Agents
AI agents and automation
code-documentation
by plaited
TSDoc standards for TypeScript/JavaScript code. Automatically invoked when writing, reviewing, or editing any TSDoc comments, code documentation, or API documentation. (project)
forge-ux
by fwehrling
FORGE UX Agent — Generates UX design, wireframes, design system, and accessibility guidelines. Usage: /forge-ux
agentscope-sdk
by CaiZongyuan
This skill should be used when users need to work with AgentScope, a multi-agent platform for building AI-powered applications. It provides comprehensive guidance on agents, tools, memory management, models, RAG, workflows, evaluation, and development operations.
agent-orchestrator
by aatmaan1
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
overview
by tracemem
Overview of TraceMem core features, rules, and best practices.
analyze-and-recommend-third-party-optimizations
by Nebutra
Scan a codebase to identify hand-rolled implementations that should be replaced by third-party libraries, identify missing capabilities, and detect code organization issues (directory structure, naming, circular deps, barrel bloat). Produce structured migration plans with Context7-verified recommendations. Use when analyzing technical debt, auditing dependency health, reviewing hand-rolled code, planning library migrations, assessing capability gaps, or auditing project structure and module organization.
plugin-architecture
by pluginagentmarketplace
Master plugin folder structure, manifest design, and architectural patterns. Learn to organize plugins for scalability and maintainability.
aegis-router
by disi3r
"AEGIS — Neural Routing Engine for OpenClaw Agent Swarms. Dynamically routes prompts to optimal model tiers using 15-dimensional analysis."
google-adk-python
by vysotin
Build production-ready AI agents in Python using Google Agent Development Kit (ADK). Use when creating agentic Python applications with LlmAgent, workflow agents (SequentialAgent, ParallelAgent, LoopAgent), multi-agent orchestration, tool development (function tools, MCP, OpenAPI), session and state management, callbacks and guardrails, testing and evaluation, Python backend integrations (FastAPI, Flask, Streamlit, Slack), streaming, A2A protocol, or deploying to Vertex AI, Cloud Run, or GKE. Triggers on "build an agent", "ADK", "ADK Python", "multi-agent system", "agentic application", "agent orchestration", "Gemini agent".
langsmith-code-eval
by langchain-ai
Creates code-based evaluators for LangSmith-traced agents. Use when building custom evaluation logic, testing tool usage patterns, or scoring agent outputs programmatically. Triggers on requests to evaluate agents, create evaluators, or run experiments against LangSmith datasets.
skill-manager
by L61
Analyze and clean up duplicate skills across vibe coding tools. Use when user asks to analyze skills, find duplicates, or clean up their skill collection.
trading-agents
by luohy15
Multi-agent stock analysis workflow
create-ai-tool
by khw1031
사용자 요구사항을 분석하여 Skill 또는 Agent 중 적절한 유형을 결정하고 생성을 위임합니다. 도구 만들기, 스킬 vs 에이전트, 어떤 걸 만들어야 할지, 도구 유형 선택 요청 시 활성화.
元编排 — 核心语法
by xy7365527-lang
ææ循ç¯çç»æ¢æ¯ç»ææ§çï¼èé©°+ååï¼ï¼ä¸æ¯è®¡æ°æ§çã3 ä¸æ¯éå¼ï¼æ¯ååçæå°æ°æ®éã
orchestrating-agents
by Git-Fg
"Implements Orchestrator, Swarm, and Hierarchical patterns for preventing context saturation. Use when designing multi-agent systems for context isolation and parallel execution."
project-health
by fefogarcia
AI-agent readiness auditing for project documentation and workflows. Evaluates whether future Claude Code sessions can understand docs, execute workflows literally, and resume work effectively. Use when onboarding AI agents to a project or ensuring context continuity. Includes three specialized agents: context-auditor (AI-readability), workflow-validator (process executability), handoff-checker (session continuity). Use PROACTIVELY before handing off projects to other AI sessions or team members.
decision-recording
by tracemem
Recording architecture and engineering decisions with one-shot decision recording and search.
conventional-commit-batcher
by cnkang
Auto-split mixed changes into logical commit batches with validated Conventional Commit messages. MUST BE USED for ANY git add, git commit, or git push operation.
four-causes-analysis
by sethmblack
Achieve complete understanding of anything by systematically examining its material, formal, efficient, and final causes.
cui-maven-rules
by cuioss
Complete Maven standards covering build processes, POM maintenance, dependency management, and Maven integration for CUI projects
multi-agent-locks
by wilbertliu
Lock coordination skill for concurrent agents. Mandatory on primary main checkout; optional on worktrees/non-main branches unless stricter repo policy applies.
agent-browser
by watzon
MUST USE for any browser automation tasks. Headless browser via agent-browser CLI - web interactions, scraping, testing, screenshots, login flows, and form submission. Uses ref-based element selection (@e1, @e2) from accessibility snapshots.
agent-md-refactor
by cachemoney
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
multi-agent-patterns
by fefogarcia
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.