智能体
Agent 规划、多步流程与编排
breadth-reader
barkain
Forked skill for breadth tasks (explore, review, summarize)
pi-interactive-shell
Dwsy
Cheat sheet + workflow for launching interactive coding-agent CLIs (Claude Code, Gemini CLI, Codex CLI, Cursor CLI, and pi itself) via the interactive_shell overlay or headless dispatch. Use for TUI agents and long-running processes that need supervision, fire-and-forget delegation, or headless background execution. Regular bash commands should use the bash tool instead.
agent-browser
kevinslin
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
dev.new
kevinslin
Sync a repo to the latest master branch by checking out master and pulling from origin. Use when the user asks to refresh local state before new work.
dev.codex
kevinslin
“Codex runtime/config management (MCP servers, config.toml, session setup) plus session analysis/summaries. Use only for Codex self‑configuration. Do not use for creating or updating skills or SKILL.md content; use $sc for that.”
dev.research
kevinslin
Create structured research documentation for codebase exploration and feature investigation. Enables agents to produce docs that capture findings, methodologies, and recommendations. Covers architecture docs, research briefs, flow docs, state docs, service design docs, feature design docs, feature specs (execution plans), investigation specs, validation specs, recipes, vendor docs, frequently asked questions (FAQ), and FAQ specs that append Q&A to an existing research document.
architect-refine-critique
NTCoding
"Three-phase design review. Chain architect → refiner → critique subagents. Triggers on: 'design review', 'architecture review', '/arc', system design proposals, significant refactoring decisions, new service or module design."
MacPowerTools
openclaw
Trillion-Agent Forge + CoreML — Safe 24/7 self-learning toolkit + swarm orchestrator for OpenClaw agents on Apple Silicon Mac Mini. 1-trillion coherence simulation, native CoreML forecasting, real Moltbook fleet discovery & viral recruitment.
agent-analytics
openclaw
"Web analytics platform that AI agents can query via CLI. Track page views, custom events, run A/B experiments, analyze funnels, retention cohorts, and traffic heatmaps. Use when the user needs web analytics, visitor tracking, event tracking, conversion optimization, growth insights, A/B testing, or wants to add analytics to their website or app. Also available as an MCP server at mcp.agentanalytics.sh."
pentest-auth-bypass
openclaw
Test authentication and session management controls for bypass and account takeover scenarios.
nmap-pentest-scans
openclaw
Plan and orchestrate authorized Nmap host discovery, port and service enumeration, NSE profiling, and reporting artifacts for in-scope targets.
agentic-workflow-automation
openclaw
Generate reusable multi-step agent workflow blueprints. Use for trigger/action orchestration, deterministic workflow definitions, and automation handoff artifacts.
creating-an-agent
ed3dai
Use when creating specialized subagents for Claude Code plugins or the Task tool - covers description writing for auto-delegation, tool selection, prompt structure, and testing agents
verification-before-completion
ed3dai
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
testing-skills-with-subagents
ed3dai
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes
agent-browser
m1heng
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
using-generic-agents
ed3dai
Use to decide what kind of generic agent you should use
feishu-e2e-test
m1heng
Local E2E debug and test framework for clawd-feishu plugin development. Use when debugging message flow, testing bot responses, verifying Feishu web UI interactions, or performing end-to-end validation of the OpenClaw-Feishu integration during development.
langconfig-builder
LangConfig
"Complete guide for building agents and workflows in LangConfig. Use when users need help configuring nodes, connecting agents, setting up tools, or designing multi-agent systems within the LangConfig platform."
nav-onboard
alekspetrov
Interactive onboarding for Navigator - learn by doing. Auto-invoke when user says "onboard me", "teach me Navigator", "how do I use Navigator", "Navigator tutorial", "learn Navigator", "new to Navigator", or "what skills should I use".
nav-init
alekspetrov
Initialize Navigator documentation structure in a project. Auto-invokes when user says "Initialize Navigator", "Set up Navigator", "Create Navigator structure", or "Bootstrap Navigator".
tree-view
Dwsy
Display directory tree structure with customizable depth, using fd and Python3 for fast and beautiful tree visualization.
improve-skill
Dwsy
"Analyze coding agent session transcripts to improve existing skills or create new ones. Use when asked to improve a skill based on a session, or extract a new skill from session history."
tmux
Dwsy
"Remote control tmux sessions for interactive CLIs, background tasks, and services."