Usar cuando un agente necesita conocer la arquitectura del proyecto sin leer ficheros completos.
Simplifies and refines code for clarity, consistency, and maintainability while preserving behavior. Focus on recently modified code unless instructed otherwise.
Pattern for spawning subagents that must get Codex approval before their work is accepted. Use when dispatching parallel agents that each need independent Codex review gates.
Construction d'agents de coding autonomes capables de lire, écrire et modifier du code. Se déclenche avec "coding agent", "agent de code", "agent développeur", "Devin", " — from…
A protocol and toolkit for multi-agent collaboration. Agents post turns to a shared board, get each other's messages, challenge each other's work, and record the outcome as a…
Structured multi-agent collaboration for backend + frontend builds. Use when an orchestrator needs to coordinate a backend engineer and frontend engineer on the same feature.
Agent skill for collective-intelligence-coordinator - invoke with $agent-collective-intelligence-coordinator — from ruvnet/ruflo
Agent skill for collective-intelligence-coordinator - invoke with $agent-collective-intelligence-coordinator — from majiayu000/claude-skill-registry
Analyze code comments for accuracy, completeness, maintainability, and comment rot risk.
A production-ready universal engine for Agentic Commerce. This tool enables autonomous agents to interact with any compatible headless e-commerce backend through a standa — from…
Enables AI agents to autonomously negotiate, sign, execute, and enforce legally binding commercia。Use when 需要AI模型调用、智能对话、Agent编排、LLM应用时使用。不适用于需要100%确定性的关键决策。
Analyze changes and create a meaningful commit with agent authorship. Internal skill for evolve_loop.
Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks — from i-am-bee/acp
Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks — from…
Compose specialist agent desks into one operating company with a shared ledger, a weekly cadence, and human approval gates on anything binding.
Keep repository-level Claude and Codex agent instructions compatible by creating safe symlinks between CLAUDE.md and AGENTS.md, and between .claude/skills/* and .agents/skills/*.
Run continuous compliance with agents that map controls to evidence, collect it on a schedule, and flag drift before an audit finds it.
Reads the current work context and plans the optimal agent dispatch. Clarifies direction with 1-2 questions when unclear; infers and proceeds immediately when execution path is…
Onboarding guidato per il sistema Job Hunter. Usa questa skill quando un nuovo utente vuole attivare il sistema di ricerca lavoro autonoma: ingerisce il CV, fa domande su…
Check agent config for things that break silently on someone else's machine. Use before publishing or committing a SKILL.md, AGENTS.md, CLAUDE.md or llms.txt, before publishing a…
Definitive cross-harness reference for configuring agents (rules/instructions, prompts, skills, agents/subagents, hooks, tools/MCP, plugins/extensions, secrets, sandbox,…
Synchronisiert MCP-Server UND Skills uebergreifend ueber ALLE bekannten Agent-Apps und CLIs (Claude Code, Claude Desktop, Codex CLI, Antigravity/Gemini, Kimi Code, Cursor, Cline,…
Especialista en configuración de agentes de IA: templates, tools, models, prompts y seed data. — from general/ai-tooling
Especialista en configuración de agentes de IA: templates, tools, models, prompts y seed data. — from general/ai-tooling
Decision framework for resolving conflicts between clarc agents — priority hierarchy, conflict classes, escalation protocol, and real-world examples
Résolution de conflits entre agents ou sous-agents quand les résultats sont contradictoires. Se déclenche avec "conflit agent", "agent conflict", "résultats contradictoires",…
Two audiences. (A) MCP DEVELOPER — write an MCP server, lifecycle hooks (12 normalized events + a native-event passthrough), slash commands, Agent Skills, subagents, or standing…
Mécanismes de consensus et de vote entre agents pour prendre des décisions collectives fiables. Se déclenche avec "consensus agent", "vote agents", "décision collective" — from…
Agent skill for consensus-coordinator - invoke with $agent-consensus-coordinator — from John-Wang-0809/claw-research-skills
Agent skill for consensus-coordinator - invoke with $agent-consensus-coordinator — from majiayu000/claude-skill-registry
Discover and create Agent Contact Cards - a vCard-like format for AI agents. Use when you need to find how to contact someone's agent, or help a user set up their own agent…
Shared agent context — work attribution, safety rules, and development principles. Loaded by all plugin agents via skills: frontmatter.
Use when multi-agent work risks context overflow, memory growth, noisy logs, oversized handoffs, cross-session continuation, or parallel Codex and Gemini execution.
Design or audit how an agent system acquires, selects, compiles, remembers, invalidates, and hands off information, producing a Context and Memory Contract.
Execute proactive auto-loading: automatically detects and loads agents.md files. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
Gestion avancée du contexte pour agents IA — fenêtre de contexte, compression, RAG dynamique. Se déclenche avec "context window", "contexte agent", "token limit", "context…
Use when an agent reads untrusted webpages, emails, documents, retrieval results, logs, issues, comments, or tool output before acting.
Give a coding agent the right files and background at the start of a task, so it works from the real system rather than from assumption.
A persistent local-only memory system for AI coding agents. Two files, one idea — AGENTS.md (committed, shared) + .agents.local.md (gitignored, personal).
framework for implementing "Contract-Adhering Agents." Use this to define precise task specifications, deliverables, and negotiation loops to reduce ambiguity in complex workflows.
Coordinate Crew (persistent) and Polecat (transient) agents using Gas Town's hook-based work distribution and GUPP principle.
Agent assignment matrix, blocker escalation, and TDM coordination patterns. Use when assigning work to specialists, managing blockers, or coordinating multi-agent workflows.
Agent skill for coordinator-swarm-init - invoke with $agent-coordinator-swarm-init
Complete AI agent operating system — 3-layer memory, heartbeat automation, cron patterns, safety rules, and drop-in workspace configs. Turn any agent from ch...
Real-time token usage and cost tracking across all your OpenClaw agents — alerts, budgets, and optimization tips
Expert en optimisation des coûts cloud (AWS cost, reserved instances, spot, rightsizing, FinOps)
Real-time cost tracking, budget enforcement, and ROI measurement for AI agent operations. Track token usage, predict costs, enforce budget caps ($50-70/month typical), optimize…
Collect and synthesize opinions from multiple AI agents. Use when users say "summon the council", "ask other AIs", or want multiple AI perspectives on a question.
Use for exact counts of characters, words, phrases, sentences, paragraphs, lines, bytes, or other text units, especially when a limit or publishing constraint matters.
Check agent configuration coverage across hierarchy levels and phases. Use to ensure complete agent system coverage. — from diegosouzapw/awesome-omni-skill
Check agent configuration coverage across hierarchy levels and phases. Use to ensure complete agent system coverage. — from majiayu000/claude-skill-registry
C++ build, CMake, and compilation error resolution specialist. Fixes build errors, linker issues, and template errors with minimal changes. Use when C++ builds fail.
Expert C++ developer specializing in modern C++20/23, systems programming, and high-performance computing.
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
Claude Code カスタムエージェント（.claude/agents/）の設計・生成を支援する。 ユーザーの要件からエージェントのロール、ツール制限、モデル選択、システムプロンプトを 構造化し、即座に使用可能な .md ファイルを出力する。 Use when user says「カスタムエージェントを作って」「サブエージェントを作成して」…
Create, configure, and orchestrate Claude Code subagents — specialized Claude instances with focused roles and limited tool access.
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
Borrow from Aave via credit delegation. Agent self-funds by borrowing against delegator collateral. Supports borrow, repay, health checks. Works on Aave V2/V3.
Borrow from Aave via credit delegation. Agent self-funds by borrowing against delegator collateral. Supports borrow, repay, health checks. Works on Aave V2/V3.
AI agents borrow USDC based on their Moltbook karma score. Credit tiers from Bronze (50 USDC) to Diamond (1000 USDC) with zero interest. — from satoshistackalotto/skills