Designs multi-step agent workflows with tool usage, retry logic, state management, and budget controls.
Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated…
Expert agent organizer specializing in multi-agent orchestration, team assembly, and workflow optimization.
Expert in designing, orchestrating, and managing multi-agent systems (MAS). Specializes in agent collaboration patterns, hierarchical structures, and swarm intelligence — from…
Expert in designing, orchestrating, and managing multi-agent systems (MAS). Specializes in agent collaboration patterns, hierarchical structures, and swarm intelligence — from…
Emit OpenTelemetry trajectory spans (tool-call, latency, token usage) as an agent works — vendor-neutral, via otel-cli wrapping shell tool-calls, exported to any OTLP backend.
Convert the canonical markdown+JSON deliverable of any SfSkills runtime agent into Excel, PDF, CSV, Notion card, ServiceNow ticket, or similar downstream format WITHOUT polluting…
Use when multiple agents have completed a round and the user asks to reconcile outputs, compare Codex and Gemini, synthesize run results, identify conflicts, or decide what should…
Use when validating, importing, repairing, or rolling back GapForge agent or campaign output patches.
Design, generate, audit, or revise minimal validation-driven AI agent packs for Codex, Claude Code, and Claude skills from project descriptions, README files, specs, existing…
Use when a Paperclip adapter bootstraps an agent with heartbeat instructions. This agent is lifecycle-managed by Paperclip: it wakes on heartbeat, checks its inbox, does assigned…
End-to-end resume parsing (detect format → extract fields). Uses a combination of format detection, text extraction, and LLM parsing to normalize resume data.
View this agent's digital passport (identity + trust + allowed/forbidden actions) and verify a peer's passport against a proposed action (EXO 3.0).
AI Agent 架构模式目录。提供 ReAct、Multi-Agent Conversation、Multi-Agent Workflow、 RAG Agent、Tool-Use Agent、Autonomous Agent 六种核心模式的参考架构、组件拓扑、 数据流、设计决策和框架无关的最佳实践。供 agent-dev-workshop Phase 2…
Expert payment integration specialist mastering payment gateway integration, PCI compliance, and financial transaction processing.
中文优先：用于智能体支付x402相关任务，帮助识别、设计、实现或验证对应工作流。English keywords: Add x402 payment execution to AI agents — per-task budgets, spending controls, and non-custodial wallets via MCP tools.
Support the recurring people function with agents that maintain onboarding paths, keep policy documents current, prepare review inputs, and flag gaps, while every human decision…
Track and report agent invocation metrics including usage counts, success/failure rates, and completion times.
Agent skill for performance-benchmarker - invoke with $agent-performance-benchmarker
Expert performance monitor specializing in system-wide metrics collection, analysis, and optimization.
Agent skill for performance-optimizer - invoke with $agent-performance-optimizer
Produces an aggregated markdown performance report from stored trace data — tool call metrics, token usage, cost, bottlenecks, and numbered recommendations.
Track and report agent invocation metrics including usage counts, success/failure rates, and completion times.
Enable and explain the reusable human-in-the-loop gates used by persistent agent loops for destructive actions, false-positive overrides, and recovery escalation.
Automated Issue-to-PR-to-Merge pipeline using GitHub Actions and AI agents with review loops
Composition de pipelines de sous-agents où la sortie d'un agent alimente l'entrée du suivant. Se déclenche avec "pipeline agent", "chaîne d'agents", "agent chain", "agent — from…
Agente de planejamento — lê, pesquisa e constrói planos detalhados antes de qualquer implementação. Opera em modo somente leitura: não edita código, apenas produz planos em…
Use when a task needs single-agent self-correction across multiple iterations — write plan, execute, critique own output, revise plan, re-execute, until convergence or budget…
Separate planning from execution and replan when reality diverges, so a long task does not follow a plan that stopped being true.
Have an agent produce a plan before implementing, and review it as the cheapest intervention point in the work. Use before any non-trivial agent task.
Design or audit the planning and control mechanism of an autonomous agent or multi-step agent workflow, producing an Agent Planning and Control Contract.
Workspace bootstrap for the agent-plus plugin collection. Creates `.agent-plus/` (one shared dir with skill-feedback), reports which sibling-plugin env vars are set (names only),…
The meta plugin for the agent-plus framework. Workspace bootstrap, env-var readiness, identity cache, marketplace lifecycle, extensions.
Gestion de pools de sous-agents pré-instanciés pour performance et réutilisation. Se déclenche avec "pool agent", "agent pool", "pool de sous-agents", "pre-allocated agen — from…
Guides agents through creating, retrieving, and trading on behalf of eToro agent-portfolios. Covers the full lifecycle — creating an agent-portfolio, obtaining its user token,…
Evaluates PRs containing agent changes using specialized agents to analyze quality, compliance, and improvement value.
Convene agents to model pricing options, argue them from customer, competitor, and margin angles, and hand a human a decision pack.
Give agents context in stages, escalating to more capable models or fuller context only when the cheap path proves insufficient.
Use this agent when a project needs an immediate project-local front desk for owner questions, short status answers, request capture, communications relay, and work-order creation…
Use this agent when a project needs a durable advisor/operator to capture raw thinking, consolidate monologues, turn ideas into work orders, map dependencies, preserve…
Write effective system prompts for TD AI agents. Covers role definition, constraint specification, output formatting, tool usage instructions, and prompt structure patterns.
Load when writing prompts for sub-agents, generation CLIs (jules, agy, claude-code, opencode, codex), or any model emitting structured artifacts (SVG, JSON specs/ops, code files).
Battle-tested prompt patterns for production AI agents. Covers consumer-first design, deletion test, cascading validation, advisory mode tiers, proof-of-work enforcement,…
Optimisation systématique des prompts d'agents pour améliorer performance et fiabilité. Se déclenche avec "optimiser prompt agent", "agent prompt", "améliorer mon agent" — from…
Inter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, and response formats.
Use quando um usuário ADMIN descreve, num grupo, um papel restrito para a Otto e diz que ela "não pode fazer nada além disso".
Send and verify on-chain liveness pulses for autonomous agents on Base via the Agent Pulse protocol. Use when you need to: (1) prove an agent is alive by sending a pulse, (2)…
Competitive puzzle arena for AI agents with timed solving, per-model leaderboards, and 5 categories (reverse captcha, geolocation, logic, science, code).
PyTorch runtime, CUDA, and training error resolution specialist. Fixes tensor shape mismatches, device errors, gradient issues, DataLoader problems, and mixed precision f — from…
Create, edit, validate, and run Agent QA tests, suites, and hooks through MCP or CLI while preserving canonical IDs and schema contracts.
Place a QA agent as the last blocking node before output ships, checking acceptance criteria against executed test evidence with the power to veto.
Triage failed Agent QA runs with MCP evidence, artifacts, logs, fixed failure categories, confidence, and actionable next steps.
Auditor de qualidade de código — revisa conformidade com as regras de arquitetura, estilo e segurança do AGENTS.md.
Hold a consistent standard across everything a company ships, with agents that review against written criteria and escalate disagreements rather than averaging them.
Train LLM-based agents with end-to-end RL by extending MDPs to handle tool invocation and environmental stochasticity—enable dense process rewards for intermediate steps and…
Use when multi-platform e-commerce and messaging channel extraction (Shopee, TikTok Shop, WeChat)
Use when writing technical documentation that needs to be readable by both humans and AI models, converting existing docs to HADS format, validating a HADS document, or o — from…
Use when making a repository easy for coding agents to work in, or keeping it that way, auditing a repo for agent ergonomics, bootstrapping or refreshing CLAUDE.md / AGENTS.md,…
Evaluate a codebase for agent-friendliness based on autonomous agent best practices. Use when asked to "evaluate for agents", "check agent readiness", "audit for autonomous…