Use Phoenix to trace LLM and agent calls, run evaluations, replay prompts, inspect datasets, and expose observability workflows through MCP.
Automatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversation turns, and tool calls as hierarchical traces.
Use OpenLIT to instrument coding agents and LLM applications with OpenTelemetry traces, metrics, costs, prompts, tool calls, and evaluation signals.
Run Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, and related coding agents through a local proxy so an operator can inspect prompts, tool calls, token usage, and…
Use Future AGI to instrument agent runs, run evals and simulations, apply guardrails, and turn production traces into release-quality feedback.
Add OpenTelemetry-based instrumentation to LLM and agent code so operators can inspect prompts, tool calls, latency, errors, and provider behavior in their existing observability…
Use trace-mcp apply_codemod for any bulk mechanical change instead of repeated Edit calls. Activate whenever the same edit pattern would be applied 2+ times, across one file or…
Understand how ideas evolved over time to find old solutions for new problems and avoid repeating past failures — from majiayu000/claude-skill-registry
Monitor quota, spend, resets, and alerts across multiple coding-agent providers from one local dashboard before a long run hits throttling or budget limits.
Aggregate local coding-agent usage logs into spend, token, and trend views before quotas or budgets surprise the team.
Create a local dashboard that joins coding-agent session logs, token estimates, recorded work steps, and verification checks into reviewable task evidence.
A股多智能体 AI 投研分析工具 — 15 名 AI 分析师协作完成技术分析、基本面分析、 市场情绪研判、资金流向追踪（北向资金/主力资金）、宏观经济分析及博弈论推演， 输出结构化买卖建议与风险评估。支持沪深 A 股股票代码和中文名称。 Multi-agent AI stock analysis for China A-shares.
Orchestrates TRAE IDE for automated software development with multi-agent collaboration. Invoke when user wants to develop software using TRAE or needs automated project…
Use rLLM to evaluate, trace, reward, and train LLM agents with reinforcement learning across common agent frameworks.
Drafts U.S. transfer agent agreements between issuers and SEC-registered transfer agents covering appointment, stock ledger, transfer processing, Rule 17Ad compliance, fees,…
Practical application guide for HUMMBL's 6 transformations (Perspective, Inversion, Composition, Decomposition, Recursion, Meta-Systems).
Informationsfreiheit und Presseauskunft: Transparenzgesetz: Antrag formulieren im Informationsfreiheit/Presseauskunft: prüft konkret die einschlägigen Tatbestandsmerkmale,…
Internationales Handelsrecht: Seetransportrecht — Haager-Visby-Regeln (HVR), Hamburger Regeln 1978 und Rotterdamer Regeln 2009. Haftungsregime des Reeders, Seefrachtbrief vs.
Internationales Handelsrecht: Strassengütertransportrecht nach CMR-Übereinkommen 1956. Haftung des Strassenfrachtführers (Art.
私人旅行管家 — 从出发地到目的地的完整行程规划+攻略导出。 输入出发地、目的地、天数、预算、风格偏好，自动输出闭环行程， 包含交通推荐、酒店推荐、美食路线、每日预算，并可选生成攻略。 当用户提到「做攻略」「旅行规划」「旅游计划」「行程安排」时使用。
Gesellschaftsrechtliche Treuepflicht: Treuepflicht Drag Tag Liquidation Preference; konkretisierter Spezialmodul mit Prüfachsen, Red Flags, Varianten, Quellenhygiene und…
Agent-actor triage loop. Batch-claims rows with agent='agent_unset' OR pool='pool_unset', assigns {tier, pool, agent} per payload + context, writes via bookie.
Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs. — from majiayu000/claude-skill-registry
Sum agent-trial spend ($) from TB3 PR comments and Modal compute spend. Reports totals by kind (/run vs /cheat) and provider (anthropic, openai, ...), top-spender PRs, per-task…
Troubleshoots Monte Carlo AI agent alerts and traces — eval score drops, latency/token spikes, trajectory and validation breaches.
Tunnel: Eilantrag skizzieren im Straßenrecht und Infrastruktur: prüft konkret die einschlägigen Tatbestandsmerkmale, Fristen, Belege und Rechtsprechung dieses Spezialthemas.
Use claude-smart to capture corrections and working patterns as preferences, project skills, and shared skills that Claude Code, Codex, and OpenCode reuse later.
Decompose goals into task DAGs, delegate work to agents and tools, and inspect execution traces.
Feed an agent your docs, links, code, or rough process notes and it generates, validates, installs, and optionally shares a reusable SKILL.md-based workflow across supported agent…
Управление локальным Tuvio/Tuya роботом-пылесосом через MCP-сервер и локальный хаб. Use when the user asks in Russian or English to check vacuum status, start/pause cleaning, send…
Integrate and operate 91APP in Taiwan e-commerce context via mcp-91app. Use when syncing orders/products/members on 91APP, running OMO (online-merge-offline) flows, integrating…
Integrate NewebPay (藍新金流) for Taiwan e-commerce via mcp-newebpay. Use when accepting credit card / ATM / CVS / LINE Pay / periodical payments on NewebPay, handling 3DS 2.0 flows,…
Use when building or integrating Twilio Agent Connect (TAC) to connect third-party LLM agent runtimes with Twilio Voice, Messaging, ConversationRelay, Conversation Memory,…
Generate a complete TypeSpec declarative agent with instructions, capabilities, and conversation starters for Microsoft 365 Copilot — from majiayu000/claude-skill-registry
Best practices for using the Council MCP server in Tzurot v3 development - When to consult external AI, how to structure prompts, model selection, and multi-turn conversations.
Discover MCP tools and generate a phased UAT plan with agent-executable test specifications
the UGC fix-loop toolkit — surgically re-render a bad window/beat of a single-take UGC master (stitch_replacement.py, pure FFmpeg) and GPT cross-model review a Seedance prompt…
Patterns for delegating UI work to specialized agents. Covers synthesis-master vs specialized agents, multi-agent UI generation workflows, and orchestration strategies for complex…
Captures screenshots of key UI flows after E2E tests pass, runs an agent-side first-pass diff (regressions, console errors, layout shifts), then surfaces a checklist for the…
Plan and execute a SAPUI5/OpenUI5 version upgrade. Use when the user is bumping the UI5 version in manifest.json, ui5.yaml, package.json, or an existing UI5 app and wants to…
Multi-agent workflow orchestration. Use when the user says "ultracode", "workflow", "parallel agents", "pipeline", or asks to orchestrate multiple agents for complex tasks.
When the user needs to plan a complex feature, system, or project that requires deep creative exploration before execution.
Use when after completing PCA and k-nearest neighbor graph construction on preprocessed, log-normalized, highly-variable-gene-filtered single-cell RNA-seq data (stored in an…
Informationsfreiheit und Presseauskunft: UIG Umweltinformation: Antrag formulieren im Informationsfreiheit/Presseauskunft: prüft konkret die einschlägigen Tatbestandsmerkmale,…
Anlagenbetreiber oder Nachbar: BImSchG-Genehmigung beantragen anfechten oder Nachbar-Drittschutz geltend machen. BImSchG §§ 4 6 10 16 17 4. BImSchV UVPG. Normen BImSchG § 5 Abs.
Internationales Handelsrecht: UNIDROIT Principles of International Commercial Contracts 2016. Anwendungsfälle nach der Präambel, Art. 1.1 Vertragsfreiheit, Art.
Use for AI-assisted Unity work that needs live repo discovery, project-derived routing, runtime-owner proof, runtime-visible output hard stops, runtime numeric proof for repeated…
Provides an initial setup for AI Skills, `unity-mcp-cli` command line tool installation and everything else that is helpful to set up at the start of the project.
Minimal governance constitution for any multi-agent or solo-agent workflow. Load when work touches shared state, requires review, or spans more than one step.
Synchronizacja KFG między urządzeniami (Windows/Android). Triggers: sync KFG, updatekfg, zaktualizuj — from general/ai-tooling
Enhanced docs unified with AI-powered features. Enhanced with Context7 MCP for up-to-date documentation.
Synchronizacja KFG między urządzeniami (Windows/Android). Triggers: sync KFG, updatekfg, zaktualizuj — from general/ai-tooling
Vectorized string manipulation using the char module and modern string alternatives, including cleaning and search operations.
Define and document performance budgets for a web service or application. Use when asked to set performance targets, define SLOs for latency or throughput, establish Core Web…
Build a customer health scorecard for a specific account. Use when asked to score account health, assess renewal risk, build a health dashboard, or evaluate an account's — from…
Best practices for handling data with Lindy AI. Use when managing sensitive data, implementing data privacy, or ensuring data compliance.
Compare AI agent-made UI variants locally in a real app, then keep one and clean up unused temporary code.
Audit an external or untrusted source before using it in code, skills, plugins, workflows, prompts, or operations.
Use this if the user wants to update the agent instructions for the Home Assistant website.
Use when commits have landed since the onboarding files were last synced (the drift-check hook nudges for this), or the user asks to refresh AGENTS.md.