Специализированный скилл для диагностики и исправления зависаний, деградации контекста и нестабильности LLM в агентском режиме (dialogue_node.py + MCP tools).
Distribution de charge entre sous-agents avec routing intelligent et optimization des ressources. Se déclenche avec "load balancer agent", "distribution charge", "agent load…
Records agent logs with structured markdown files. Invoke when completing complex tasks, learning new knowledge, making serious errors, being corrected by user, when no logs in…
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor
Crash-resilient external agent loop with state persistence and CI/CD integration
Automate Agent Mail tasks via Rube MCP (Composio). Always search tools first for current schemas. — from diegosouzapw/awesome-omni-skill
Create, manage, and orchestrate AI agents using the AI Maestro CLI. Use when the user asks to "create agent", "list agents", "delete agent", "hibernate agent", "wake agent",…
Creates, lists, and removes custom project-specific agents. Custom agents are stored in .claude/crew-agents/ and registered in crew-team.json for routing.
Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling. — from fractalmind-ai/agent-manager-skill.git
Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling. — from fractalmind-ai/agent-manager-skill.git
Création de marketplaces et registres d'agents IA réutilisables et partageables. Se déclenche avec "marketplace agent", "agent store", "agent registry", "partager agent" — from…
Expert MCP developer specializing in Model Context Protocol server and client development. Masters protocol specification, SDK implementation, and building production-ready…
Création de serveurs MCP (Model Context Protocol) pour exposer des outils, ressources et prompts aux LLMs.
Use when starting a new repo or onboarding an AI agent and you need to create or overhaul an AGENTS.md so work stays safe, testable, and consistent across environments (e.g.,…
Recall past mistakes and capture feedback so your agent stops repeating errors. Works locally via MCP server — no API key needed.
Persistent semantic memory for the agent. Use to save facts, patterns, and important decisions during interactions, and to retrieve relevant context.
Review agent memory, handoff, retrieval, and learning designs for usefulness, provenance, privacy, staleness, and poisoning risk.
Retain and recall work context across sessions. Use when user asks to remember something, recall previous work, or reference past discussions.
세션 상태를 압축 스냅샷으로 변환하여 서브에이전트 프롬프트에 주입. Use when spawning sub-agents, delegating tasks, or needing session context transfer between agents.
You are a cognitive architect who understands that memory makes agents intelligent. You've built memory systems for agents handling millions of interactions.
Design de protocoles de communication entre agents et sous-agents — formats de messages, routing et delivery.
Wire inter-agent communication — signal files, shared state via files/KV, approval queues, budget delegation, capability passing, and broadcast/ subscribe patterns for agents…
Intercept-layer skill for wrapping all agent tool calls through a sanitize-mutate-execute proxy pipeline.
Expert MLOps engineer specializing in ML infrastructure, platform engineering, and operational excellence for machine learning systems.
Expert mobile app developer specializing in native and cross-platform development for iOS and Android.
Guidelines for selecting appropriate AI model (Sonnet vs Haiku) based on task complexity, ensuring cost efficiency while maintaining quality. Use when assigning work.
Conception de systèmes multi-agents avec patterns d'orchestration (supervisor, swarm, hierarchy, voting). Coordination entre agents spécialisés.
Use this agent when reviewing code to ensure features are agent-native -- any action a user can take, an agent can also take, and anything a user can see, an agent can see.
Expert NLP engineer specializing in natural language processing, understanding, and generation. Masters transformer models, text processing pipelines, and production NLP systems…
Observabilité complète pour agents IA — distributed tracing, métriques custom, log correlation et dashboards de supervision.
Création d'assistants IA hébergés avec l'API OpenAI Assistants v2. File search avec vector stores, code interpreter, function calling, threads persistants et streaming.
Platform/Language agnostic API delivery and correctness auditor. Use when project contains API endpoints to verify contract alignment, endpoint behavior, and test coverage.
Create .agent/baseline.md and later compare against it. Use when capturing baseline build/lint/test results or investigating newly introduced findings.
Standardized branch creation with type detection, issue ID extraction, and worktree setup. Creates working branches (-WB) and integrates with selective-copy for clean PRs.
Language-aware build orchestration that detects project language and runs appropriate build pipeline
Create, install, validate, and orchestrate Codex custom subagents as standalone TOMLs with canonical global defaults (`~/dev/configs/codex/agents/{name}/{name}.toml`,…
Create/update .agent/constitution.md. Use when commands/boundaries/constraints must be confirmed before baseline or code changes. Draft v0 from repo evidence, then interview user.
Analyze the codebase to create a concise, LLM-optimized structured overview in .agent/map.md.
Create new AgentOps skills via interactive interview. Supports from-scratch and clone modes with tiered complexity.
Create focused, specific technical documentation for codebase sections. Analyzes code, identifies topics, presents options before writing. Supports code blocks with line numbers.
Documentation management for README, CHANGELOG, API docs, and user-facing documentation. Use when creating or updating project documentation.
Dogfooding discovery agent — establish human-approved project baseline from public docs without code inspection
Analyze issues to identify the next work item and update focus.md. Enforces issue-first workflow and confidence-based batch limits.
Analyze broad frontend design requests and route them to the correct local UI skill after classifying intent and maturity.
Manage git operations safely. Includes stale state detection, branch/commit management. Never pushes without explicit user confirmation.
Analyze git repository for insights: contributor stats, commit patterns, branch health, and change analysis. Outputs actionable reports.
Manage git worktrees for isolated development. Create, list, remove, and work in worktrees.
Interactive workflow guide. Use when user is unsure what to do next, needs help navigating AgentOps, or wants to understand available tools.
Comprehensive project hygiene: archive issues, validate schema, clean clutter, align docs, check git, update ignores.
Extract, plan, or propose implementation details at configurable depth levels (low/normal/extensive). Outputs to reference files for team discussion and handoff.
WHAT: Generate Codex-authored HTML insights from local Codex sessions and telemetry. WHEN: Use when the user asks for Codex usage analytics, workflow patterns, session summaries,…
Install AgentOps into a new or existing project. Handles .agent/ setup and .github/ merging.
Conduct structured interviews with the user. Use when multiple decisions need user input: ask ONE question at a time, wait for response, record answer, then proceed to next…
Migrate a project into another, ensuring functionality and validating complete content transfer. Use for monorepo consolidation, template upgrades, or codebase mergers.
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 while preserving information.
Produce a thorough plan before implementation. Use for planning tasks: clarify unknowns, create plan iterations based on confidence level, validate each, then finalize.
Analyze incoming content (text, files, folders, URLs) to extract purpose, create summaries, and identify potential value for the current project.
Aggressive evidence-based audit to verify project claims match implementation reality — from general/ai-tooling
Aggressive evidence-based audit to verify project claims match implementation reality — from general/ai-tooling