Microsoft Learn MCP Server gives agents and IDE assistants direct access to official Microsoft documentation and code samples through a hosted MCP endpoint.
用于排查 sit/uat/prod 环境下 `/rag-recall/api/search/keyword` 未召回目标 doc/faq 的问题。支持两种输入：1) 完整请求（headers+body；若 `headers.appId` 缺失但 `body.appId` 存在，可回填）；2) requestId+targetId。统一走“回放 -> ELK…
Analyze and optimize Midjourney prompts using parameter tuning for --ar, --stylize, --chaos, and --weird flags.
Bauleiter Wohnraum-Mietvertrag: Schoenheitsreparaturen, Kaution, Kuendigung, Mieterhoehung, Untervermietung. Pruefraster fuer Vermieter und Mieter.
Mietvertrag AGB-Klauseln: Fachmodul im Miet- und Wohnungseigentumsrecht: prüft typische Klauseln auf Transparenz, Überraschung und unangemessene Benachteiligung; mit Normprüfung,…
Mietvertrag Apothekenstandort Konkurrenzschutz: prüft die einschlägigen Voraussetzungen, Dokumente, Risiken und Ausnahmen.
Prüft Mietvertrag vor Gründung/Eintragung, Vor-GmbH-Haftung und Genehmigungen im Gesellschaftsgruender.
Mietvertrag § 535 BGB: Pflichten, Gebrauchsüberlassung, Kündigung, Kaution und Schönheitsreparaturen.
Spezialfall Asyl-Folge- und Zweitantrag: § 71 AsylG, neue Beweismittel, geaenderte Sachlage. Antragsbegruendung, Erfolgschancen, Eilantrag Aufschiebende Wirkung.
Re-anchor cooperative-communication discipline — Grice's conversational maxims plus the AI-augmented transparency maxim — then audit recent responses and agent-authored artifacts…
Mine recent Claude Code sessions for non-obvious, multi-file CLAUDE.md candidates, adversarially verify them, and propose paste-ready additions.
MiniMax MCP tools - Web search and image understanding via MiniMax Coding Plan. Use when user needs web search, current information, or image analysis.
Show or request Mission Control agent contracts. Use when the user wants to inspect a worker mission, allowed paths, forbidden paths, tools, validation obligations, stop…
Design graph-style agent workflows with nodes, edges, gates, retries, checkpoints, and human approvals through Mission Control.
Diagnose a stuck Mission Control agent. Use when an agent shows no output, repeats errors, times out, asks for the same approval repeatedly, or stops making progress events.
Design, build, or audit MCP servers and tool/resource/prompt contracts through Mission Control. Use for MCP schemas, stdio startup, auth boundaries, plugin packaging, and smoke…
Design retrieval, indexing, chunking, ranking, and RAG workflows through Mission Control. Use for docs search, code search, semantic recall, and context-pack construction.
Recommend or review Mission Control Codex subagent bursts for bounded read-heavy work. Use when the user wants parallel exploration, review, planning, handoff audit, or failure…
Parallel multi-agent mission loop using yamtam-rt — decompose task into subtasks with deps, dispatch waves, collect reports, apply changes.
Multi-agent orchestration plugin for OpenCode. Use when the user wants to install, configure, or operate oh-my-opencode — including agent delegation, ultrawork mode, Prom — from…
Use MMSkills for GUI, computer-use, visual-agent, OSWorld, Ubuntu desktop, macOS, Minecraft, or Mario tasks where reusable multimodal skill packages can guide planning, state…
AI-powered enterprise performance optimization orchestrator with Context7 integration, Scalene AI profiling, intelligent bottleneck detection, automated optimization strategies,…
Manages context window optimization, session state persistence, and token budget allocation for multi-agent workflows.
Enterprise code quality orchestrator with TRUST 5 validation, proactive analysis, and automated best practices enforcement
Design modal agents that cannot be exited until explicit completion choices are selected.
Use before routing a /meta-agent request to choose single-agent-creator, team-builder, or agentlas-packager from the user's wording and available files.
Automatically applies when choosing LLM models and providers. Ensures proper model comparison, provider selection, cost optimization, fallback patterns, and multi-model s — from…
Set and manage the preferred backbone LLM for compatible AI-agent workflows. Supports manual model selection, automatic best-model selection based on task type, and a…
Model-specific prompt engineering guidelines for major LLMs. 主要 LLM 之模型專屬提示工程指引。 Use when: targeting specific model family, avoiding model-specific anti-patterns, selecting…
Multi-Modell Orchestrierung und Model-Switching Strategie. Score-basierte Modellauswahl, Cross-Agent-Delegation (Gemini, Codex, Ollama), Advisor-Pairing, Eskalations-Trigger,…
Use when spawning agents (Agent tool, agent-team teammates, Workflow/ultracode agent() calls) and choosing the model parameter, when the tier-policy hook denies a workflow script,…
Compiles web documentation into agent-native memory context using the Moltext Compiler. — from general/ai-tooling
Earn USDC completing bounties, post jobs, join multi-agent raids, build reputation, rank up. AI agent freelance marketplace with x402 escrow on Solana. Free SOL airdrop on signup.
The launchpad for agent-built projects. Submit, hunt, upvote, and earn coins for every project.
Agent-to-agent task marketplace with USDC escrow payments. Pay with credits or blockchain.
Route model calls through Helicone, inspect costs, latency, traces, prompts, and evaluations, then review changes before they ship.
Use ccusage when an agent operator needs to turn local Claude Code or Codex usage logs into spend and usage reports instead of manually reading raw JSONL files.
Install Claude Code hooks that stream session, tool, subagent, and workflow events into a local dashboard for live observability and review.
Track token burn, spend, and model mix across multiple coding-agent tools from one local monitoring workflow.
Run a local read-only terminal dashboard for Claude Code, Codex CLI, and OpenCode sessions to watch tokens, context, rate limits, child processes, and orphan ports.
When the persona needs to watch a long-running local subprocess for completion or stream events from it without burning conversation turns on busy-waiting, reach for the Monitor…
Morning Star (启明星) harness 的**强制全局入口** —— 多角色 agent 交付的生命周期、状态机、Spec-Driven 双阶段门禁、Task category 路由、意图门禁、@explore 能力边界、长任务纪律、Git 功能分支与 worktree 隔离、QC/QA 检出上下文对齐、Context7…
Morning Star (启明星) harness 的计划目录约定 —— {HARNESS_DIR} 与 {PLAN_DIR} 的发现与初始化、status.json 的 SSOT 结构与状态权限、residual findings 登记/归档/生命周期、severity 枚举（SSOT，机器字段）、notes.json…
[Cursor maint] Morning Star 路由与 prompt 迭代评估 —— 维护/回归专用（非日常 PM 编排 runtime）。路径：本仓库 `.cursor/skills/mstar-routing-eval/`。(1) PM 路由回归：`assets/routing-evals.json`；(2) Prompt/规则迭代评估；(3)…
Orchestration de tâches complexes avec décomposition et coordination multi-agents
Use when designing specialized Dataverse AI agents for sales, operations, compliance, data stewardship, ALM, or other enterprise action domains.
Analyze coordination patterns, handoff mechanisms, and state sharing in multi-agent systems. Use when (1) understanding how agents transfer control, (2) evaluating shared vs…
Design and optimize production-grade multi-agent systems with LangGraph, LangChain, and DeepAgents for complex AI workflows.
Simulate a structured peer-review process using multiple specialized agents to validate designs, surface hidden assumptions, and identify failure modes before implementation.
Build multi-agent systems that discover causal rules from event sequences using specialized agents (causal discovery, contextual information, orchestrator).
Activate for ANY request involving specialist delegation — single or multi-step. Contains the complete orchestration SOP: plan-and-confirm format, sequential execution rules, how…
Activate when a multi-agent orchestration goes wrong. Contains: recovery from `ValueError: Tool '' not found`, the full forbidden-tool reference for each specialist, retry…
Uses Agent SDK to deploy 3 parallel agents for client onboarding -- workflow auditor, tech stack mapper, and strategy drafter.
Universal multi-agent collaboration methodology for Claude Code. Model-tiered cowork + document-driven sync + self-evolution.
Decision frameworks and patterns for choosing and composing Claude Code components — skills, sub-agents, hooks, MCP servers, and slash commands — into effective multi-component…
Use when multiple Starlight agents need to collaborate on a related task — handles agent selection, task decomposition, dependency management, and result aggregation across the…
An advanced orchestration specialist that manages complex coordination of 100+ agents across distributed systems with hierarchical control, dynamic scaling, and intelligent…
Design the agent topology for a multi-agent feature and produce agent_topology.md. Use when eval_criteria.yaml declares multi_agent:true or when invoking /multi-agent-design.
Plan and document handoffs between specialized AI agents (foreman, workers, reviewers). Use for multi-agent workflows, subagent delegation, baton passes, or guild-style agent…
Run recoverable multi-agent long-task scheduling after the required launch review and authorization.