Agents
AI agents and automation
cui-marketplace-architecture
by cuioss
Architecture rules and validation patterns for Claude Code marketplace components ensuring self-contained skills, proper skill usage, and clean reference patterns
evm-balance
by melonask
Comprehensive guide for the EVM Balance project, including CLI usage, SDK integration, and development workflow. Use when working with EVM balance fetching, configuring the CLI, or integrating the SDK.
claude-agent-ruby
by ya-luotao
Implement or modify Ruby code that uses the claude-agent-sdk gem, including query() one-shot calls, Client-based interactive sessions, streaming input, option configuration, tools/permissions, hooks, SDK MCP servers, structured output, budgets, sandboxing, session resumption, Rails integration, and error handling.
forge-stories
by fwehrling
FORGE SM Agent — Decomposes requirements into stories with test specs. Usage: /forge-stories
interactive-intro-writer
by dw-dengwei
"Interactive deep learning paper Introduction writing assistant. Helps users discover scientific narrative, innovation points, and contributions through multi-turn dialogue. Supports writing from scratch or polishing existing LaTeX files. Follows standard Introduction structure: Background → Problem → Existing Work → Limitations → Overall Approach → Method Overview → Three Contributions."
agent-browser
by dereknex
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.
adr-index
by studiojin-dev
Generate and validate the ADR index for this repo (docs/adr/*.md -> docs/adr/index.json). Use when updating ADRs, checking ADR metadata format, or keeping agent context small; enforce header/metadata rules and never append done-logs to AGENTS.md.
ledger-agent-intents
by brackets-fistfulayen
"Explore Agent Payments with Ledger — the secure agent payment system where agents propose, humans sign, and Ledger hardware enforces. Test the live demo, review the architecture, and share your assessment."
proxy-pay-mcp
by proxyhq
Proxy MCP server integration for agent payments. Use MCP tools to create intents, issue cards within policy, and track transactions. Supports agent tokens for autonomous runs and OAuth for interactive clients.
handlebar-setup
by gethandlebar
Connect an AI agent to Handlebar governance platform
skill-authoring
by cachemoney
Use when authoring, creating, refining, or troubleshooting agent skills — covers SKILL.md structure, frontmatter syntax, description optimization, and activation testing. Also when building a new skill from scratch, when a skill won't trigger, loads incorrectly, or the agent ignores it entirely. Use when a skill misbehaved in the current session and needs adjustment based on learnings.
openclaw-dev
by frank8ai
Autonomous OpenClaw + Codex CLI development workflow that enforces spec-driven execution, minimal-token supervision, and test-gated acceptance. Use when you need to set up agent/ templates, run codex exec/resume loops, and manage STATUS/DECISIONS/RESULT files for autonomous project delivery.
spanora-setup
by spanora
Setup Spanora AI observability in any project (JavaScript/TypeScript or Python). Use when user asks to "add spanora", "setup spanora", "integrate spanora", "add AI observability", "monitor LLM calls with spanora", "track AI costs", or mentions spanora in the context of adding observability to their project. Detects the language and installed AI SDKs (Vercel AI, Anthropic, OpenAI, LangChain) and configures the optimal integration pattern.
mixseek-team-config
by drillan
MixSeekのチーム設定ファイル（team.toml）を生成します。「チームを作成」「エージェント設定を生成」「Web検索チームを作って」「分析チームを設定」といった依頼で使用してください。Leader AgentとMember Agentの構成を定義します。
nft-development
by pluginagentmarketplace
Master NFT development with token standards, metadata, marketplaces, and on-chain art
chat-profile-analysis
by duckytan
通过AI分析聊天历史生成个性化用户画像报告。支持多种AI编程工具的聊天记录分析，包括Claude Code、OpenCode等。本技能强调AI驱动的灵活分析，而非死板模板。
Tool Documentation Quick Reference
by cadrianmae
This skill should be used when the user asks for "quick reference", "show me examples for [tool]", "common commands for pandoc", "how do I use pandoc", "pandoc cheatsheet", "show pandoc examples", "tool-lookup", or needs fast offline access to command-line tool commands without detailed explanations. Load when user wants working examples at a glance, not troubleshooting or in-depth documentation.
rust-agent-handoff
by bug-ops
Handoff protocol for Rust multi-agent development system. Use when working as rust-architect, rust-developer, rust-testing-engineer, rust-performance-engineer, rust-security-maintenance, rust-code-reviewer, rust-cicd-devops, or rust-debugger. ALWAYS read on agent startup.
feature-workflow
by khw1031
기능 구현을 5단계(Requirements → Design → Task → Implementation → Review) 워크플로우로 체계적으로 진행합니다. Agent Team 기반 병렬 구현을 지원합니다. 워크플로우, 기능 구현, 기능 개발, 작업 재개, TASK-ID 패턴, .ai/tasks 요청 시 활성화.
openspec-to-beads
by cachemoney
PROACTIVELY convert approved OpenSpec specs into Beads issues when user applies a change or explicitly approves implementation. Creates trackable work with dependencies, discovers gaps, and maintains audit trail between planning and execution.
forge-analyze
by fwehrling
FORGE Analyst Agent — Domain research and requirements elicitation. Upstream of /forge-plan. Usage: /forge-analyze
Clawderous
by tawkiebot
Discord: discord.gg/DbbHB7g3
agent-browser
by xdrshjr
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.
clear-mind
by webray1983
"Memory file maintenance and optimization system. Use when factual information (portfolio, projects, technical details) accumulates in MEMORY.md, or when periodic memory cleanup is needed. Migrates factual content to separate files, keeps only core rules and indexes in MEMORY.md, maintains Quick Index table for navigation. Size/line count is NOT a trigger — only factual bloat matters."