Epistemic logic for multi-agent perceptual systems — Kripke models, vision sets, public announcement as coordination primitive, and satisfiability-as-reconfiguration applied to…
Charterparty: Reeder; Time Charterer; Voyage Charterer; Bareboat Charterer scopet Kaufvertrag für Gechartertes Seeschiff unter Charterparty: Gewaehrleistung; Lastenfreistellung;…
Use when the user wants to CREATE, AUTHOR, or PUBLISH a new Cinatra agent — OAS Flow 26.1.0 scaffold → validate → compile → publish, the orchestrator/subflow pattern,…
Implement AI chatbot analytics and conversation monitoring. Use when adding conversation metrics, tracking AI usage, measuring user engagement with chat, or building conv — from…
Run the full repository compatibility pass: scanner score, startup path, validation loop, and docs reliability.
Compare complete MCP 2025-11-25 tools/list snapshots before accepting a server upgrade or changed tool catalog.
Run long or failure-prone Claude Code tasks as bounded, resumable loops with a durable state machine, attempt budget, and verification evidence checkpoint.
6 unique agent skills cherry-picked from Addy Osmani's agent-skills — interview extraction, idea refinement, adversarial review, source-driven development, context engineering,…
Comprehensive interface for the Grandmaster AI chess platform. Play games, submit moves, and monitor matches. — from satoshistackalotto/skills
Route Hermes Agent work to the correct operator, extension-development, messaging-gateway, Nous services, or Socket compatibility workflow.
Wählt vor komplexer Multi-Agent-Arbeit gemeinsam mit dem Nutzer eine passende, begrenzte Orchestrierung und erzeugt einen kompakten Session-Vertrag.
Use when coordinating multiple AI agents with Agent Relay's workflow engine and need to pick the right orchestration pattern - covers the 10 core patterns (fan-out, pipeline,…
Use when coordinating multiple AI agents and need to pick the right orchestration pattern - covers 10 patterns (fan-out, pipeline, hub-spoke, consensus, mesh, handoff, cascade,…
Archived. Use ft-build-christian-ai-guardrails, ft-evaluate-christian-ai-apps, or ft-find-bible-developer-resources instead.
An official MCP server for the Chroma open-source embedding database. Enables AI agents to create collections, add documents, perform vector search, full-text search, and metadata…
Run and manage a single-instance Chrome DevTools MCP server on this machine, including start/stop/status/dedupe workflows and safe cleanup to prevent multiple chrome-devtools-mcp…
Chrome MCP Server uses a Chrome extension and local bridge to expose your everyday browser to MCP-compatible agents.
Diagnose and fix Claude in Chrome MCP extension connectivity issues. Use when mcp__claude-in-chrome__* tools fail, return "Browser extension is not connected", or behave — from…
Unified operational manual for AI agents driving the Chrono AI service stack — NyxID (identity, services, orgs, OAuth clients, proxy) AND Ornn (skill lifecycle — search, pull,…
[BETA STUB — not yet implemented] Chutes.ai agent-native onboarding. Use when an autonomous agent needs to self-register on Chutes without human signup, bootstrap its own account,…
Audit Chinese, Japanese, or Korean text layout in frontend pages, web apps, rendered webpages, EPUB/ebook content, PDFs, screenshots, or source files against W3C JLReq, CLReq, and…
Patterns for using clarc MCP server in multi-agent workflows, CI pipelines, and external tools
Intensive requirement clarification using structured AskUserQuestion workflow. Gathers MUST_HAVE (blocking) and NICE_TO_HAVE (optional) information before implementation.
AKTIVIERT SICH AUTOMATISCH bei vagen Auftraegen. LIEBER EINMAL ZU OFT NACHFRAGEN als falsch implementieren. — from majiayu000/claude-skill-registry
AKTIVIERT SICH AUTOMATISCH bei vagen Auftraegen. LIEBER EINMAL ZU OFT NACHFRAGEN als falsch implementieren. — from general/ai-tooling
AKTIVIERT SICH AUTOMATISCH bei vagen Auftraegen. LIEBER EINMAL ZU OFT NACHFRAGEN als falsch implementieren. — from majiayu000/claude-skill-registry
AKTIVIERT SICH AUTOMATISCH bei vagen Auftraegen. LIEBER EINMAL ZU OFT NACHFRAGEN als falsch implementieren. — from majiayu000/claude-skill-registry-data
AKTIVIERT SICH AUTOMATISCH bei vagen Auftraegen. LIEBER EINMAL ZU OFT NACHFRAGEN als falsch implementieren. — from majiayu000/claude-skill-registry-data
Use when the user wants to work with the Clarity MCP Server MCP Registry server or inspect its connection/capabilities.
Run one drift round on a clash Workflow item — compare `plan.md` against the change that was actually built from it, inventory every divergence, and grade each one INTENDED /…
Classifies legal domain, proceeding type, doc_type, court_type, draft_goal, language and style from MASTER_FACTS.json.
Audits your codebase for Claude Agent SDK usage affected by Anthropic's June 15 2026 billing split. Scans for claude -p invocations, GitHub Actions steps, and SDK imports;…
Convert Claude Code subagents (.claude/agents/*.md) to standard Agent Skills (skills/*/SKILL.md). Use when migrating subagents to portable skill format, extracting reusable…
Spin up a Claude agent team for implementation tasks. Use when user says "team go", "agent team go", "agent team", "/claude-agent-team", or wants a coordinated multi-agent…
Use when coordinating Claude Code background agents, `claude agents --json`, dispatched-session defaults, git worktrees, tmux/iTerm panes, resume/continue/from-pr/fork-session,…
USE THIS for Claude models. Access Claude 4.5 Opus, Claude 4.5 Sonnet, Claude 4 Sonnet, Claude 3.7 Sonnet, Claude 3.5 Haiku. No Anthropic account needed. OpenAI-compatible API.
Generate a paste-into-DevTools snippet that probes a Claude.ai internal API endpoint and downloads the response as JSON.
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, slash commands, plugins, MCP servers).
Create and maintain Claude Code agents/subagents (.claude/agents/*.md) with YAML frontmatter (name/description/tools/model/permissionMode/skills/hooks), least-privilege tool…
Create and configure Claude Code agents with YAML frontmatter, tool selection, model specification, and naming conventions.
Аудит кода, написанного Claude Code, через «второе мнение» другой LLM (DeepSeek/GLM/Kimi): вызывает CLI Hermes (`hermes -z`) — свежий взгляд не-Claude модели: галлюцинации API,…
Run Claude Code programmatically in headless mode or via bidirectional stream-json protocol. Use when building agents, automating Claude, running headless Claude, implementing…
Bridges OpenClaw (QQ, Telegram, WeChat, and other messaging channels) to a persistent Claude Code CLI session running in a background tmux process.
Push Claude Code activity to the user's device (e.g. a lamp) over the LAN. The plugin POSTs semantic events to a companion daemon on the device (HTTP, port 5002); the device turns…
Use when the user asks to build, deploy, create a dashboard, create a deck, push to GitHub, ship a page/tool, or deploy to Vercel.
Comprehensive guide to Claude Code's extensibility features including subagents, skills, plugins, commands, hooks, MCP servers, permissions, and automation.
Set up Claude Code messaging channels for Telegram and Discord — bot creation, plugin installation, token configuration, access control (pairing, allowlists, guild channels), and…
Diagnose slow Claude Code startup and guide cleanup. Use /bluera-base:claude-code-clean to run.
Executes tasks using the Claude Code CLI (`claude`). Automatically determines the safest permission mode (plan, acceptEdits, or bypassPermissions) based on the task type.
Use claude_code MCP as a third-party co-agent to gather alternative opinions, unblock stalemates, or delegate scoped tasks (reviews, ideas, draft edits) while you remain the…
Create slash commands for Claude Code with $ARGUMENTS handling, agent invocation patterns, and template best practices. Reference for building user-triggered workflow shortcuts.
Use Claude Code to run computer-use style UI automation loops with screenshot → decide → act cycles, safety guardrails, and step-bounded execution.
Troubleshoot Claude Code extensions and behavior. Triggers on: debug, troubleshoot, not working, skill not loading, hook not running, agent not found.
把编程任务委托给ai-assistant Code CLI执行。触发关键词: programming, tasks, code, ai-assistant, delegate。轻量级设计,低资源占用,适配云端与本地部署。轻量级设计,低资源占用,适配云端与本地部署。
Claude Code Plugin 开发专家。当用户要创建 Plugin、Skill、Subagent、Slash command、Hook 时触发。也用于解答 Claude Code 开发相关问题。触发词：创建 plugin、写 skill、写 agent、创建 hook、写 command、插件开发。
Search local Claude Code documentation to answer implementation questions. Use when asked about Claude Code features, subagents, workflows, skills, hooks, MCP servers, plugins,…
Audits Claude Code project setup and provides score with recommendations. Use when user asks about Claude Code setup, configuration quality, or wants to improve their Claude Code…
Especialista profundo em Claude Code - CLI da Anthropic. Maximiza produtividade com atalhos, hooks, MCPs, configuracoes avancadas, workflows, CLAUDE.md, memoria, sub-agen — from…
Construction d'extensions et skills pour Claude Code — slash commands, hooks, intégration MCP et commandes personnalisées.
Load before changing Claude Code config — agents, skills, hooks, settings, MCP, plugins; stack conventions.