智能体
Agent 规划、多步流程与编排
agent-interop
docxology
Apply the repository's portable Codex, Claude Code, and Hermes interoperability workflow.
Recursive Agentic Task Orchestration (Fractals)
docxology
A powerful orchestration skill for breaking down high-level objectives into hierarchical task graphs and resolving them through isolated multi-agent execution in dedicated worktrees.
systems-thinking
docxology
Analyze a change as part of a wider system by mapping boundaries, dependencies, feedback loops, delays, incentives, and leverage points.
desloppify
docxology
Improves codebase quality via the desloppify CLI — install, exclude noise, scan, and drive the next/resolve execution loop to raise strict score. Use when the user invokes /desloppify, asks for tech-debt cleanup, desloppify, strict score, or codebase health scanning.
red-team
docxology
Apply the repository's portable red-team review workflow within authorized scope.
first-principles
docxology
Apply the repository's portable first-principles reasoning workflow.
systems-thinking
docxology
Apply the repository's portable systems-thinking workflow to changes and decisions.
mcp-tool-use
docxology
Apply the repository's portable least-privilege MCP and tool-use workflow.
writing-skills
ZhanlinCui
Use when creating new skills, editing existing skills, or verifying skills work before deployment
agent-ready-codebase
Casper-Studios
This skill should be used when auditing a codebase for AI agent readiness, or when guiding improvements to make a codebase work well with agentic coding tools. It applies when users ask to evaluate test coverage, file structure, type system usage, dev environment speed, or automated enforcement -- the five pillars that determine how effectively coding agents can operate in a project. Triggers on "audit my codebase", "make this agent-ready", "improve for AI agents", "agent-friendly", or questions about why agents struggle with a codebase.
voice-agents
Casper-Studios
ElevenLabs voice agent creation for client discovery and feedback calls. Use this skill when creating AI voice agents, setting up discovery call agents, or configuring automated phone conversations. Triggers on voice agent creation, ElevenLabs agent setup, or automated call agent requests.
agent-browser
Casper-Studios
Browser automation and testing using Vercel's agent-browser CLI with ref-based element targeting
agent-creator
mhylle
Create composable AI agent systems in NestJS projects following the "tools all the way down" architecture. Use this skill when users want to: (1) Create new AI agents with orchestrator/planner/executor/evaluator components, (2) Build agentic systems that can call other agents as tools, (3) Implement DAG-based planning with parallel execution, (4) Add database-backed state persistence for agent runs, (5) Create custom evaluators for quality assurance. Triggers on "create agent", "build agent", "agent system", "agentic", "orchestrator", "planner/executor pattern", or NestJS AI agent requests.
chat-compactor
ZhanlinCui
Generate structured session summaries optimized for future AI agent consumption. Use when (1) ending a coding/debugging session, (2) user says "compact", "summarize session", "save context", or "wrap up", (3) context window is getting long and continuity matters, (4) before switching tasks or taking a break. Produces machine-readable handoff documents that let the next session start fluently without re-explaining.
agent-browser
grota
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.
agent-tail
gillkyle
Capture browser console logs and dev server output to files with agent-tail. Use when debugging runtime errors, checking console output, tailing or diagnosing logs, or setting up Vite/Next.js log capture.
kkclaw
kk43994
给你的 AI Agent 一个桌面身体 — Setup Wizard、14情绪球体、语音克隆、歌词窗、Doctor 自检、跨平台支持（Windows + macOS）
swift-async-algorithms
nonameplum
Algorithms for working with AsyncSequence: combining, throttling, debouncing, chunking, and more
ai-debate-dominator
sandraschi
Master AI debate techniques with comprehensive counter-arguments against slop criticism, safety concerns, philosophical objections, and political rhetoric
setting-detector
wordflowlab
"Automatically detects story settings (genres, time periods, themes) based on keywords and activates corresponding knowledge bases - works silently in the background to provide relevant writing guidance without user intervention"
getting-started-guide
wordflowlab
"Activates when users start a new novel project - guides them through the seven-step methodology (constitution → specify → clarify → plan → tasks → write → analyze) with gentle prompts and explanations"
moai-foundation-claude
Ven0m0
Core Claude Code extension-authoring playbook for skills, agents, commands, plugins, hooks, and settings. Use when creating or reviewing Claude Code extensions and automation workflows.
brainstorming-pm
dangeles
Use when orchestrating multi-perspective brainstorming sessions requiring parallel agent execution, confidence-weighted synthesis, and optional workflow handoff. Coordinates 5 parallel perspective agents through a 4-stage pipeline (framing, diverging, converging, output).
archive-workflow
dangeles
Use when organizing projects - detecting clutter, enforcing naming conventions, structuring directories, managing gitignore, or assessing project expandability. Triggers on project organization requests, file naming audits, or gitignore maintenance needs.