Create, refresh, audit, or migrate repository agent guidance files such as AGENTS.md, AGENTS.override.md, CLAUDE.md, .claude/rules, and Cursor rules.
Agent-facing guide for mmx CLI — agent flags, piping patterns, tool schema export, async video workflow, streaming, and CI/CD examples.
Generate comprehensive handoff documentation optimized for AI agent takeover by analyzing project structure, design docs, and codebase
Design de handoffs fluides entre agents — transfert de contexte, d'état et de responsabilité. Se déclenche avec "handoff", "transfert agent", "agent handoff", "passer la — from…
Design and implement agent-to-agent handoff protocols for multi-agent systems. Covers context passing, escalation patterns, handshake mechanisms, conversation continuity, and…
HarmonyOS application development expert specializing in ArkTS and ArkUI. Reviews code for V2 state management compliance, Navigation routing patterns, API usage, and performance…
Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
Design agent tool sets with stable names, narrow schemas, deterministic output shapes, and explicit error paths. No catch-all tools unless unavoidable.
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
Agent harness optimization patterns for token efficiency, memory persistence, session management, and cross-harness parity.
Field reference for Claude Code and GitHub Copilot CLI hook contracts. Covers hook locations, events, matchers, payloads, decisions, exit codes, timeouts, plugin roots, and cloud…
Agent harness router consolidating TrueFoundry TrueForge (harness as control point, $10/mo budget enforcement), Martech (scattered AI discovery capture), GLM-5.3 (private…
Full-stack health monitoring for AI agent infrastructure. Monitors API keys, wallet balances, daemon processes, cron jobs, disk space, and service endpoints.
Monitor AI agent health, detect anomalies, set up alerting, and maintain observability dashboards for production multi-agent systems.
Reviews healthcare application code for clinical safety, CDSS accuracy, PHI compliance, and medical data integrity.
Agent skill for hierarchical-coordinator - invoke with $agent-hierarchical-coordinator
Design de hiérarchies d'agents multi-niveaux (orchestrateur → managers → workers → sous-agents spécialisés).
Generate visual hierarchy diagrams of agent system showing levels and delegation. Use for documentation or onboarding. — from majiayu000/claude-skill-registry
Generate visual hierarchy diagrams of agent system showing levels and delegation. Use for documentation or onboarding. — from majiayu000/claude-skill-registry
Generate visual hierarchy diagrams of agent system showing levels and delegation. Use for documentation or onboarding. — from majiayu000/claude-skill-registry
Simulate an interview panel as agents that design questions, score independently on anchored rubrics, and reconcile in a debrief.
<תיאור קצר של הסוכן — מה הוא עושה ומתי ה-Agent Router מנתב אליו, ושהוא מחזיר {reply} ל-orchestrator. It is a map, not a manual: it routes you to the live workflow via the n8n-live…
Agent 动作生命周期钩子注册表。定义 PreAction/PostAction 钩子规则，当 Agent 执行特定操作（文件修改、代码生成、切片路由）前后自动触发检查。借鉴 OpenHarness PreToolUse/PostToolUse 机制，在 Prompt 层实现声明式守卫。
Scaffold the agent-hub project profile (.claude/agent-hub/profile.yml + CLAUDE.md) for the current project so the super-team can specialize to it.
Place human approval at the points where being wrong is expensive or irreversible, with enough context to decide quickly. Use when agents perform work that has real consequences.
Design de systèmes human-in-the-loop pour agents IA avec approbation, correction et escalade. Se déclenche avec "human in the loop", "HITL", "approbation humaine", "valid — from…
Invisible privacy guardian for agent workspaces. Automatically intercepts outbound actions (git push, skill publish, file sharing) and checks for sensitive data leaks.
Explicit-only audit of local coding-agent setup, installed skills, MCP servers, plugins, and recent usage signals. Use only when the user explicitly invokes $agent-hygiene.
Give your agent a persistent cross-platform identity. Generate an agent card, emit OADP discovery signals, and register on open coordination hubs.
Agent real-world identity — email, phone, payment, and personal info for autonomous service registration.
Implements a single, well-scoped GitHub issue in an isolated worktree, validates it, logs it for human review, and has a Haiku agent review the diff.
Implementation guidance for creating individual agents in the Arcanea system with proper structure, capabilities, and integration.
Agent skill for implementer-sparc-coder - invoke with $agent-implementer-sparc-coder — from John-Wang-0809/claw-research-skills
Agent skill for implementer-sparc-coder - invoke with $agent-implementer-sparc-coder — from majiayu000/claude-skill-registry
Self-improvement loop for multi-agent workflows. Diagnose failures, improve tool descriptions, and learn from success/failure patterns.
Check and process messages from autonomous AILANG agents. Use when starting a session, after agent handoffs, or when checking for completion notifications.
Check and process messages from autonomous AILANG agents. Use when starting a session, after agent handoffs, or when checking for completion notifications.
Run a blameless postmortem for an incident caused by an AI agent or LLM feature — hallucinated facts shipped to users, runaway tool use, prompt injection, cost blowouts, or wrong…
Use the InfiniSynapse CLI (`agent_infini`) for multi-turn AI data-analysis tasks, database/RAG context, and task workspace files.
Initialize or improve AGENTS.md files that define how coding agents operate in a repo. Use when asked to set up or replace an agent init command (Codex, Claude), standardize…
Use this agent when brainstorming creative solutions, generating novel concepts, or facilitating ideation sessions.
Write the repository instruction file that coding agents read, so they follow project conventions without being told each session.
Load when the user asks for private agent interaction audits from local Codex/Claude Code traces, task profiles, tool-call decisions, collaboration bottlenecks, prompt/rule or…
Design tools, scripts, and CLIs that an agent will call, so the interface teaches its own use instead of a wall of prose and examples.
Creates PhD-grade expert agents when no suitable agent exists. Produces highly specialized agents with deep domain expertise.
Quick reference for invoking CasareRPA agents via Task tool. AUTO-CHAIN ENABLED by default. Use when: invoking agents, running agent chains, task routing, choosing the right…
Output envelope contract for subagent runs. Load in the orchestrator session before delegating to worker, planner, or oracle so the contract reaches the subagent through inherited…
Improve output through repeated critique and revision against a fixed standard, stopping when the standard is met or gains stop.
Control local Codex and Claude Code through shared tmux or Herdr terminals with Agent Knock Knock.
Expert knowledge synthesizer specializing in extracting insights from multi-agent interactions, identifying patterns, and building collective intelligence.
Conception de graphes d'agents avec LangGraph pour workflows complexes et stateful. Gestion d'état partagé, edges conditionnels, persistance et human-in-the-loop.
Launches specialized Claude agents for targeted tasks. Analyzes requirements, selects appropriate agent, and executes with optimized configuration.
Team Lead / PM for sprint planning, epic ownership, and delivery coordination. Default persona name is Lead — configurable via persona_name_team_lead in config.yml.
Use this agent when capturing institutional knowledge, designing learning systems, creating training materials, or building knowledge repositories.
Expert legal advisor specializing in technology law, compliance, and risk mitigation. Masters contract drafting, intellectual property, data privacy, and regulatory compliance…
Use agents to triage contracts and policies, extract obligations, flag unusual terms, and prepare a lawyer's review rather than replace it.
Manage agent fleet through CRUD operations and lifecycle patterns. Use when creating, commanding, monitoring, or deleting agents in multi-agent systems, or implementing proper…
Train and optimize AI agents using Microsoft's Agent Lightning framework with reinforcement learning.
Train RL on diverse agent frameworks (LangChain, AutoGen, custom) via unified data interface and transition-based RL decomposition.
Специализированный скилл для диагностики и исправления зависаний, деградации контекста и нестабильности LLM в агентском режиме (dialogue_node.py + MCP tools).