Loading...
Loading...
Found 7,248 Skills
Claude CLI sub-agent system for persona-based analysis. Use when piping large contexts to Anthropic models for security audits, architecture reviews, QA analysis, or any specialized analysis requiring a fresh model context.
Bridge plugin capabilities (commands, skills, agents, hooks, MCP) to specific agent environments (Claude Code, GitHub Copilot, Gemini, Antigravity). Use this skill when converting or installing a plugin to a target runtime.
Better proposals, faster closes. Use when creating AI agent pricing, automation proposals, ROI calculations, or sales materials. Generates professional pricing pages, case studies, and closing scripts for AI automation services.
Configure and orchestrate Claude Code agent teams (TeamCreate, SendMessage, TaskUpdate workflow). Use when you need multiple agents working in parallel on a complex task, want to coordinate background agents with messaging, or are setting up a lead/teammate architecture with a shared task list. Teams are experimental — enable with --enable-teams flag.
Autonomous agent commerce via Bitrefill CLI. Buy gift cards, mobile top-ups, and eSIMs from 1,500+ brands in 180+ countries — pay with crypto, x402, or account balance.
Enforces a 'Document-then-Execute' workflow. Use when an agent needs to run shell commands, execute tests, build projects, or perform any task that should favor established task runners (Makefile, npm run) and be logged to .cmds-by-agents/ for auditability.
Scaffolds new projects with README.md, AGENTS.md, and CI/CD (GitLab CI, GitHub Actions). Handles project type (generic / Flask backend / React frontend / Taro miniapp), tech stack, coding standards, quality level, and SDD (OpenSpec, SpecKit, GSD). All init flows (Flask, React, Taro) and conventions (backend-python-cicd, frontend-codegen, flask-backend-codegen, QA/testing, agent-roles/subagents) are built-in; no separate skills. Docs default to Chinese. Use when creating a project, initializing a repo, or setting up CI/CD/SDD.
Autonomous SDLC router. Takes a job, classifies complexity, executes the appropriate lev-* workflow (from trivial fix to full epic), and returns "done" with runnable instructions. One shot to full auto: spec/bd/poc/impl. Subagent returns completion artifact. Triggers: "sidequest", "side quest", "just do it", "autonomous", "one shot"
Autonomous crypto business development patterns — multi-chain token discovery, 100-point scoring with wallet forensics, x402 micropayments, ERC-8004 on-chain identity, LLM cascade routing, and pipeline automation for CEX/DEX listing acquisition. Use when building AI agents for crypto BD, token evaluation, exchange listing outreach, or autonomous commerce with payment protocols.
Manage AI agent memory files (AGENTS.md/CLAUDE.md). Supports update and restructure modes. Use this when users need to sync, update, or restructure agent memory files. Triggered by keywords such as "记忆文件", "memory file", "AGENTS.md", "更新记忆", "重构记忆", "memory sync", "memory restructure".
Expert guidance for building production-grade AI agents and workflows using Pydantic AI (the `pydantic_ai` Python library). Use this skill whenever the user is: writing, debugging, or reviewing any Pydantic AI code; asking how to build AI agents in Python with Pydantic; asking about Agent, RunContext, tools, dependencies, structured outputs, streaming, multi-agent patterns, MCP integration, or testing with Pydantic AI; or migrating from LangChain/LlamaIndex to Pydantic AI. Trigger even for vague requests like "help me build an AI agent in Python" or "how do I add tools to my LLM app" — Pydantic AI is very likely what they need.
Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.