. Commit when done.'
cd /tmp/issue-99 && codex --yolo 'Fix issue #99: <description>. Commit when done.'
# Create PRs after
cd /tmp/issue-78 && git push -u origin fix/issue-78
gh pr create --repo user/repo --head fix/issue-78 --title "fix: ..." --body "..."
# Cleanup
git worktree remove /tmp/issue-78
git worktree remove /tmp/issue-99
Rules
- Use the right execution mode per agent: Claude Code uses
--print(no PTY); Codex/Pi/OpenCode may need interactive terminal. - Respect tool choice — if the user asks for Codex, use Codex. Don't silently switch agents.
- Be patient — don't kill sessions because they seem slow.
- Monitor progress — check output periodically without interfering.
- Never run coding agents inside the SwarmClaw project directory — use a separate project directory or temp folder.
Progress Updates
When spawning coding agents in the background:
- Send a short message when you start (what's running, where).
- Update only when something changes (milestone, error, completion).
- If you kill a session, say so immediately and explain why.
GitHub 仓库
相关推荐技能
content-collections
元Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。
polymarket
元这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。
creating-opencode-plugins
元该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。
sglang
元SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。
