coding-lead
Coding execution skill for any implementation-focused agent. Current production path is claude-only with simple tasks direct, medium tasks preferring ACP run or direct acpx, and complex tasks handled via existing agent continuity plus context files instead of ACP session persistence. Integrates with qmd and smart-agent-memory when available.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/beyound87/coding-leadWhat This Skill Does
The coding-lead skill acts as the primary execution engine for OpenClaw agents, standardizing how fullstack development tasks are handled. It provides a robust framework for classifying coding tasks based on complexity—Simple, Medium, or Complex—and routing them to the most efficient execution path. Instead of relying on rigid, persistent IM-based sessions, it promotes a hybrid approach utilizing Claude ACP (Agent Coding Protocol) for one-shot execution, direct local file manipulation (read/write/edit/exec), and serial context management via on-disk files. The skill is designed for resilience: it auto-detects optional tools like qmd and smart-agent-memory, falling back to standard system utilities when advanced tools are unavailable. It prioritizes session continuity, ensuring that complex multi-module architecture tasks remain coherent even without persistent ACP sessions.
Installation
To integrate coding-lead into your environment, use the OpenClaw hub CLI tool:
clawhub install openclaw/skills/skills/beyound87/coding-lead
Ensure your local environment has the necessary permissions to read and write project files and access your preferred runtime environments (PHP/Python/Node). The skill automatically performs a single detection pass upon session initialization to identify available accelerators.
Use Cases
- Rapid Prototyping: Quickly generate single-file components or scripts without the overhead of session management.
- Fullstack Feature Implementation: Developing multi-file features across PHP/Laravel backends and Vue.js frontends.
- Refactoring & Maintenance: Managing complex codebase architectural shifts that require consistent context over several iterative steps.
- Environment-Agnostic Coding: When moving between environments where specific tools like ACP or memory-cli might not be installed, the skill gracefully degrades to standard CLI operations to maintain workflow productivity.
Example Prompts
- "Create a simple Vue component for a user login form that includes basic validation logic and Tailwind styling."
- "Refactor the user authentication module in the existing Laravel project to support external OAuth providers; keep track of dependencies in our context file."
- "Analyze the current system performance logs using qmd, then suggest a database optimization strategy for our MySQL tables."
Tips & Limitations
- Complexity Matters: When in doubt, default to the next level of complexity to ensure your agent provides more thorough documentation and session management.
- ACP is an Accelerator: The skill is designed to function even without ACP. If your environment lacks ACP, the skill will automatically fall back to direct file execution, ensuring your workflow is never blocked.
- Architecture Confirmation: For new projects, always confirm the stack with the agent before implementation, as the skill follows specific preferred paths like Laravel for backends and Vue.js for frontends.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-beyound87-coding-lead": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, code-execution
Related Skills
myopenclaw-backup-restore
Cross-platform backup and restore for OpenClaw. Works on Windows, macOS, and Linux — backups created on any OS can be restored on any other OS. Use when user wants to create a snapshot, restore from backup, migrate to a new machine, or protect against data loss. Supports dry-run preview, automatic pre-restore snapshots, gateway token preservation, credential permission hardening, and a built-in HTTP server for browser-based management. Only requires Node.js (no bash/rsync/python needed).
smart-agent-memory
跨平台 Agent 长期记忆系统。分层上下文供给 + 温度模型 + Skill经验记忆 + 结构化存储 + 自动归档。三层存储:Markdown(人可读,QMD 可搜索)+ JSON(结构化)+ SQLite/FTS5(高性能全文搜索)。纯 Node.js 原生模块,零外部依赖。
token-pilot
Automatic token optimization during interaction. Behavioral rules + plugin synergy + workspace analyzer. Pure Node.js, cross-platform. Activate on session start (rules auto-apply) or when user asks about token usage/cost/audit.
security-hardening-safey
Agent 安全加固技能。用于:(1) 安装后经用户确认,将安全红线注入所有 Agent 的底层记忆(AGENTS.md),精简版注入~112行,不造成token膨胀;(2) 当用户问到安全规则、提示词注入防御、危险命令管控、外部代码审查、多模态注入等话题时加载此技能;(3) 进行安全审计或排查疑似注入事件时使用。触发词:安全加固、提示词注入、prompt injection、rm -rf、eval exec、外部内容攻击、Agent被黑、安全规则、安全红线、代码审查、脚本审查、skill vetter、安装技能、初始化。
team-builder
在 OpenClaw 上一键部署多 Agent SaaS 团队工作区。内置双开发轨(devops 交付 + fullstack-dev 实现)、实时 spawn 调度、cron 巡检、Deep Dive 产品知识目录、onboarding 引导。支持自定义角色、模型、时区,可选 Telegram 接入。