智能体
Agent 规划、多步流程与编排
tmux
smallnest
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
coding-agent
smallnest
Run Codex CLI, Claude Code, Kiro CLI, OpenCode, or Pi Coding Agent via background process for programmatic control.
researching-web
alexei-led
Web research via Perplexity AI. Use for technical comparisons (X vs Y), best practices, industry standards, documentation. Triggers on "research", "compare", "vs", "best practice", "which is better", "pros and cons".
agent-ros-bridge
webthree549-bot
Universal ROS1/ROS2 bridge for AI agents to control robots and embodied intelligence systems.
audit-agent-consolidation
melodic-software
Analyze agents for consolidation opportunities. Groups agents by configuration, tracks references, and manages refactoring.
hook-management
melodic-software
Central authority for Claude Code hooks management in this repository. Automates enforcement of critical repository rules through hooks. Use when adding hooks, managing hooks, configuring hooks, troubleshooting hooks, or understanding hook behavior. Delegates to docs-management skill for official hooks documentation. Provides organization-specific patterns, configuration management, and workflow guidance.
daggr
gradio-app
Build DAG-based AI pipelines connecting Gradio Spaces, HuggingFace models, and Python functions into visual workflows. Use when asked to create a workflow, build a pipeline, connect AI models, chain Gradio Spaces, create a daggr app, build multi-step AI applications, or orchestrate ML models. Triggers on: "build a workflow", "create a pipeline", "connect models", "daggr", "chain Spaces", "AI pipeline".
agent-sdk-development
melodic-software
Central authority for Claude Agent SDK (TypeScript and Python SDKs). Covers SDK installation, authentication (Anthropic key, Bedrock, Vertex), sessions and resumption, forking sessions, streaming vs single mode, custom tools, permissions (allowedTools, disallowedTools, permissionMode), MCP integration, system prompts (CLAUDE.md, appendSystemPrompt, outputStyle), cost tracking, todo tracking, structured outputs, hosting patterns, plugins, and SDK branding guidelines. Assists with building custom agents, configuring SDK options, and troubleshooting SDK issues. Delegates 100% to docs-management skill for official documentation.
browser
saadshahd
Browser automation CLI for AI agents. Use when testing web UIs, filling forms, taking screenshots, visual verification, or extracting page data. Triggers on "open browser", "click button", "screenshot", "visual diff", "test the page", "scrape", "fill form".
forge
saadshahd
Create a persistent expert agent file. Use when "create an agent", "make an agent", "design an agent", "forge an agent", "agent for [task]", "I need a specialist", "build a [role] agent".
watch
saadshahd
Monitored development with dev3000 (d3k). Use when debugging web apps, needing full-stack visibility, reading error context, or capturing browser + server logs. Triggers on "watch", "d3k", "dev3000", "monitor app", "capture logs", "what went wrong", "error context".
create-handoff
Casper-Studios
Create handoff documentation for work-in-progress sessions. Use when handing off work to another agent to supplement history compaction and and progress summarization.
ask
doodledood
Single-model consultation using consultant agent. Defaults to gpt-5.2-pro.
investigate-bug
doodledood
Deep bug investigation using consultant agent. Identifies root causes and fix suggestions.
ask-council
doodledood
Multi-model ensemble consultation. Runs 3 models in parallel for diverse perspectives.
adk-skill
miticojo
"Build single-agent and multi-agent systems using Google's Agent Development Kit (ADK) in Python, Java, Go, or TypeScript. Use when user says 'build an agent with ADK', 'create a Gemini agent', 'multi-agent pipeline', 'agent orchestration with Google', or mentions ADK, google-adk, google agent development kit, sequential/parallel/loop agents, agent tools, callbacks, state management, agent testing, or agent deployment with Gemini. Do NOT use for LangChain, CrewAI, AutoGen, or non-ADK agent frameworks."
explore-codebase
doodledood
'Find all files relevant to a query with orthogonal exploration for comprehensive coverage. Returns topic-specific overview + file list with line ranges. Uses parallel agents for thorough+ levels to ensure nothing is missed.'
clean-slop
doodledood
Find and remove AI-generated slop (useless comments, verbose patterns, unnecessary abstractions).
review-prompt
doodledood
Review and analyze LLM prompts using the 10-Layer Architecture. Provides detailed assessment without modifying files.
define-design-guidelines
doodledood
'Create a DESIGN_GUIDELINES.md that defines how to design UI/UX for your customer. Requires CUSTOMER.md to exist first. Covers aesthetic direction, design tokens, typography, color, motion, components, and layout patterns. Bakes in frontend-design skill principles to avoid generic AI aesthetics.'
solo-setup
fortunto2
Auto-generate project workflow config (docs/workflow.md) from existing PRD and CLAUDE.md with zero questions. Use when user says "set up workflow", "configure TDD", "wire up dev workflow", or after running /scaffold before /plan. Do NOT use for founder setup (use /init) or project scaffolding (use /scaffold).
using-vit
solpbc
Helps coding agents use vit to discover, follow, skim, and ship software capabilities (caps) over ATProto. Activates when the user mentions vit, beacons, caps, shipping, skimming, following, vetting, or social coding.
ralph-wiggum
fstandhartinger
Autonomous AI coding with spec-driven development. Implements Geoffrey Huntley's iterative bash loop methodology where agents work through specs one at a time, outputting a completion signal only when acceptance criteria are 100% met.
prompt-engineering
liyecom
提示工程技术与 Agent 设计模式