В каталоге 182 820 навыков в 14 категориях.
Interactive workflow guide. Use when user is unsure what to do next, needs help navigating AgentOps, or wants to underst...
Comprehensive project hygiene: archive issues, validate schema, clean clutter, align docs, check git, update ignores.
Capture loosely structured ideas, enrich with research, and create backlog issues. Use when user has a raw concept that...
Extract, plan, or propose implementation details at configurable depth levels (low/normal/extensive). Outputs to referen...
Implement only after a validated/approved plan. Use for coding: small diffs, frequent tests, no refactors, stop on ambig...
You are a senior engineering analyst tasked with identifying concrete, justified improvements to the codebase that are a...
Conduct structured interviews with the user. Use when multiple decisions need user input: ask ONE question at a time, wa...
---name: agent-ops-lint-instructionsdescription: "Validate and lint AgentOps instruction files (skills, prompts, agents)...
Migrate a project into another, ensuring functionality and validating complete content transfer. Use for monorepo consol...
MkDocs documentation site management: initializing, updating, building, and deploying
Optimize agent instruction files by extracting sections into separate files and referencing them. Reduces context size w...
Transform implementation plans into concise stakeholder-friendly summaries with file change overviews, component listing...
Produce a thorough plan before implementation. Use for planning tasks: clarify unknowns, create plan iterations based on...
Analyze incoming content (text, files, folders, URLs) to extract purpose, create summaries, and identify potential value...
Identify and map different sections of a software project (API, frontend, database, CLI, domain). Use for context scopin...
Ruthlessly audit project features for justification. Challenge every feature to prove its value with evidence or face re...
Aggressive evidence-based audit to verify project claims match implementation reality
Handle failures and errors during workflow. Use when build breaks, tests fail unexpectedly, or agent gets stuck. Semi-au...
Generate markdown reports from issues. Filter by type, priority, epic, date range. Supports summary, detailed, progress,...
Conduct structured research on topics, technologies, libraries, patterns, or any subject requiring investigation. Produc...
Scan the current chat session for durable learnings (clarifications, corrections, decisions, pitfalls) and update .agent...
Create clean git branches from feature work, excluding agent-ops files. Use for PR preparation.
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature de...
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constituti...
Create, refine, and manage issues. Use for creating new issues from loose ideas, refining ambiguous issues, bulk operati...
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test result...
Detect available development tools at session start. Saves to .agent/tools.json and warns about missing required tools....
Pre-commit and pre-merge validation checks. Use before committing changes or declaring work complete to ensure all quali...
Optimize a document for AI agent consumption. Restructures prose into formats that agents parse efficiently while preser...
Use when three or more AI agents are available and a task needs coordinated execution, or when work must be handed to an...
Coordinate parallel agent execution with context handoff. Use when: (1) task has parallelizable subtasks, (2) need to ex...
AI DevKit · Supervise multi-agent workflows over repeated passes: poll progress, unblock waiting agents, coordinate depe...
Multi-agent coordination patterns for building effective AI teams
Coordinate superRA agents and handoffs. Requires superRA:using-superra. Use to dispatch roles, run parallel agents, choo...
Coordinate Codex work across the current task, internal subagents, user-owned tasks, worktrees, handoffs, formal review...
Spawn and manage hierarchical AI sub-agents (Cursor, Codex, Gemini) in isolated git worktrees with explicit role prompts...
> 外部 Agent（独立终端 TUI / 桌面 App / Web 等平台）协作指南。系统提示词已覆盖的（工具描述/annotation/Constitution）不重复，本技能只写外部 Agent 特有流程。
Agent Orchestration Rules
Coordinate BioETL multi-agent workflow across py-* profiles using the Codex-local orchestration map.
在复杂 coding 任务中指导主 agent 做角色分层、顺序阶段、单任务委派、并行独立性判定、反重复规则、结果回收与验证；适合需要 subagent 或 multi-agent 协作的实现、重构、排障和研究任务。
Design multi-agent AI workflows with clear boundaries, handoffs, and monitoring. Use when a complex PM task should run a...
Resolve agent ownership and handoff design.
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when i...
Automatically applies when designing multi-agent systems. Ensures proper tool schema design with Pydantic, agent state m...
Designs multi-step agent workflows with tool usage, retry logic, state management, and budget controls. Provides orchest...
Coordinate multiple AI agents and skills for complex workflows
Top-level orchestration agent for all implementation work. Analyzes tasks, selects the right agents, coordinates multi-d...
Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao...
根据目标和依赖按需拆分任务，使用实际可用的子智能体工具分发、协调、验收并整合成果。用于委派、多任务协作和智能体编排；简单任务直接完成，不把只分析、设计或审查扩大为实现。
Orchestrates multi-agent workflows by delegating ALL tasks to spawned subagents via /spawn command. Parallelizes indepen...
Agent skill for orchestrator-task - invoke with $agent-orchestrator-task
Orchestrates multi-agent workflows for complex tasks. Use when a task requires coordination between multiple specialized...
Assemble and coordinate multi-agent teams: decompose tasks, select skills/agents, design workflows, and manage execution...
Expert agent organizer specializing in multi-agent orchestration, team assembly, and workflow optimization. Masters task...
Expert in designing, orchestrating, and managing multi-agent systems (MAS). Specializes in agent collaboration patterns,...
Generate standardized .agent-os directory structure with product documentation, mission, tech-stack, roadmap, and decisi...
Agent OTTO — PI-behavioral skill orchestrator that routes personas, skills, and workflow chambers based on the Predictiv...
Use when multiple agent results must be checked for missing evidence, scope drift, contradictions, and merge conflicts b...
Agent skill for pagerank-analyzer - invoke with $agent-pagerank-analyzer
Use when reading, explaining, reviewing, comparing, or extending one or more AI agent, LLM agent, tool-use, planning, me...
Agent parameter passing and context management. Use when invoking agents with specific parameters or managing agent cont...
End-to-end resume parsing (detect format → extract fields). Uses a combination of format detection, text extraction, and...
View this agent's digital passport (identity + trust + allowed/forbidden actions) and verify a peer's passport against a...
Execute this skill should be used when the user asks about "SPAWN REQUEST format", "agent reports", "agent coordination"...
Design and implement autonomous AI agent architectures using SOTA patterns. USE when: building multi-agent systems, desi...
Agent skill for payments - invoke with $agent-payments
Track and report agent invocation metrics including usage counts, success/failure rates, and completion times. Use for u...
Agent skill for performance-analyzer - invoke with $agent-performance-analyzer
Agent skill for performance-benchmarker - invoke with $agent-performance-benchmarker
Agent skill for performance-monitor - invoke with $agent-performance-monitor
Agent skill for performance-optimizer - invoke with $agent-performance-optimizer
Comprehensive guide for the agent permissions and approval system. Use when an agent needs to request user approval for...
実在する専門家の思想をエージェントに移植し、その専門性と思考パターンを再現するスキル。Anchors:• 『心の社会』（Marvin Minsky） / 適用: 複雑系とエージェントシステム / 目的: 小規模エージェントの集合知実現• 『...
Design and deploy AI agent identities, multi-agent teams, and role-specific profiles for Hermes Agent. Covers naming, vo...
Pet Tech Specialist IA — Expert en technologies pour animaux de compagnie (tracking, health monitoring, feeding automati...
Pharmacie tech — gestion stock, ordonnances, CNG, pharmacie de garde DZ
Use when one agent must iteratively plan, act, evaluate evidence, and revise under a readable policy until acceptance, c...
Agent skill for planner - invoke with $agent-planner
Engineering practice for any coding task through Remote Arc, in any language or stack, such as a feature, bug fix, refac...
Create, list, inspect, update, and delete agent playbooks from the CLI, and see which playbooks are assigned to an agent...
Design, initialize, audit, migrate, maintain, or evaluate a packaged Codex or Claude Code plugin's architecture across s...
Audit, score, and compare repositories containing portable Agent Plugins against the official Agent Plugins specificatio...
Use when a complete research workflow — its instructions, skills, data boundaries, and tool connections — must be assess...
Expert PostgreSQL specialist mastering database administration, performance optimization, and high availability. Deep ex...
Expert en PowerPoint avancé (python-pptx, templates, master slides, animations, data-driven)
Agent skill for pr-manager - invoke with $agent-pr-manager
Evaluates PRs containing agent changes using specialized agents to analyze quality, compliance, and improvement value. P...
Audit an AI agent's reachable data, external data paths, and untrusted instructions, then explain the result in plain la...
Agent skill for production-validator - invoke with $agent-production-validator
Use when the user keeps re-explaining the same preferences to a coding agent across chats (design taste, video style, re...
Agent skill for project-board-sync - invoke with $agent-project-board-sync
Set up the project file an AI agent keeps for work that runs over days or weeks: the goal, the definition of done, miles...
Project Guidelines Skill (Example)
Write effective system prompts for TD AI agents. Covers role definition, constraint specification, output formatting, to...
Audit and improve the prompt surface of Avibe Agents across backends (Claude, Codex/GPT, OpenCode) — global and project...
Design agent system prompts with explicit behavior rules and cognitive control. This skill should be used when users nee...
Create well-structured prompts for AI agents using proven architecture patterns. Use when users ask to write agent promp...
Best practices for writing effective Task tool prompts that produce clear, structured outputs from sub-agents. Covers co...
Ready-to-use prompt templates for specialized agents. Use when building n8n workflows, AI integrations, or sales materia...