Facilita desarrollo estructurado con sub-agentes para features, refactors grandes y cambios multi-archivo siguiendo diseño aprobado y TDD.
Instrument Python LLM apps, build golden datasets, write eval-based tests, run them, and root-cause failures — covering the full eval-driven development cycl...
Guide OpenClaw agents to execute Ralph Wiggum loops using exec and process tools. Agent orchestrates coding agents (Codex, Claude Code, OpenCode, Goose) with proper TTY support via pty:true. Plans/bui
Route mid-session work to the right spawned model without changing the fixed main session. Use for coding, architecture, math, algorithms, web development, b...
Systematic task implementation using TDD, phase checkpoints, and structured commits. Ensures quality through red-green-refactor cycles, 80% coverage gates, and verification protocols before proceeding
Use GitHub Spec Kit for Spec-Driven Development. Initialize projects, create specifications, and build software using the /speckit.* slash commands. Supports...
Create detailed implementation plans for software projects — break down features into steps, files, tasks, and executable code.
The complete operating system for building software with AI. From first prompt to production deployment — prompting frameworks, architecture patterns, testin...
--- name: large-codebase-workflow description: Best practices for using Claude Code with large, multi-part codebases --- # Large Codebase Workflow Guide ## Core Principle **Context is your scarcest
Error: --action required. Use when you need stripe manager capabilities. Triggers on: stripe manager, key, customer-id, amount, currency, desc.
Scaffold and configure a production-ready SvelteKit PWA with opinionated defaults. Use when: creating a new web application, setting up a SvelteKit project,...
--- name: antigravity-global-rules description: # ANTIGRAVITY GLOBAL RULES --- # ANTIGRAVITY GLOBAL RULES Role: Principal Architect, QA & Security Expert. Strictly adhere to: ## 0. PREREQUISITES H
Runs autonomous iterative AI loops for requirements, planning, or building phases using structured prompts and fresh context per iteration.
禅道-ZenTao 项目管理 API 集成技能。支持查询产品、项目、执行、需求、任务、缺陷等。触发词：禅道、zentao、禅道查询、禅道项目
Use when planning product experiments, writing testable hypotheses, estimating sample size, prioritizing tests, or interpreting A/B outcomes with practical s...
Ads Execution Hub control skill for ad campaign management and optimization across Meta (Facebook/Instagram), Google Ads, TikTok Ads, YouTube Ads, Amazon Ads...
Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when aske...
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks,...
--- name: evolve description: Local DevOps/autonomy skill for OpenClaw (safe evolution loop with guardrails). metadata: { "openclaw": { "emoji": "🧬" } } --- # evolve Local DevOps/autonomy skill f
Professional investment advisory skill. Use when user asks about investing, wealth management, asset allocation, fund/etf selection, retirement planning, or...
Add AI voice assistants to your website. Engage visitors with natural voice conversations, capture leads, automate support, and boost conversions.
Meta-skill that orchestrates comprehensive testing across a project by coordinating testing-patterns, e2e-testing, and testing agents. Use when setting up testing for a new project, improving coverage
Provides a comprehensive methodology to optimize productivity and tool use across multiple AI coding assistants through assessment, selection, context engine...
Security expert for OpenClaw deployments. Audits local configuration files for vulnerabilities in network settings, channel policies, and tool permissions. P...