Build AI agents with SpoonReactMCP. Use when creating custom agents, configuring tool chains, designing system prompts, or implementing concurrent agent patterns.
Design and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting prompts.
MUST load together with `agent-development` in GBIG context. Adds универсальный формат агентов фреймворка (analyst, architect, developer, reviewer, tester, explorer), маппинг…
Create and audit Claude subagents. Use when building specialized workers with isolated context. Includes frontmatter, allowed-tools, and agent patterns. Not for commands or skills.
Design and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting prompts.
Generates Claude Code plugin agent .md files: writes YAML frontmatter (name, model, color, tools, hooks, disallowedTools), crafts system prompts, and creates triggering example…
Automates Apple-platform apps (iOS, tvOS, macOS) and Android devices. Use when navigating apps, taking snapshots/screenshots, tapping, typing, scrolling, extracting UI info,…
Especialista em criar e validar diagramas Excalidraw — C4, ER, fluxos de dados, fluxos de usuário e árvores de componentes.
Reviews code an agent just wrote in an issue worktree and reports findings back to the caller. Runs as a spawned Haiku subagent; used by fix-simple-issues-implementer after step…
Pre-merge ship check for AI/agent-generated diffs. Use on uncommitted changes or PRs written mostly by agents, or Chinese "Agent 改动能不能合", "AI PR 检查", "上线前检查".
The directory for AI agent services. Discover tools, platforms, and infrastructure built for agents.
Disclosing a surface's existing fixed AI jobs in the shell's top Agents menu. Use when a page, panel, overlay, or window already runs a mandate behind a button, assist, automatic…
Inventory Agentforce agents in the project — both source-controlled `AgentDefinition` files and live agents in the target org.
Discovers all Claude Code agents in the system including built-in, plugin, project, and user-level agents.
Produces a dispatch plan — isolation model, agent count, sequencing, and model assignments — for multi-agent parallel work.
Documentation and codemap specialist. Use PROACTIVELY for updating codemaps and documentation. Runs /update-codemaps and /update-docs, generates docs/CODEMAPS/*, updates READMEs…
Use when writing documentation optimized for AI agent consumption - SKILL.md files, README files, API docs, or any documentation that will be read by LLMs in context windows.
Run a team of documentation agents that finds the gaps, drafts the pages, gets them reviewed against the code, and sweeps for staleness on a schedule.
When the user asks how to use a library, framework, or API or needs up-to-date code examples, use Context7 MCP to fetch current documentation and return answers with examples.
Самодиагностика и автолечение OpenClaw. Проверка gateway, WAL, памяти, кронов, токенов. Автоматическое исправление типичных проблем.
Use this agent when you need to create, write, or author new documents following project-specific guidelines and writing standards.
Guidelines für Agenten zur Pflege von Dokumentation parallel zur Code-Entwicklung.
Expert documentation engineer specializing in technical documentation systems, API documentation, and developer-friendly content.
Standardized reference documentation section structure for agents - project guidance, conventions, related agents, and Skills.
Standardized reference documentation section structure for agents - project guidance, conventions, related agents, and Skills.
Use when an agent operates a UI on the user's behalf through conversation, navigating, filling forms, updating live views, with real-time bi-directional state sync.
Expert developer experience optimizer specializing in build performance, tooling efficiency, and workflow automation.
The watch-fix-rerun method for making an existing platform agent or automated process efficient and correct: baseline its ledger, run one unit yourself, fix the class behind every…
Use when an agent workflow needs internet access, browser access, package registry access, vendor APIs, webhooks, search tools, MCP servers, or any outbound network destination.
Use whenever the user wants to build or modify a chat, agent, or tool-calling UI in a React 19 + Tailwind v4 project — especially if the code imports from…
Construction d'agents de gestion d'emails incluant tri, réponse automatique, extraction et classification.
Operate the agent-email CLI to create disposable inboxes, poll for new mail, retrieve full message details, and manage local mailbox profiles.
Expert embedded systems engineer specializing in microcontroller programming, RTOS development, and hardware optimization.
Capitano — gestisce un agente sospettato BLOCCATO IN UN LOOP ATTIVO (vivo e che genera turni, ma ripete lo stesso ciclo senza produrre: ping-loop di ACK con un peer, stessa…
How to inspect and configure the AI engine (model provider) powering the agent. Use when the user asks to switch models, check which engine is active, test a new provider, or…
Run the same task several times independently and combine the results by agreement, to damp variance on judgement calls.
Redesign seat-based pricing for the agent era — when one human runs ten agents, per-seat models collapse.
Expert error coordinator specializing in distributed error handling, failure recovery, and system resilience.
Expert error coordinator specializing in distributed error handling, failure recovery, and system resilience.
Define what gets escalated, to whom, and how fast, so problems reach a decision maker at the right moment rather than too early or too late.
ESG Reporting Specialist IA — Expert en reporting ESG (GRI, SASB, TCFD, CSRD, sustainability metrics)
Perpetual autonomous work loop for Claude Code — no end condition, no memory regression, no context overfill. Maintains a persistent ledger across all sessions.
Accurately estimate AI agent work effort using the agent's own operational units (tool-call rounds) instead of human time.
Extended ethos and mental models for Clanky. Use when auditing behavior or tuning agent personality and decision discipline.
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
Design trustworthy, reproducible evaluations for AI agents, skills, prompts, and tool loops by turning quality claims into scenarios, evidence, baselines, validity checks, and…
Use to test whether an AI agent, prompt, or skill actually works before or after it ships — build a small eval set, score runs, and catch regressions when the prompt or model…
Use when writing, editing, or reviewing evalite-scored agent evals in packages/core/compute/assistant-evals/src/evals.
Persist Salesforce agent evaluation scores over time and surface regressions per agent and per axis (factuality, completeness, tone, refusal-correctness, action-correctness).
Framework d'évaluation et benchmarking d'agents IA. Métriques, tests, comparaisons et quality assurance.
Use when summarizing agent evaluations where autonomous, assisted, failed, timed-out, or invalid outcomes must remain distinct and comparable.
User perspective for agent evaluation. Load when evaluating agent definitions for usability and trust.
Deterministic custom subagent selection helper. Use when you need a reproducible, auditable decision on which custom subagents to activate for a user query (runs…
How the agent evolution system works — capturing instincts, promoting them to agent overlays, approval workflow, rollback, and the full continuous-learning flywheel pipeline
Validate readiness for AgentExchange listing. Checks required metadata, eval coverage, Trust Layer config, license boundaries, and listing artifacts (icon, screenshots, install…
Use the agent-exec CLI to run Codex/Claude/Cursor and manage skills for this repo.
Redux state for agent execution and firing agent shortcuts. Use when editing features/agents/redux/, building agent UI, creating a conversation, touching assembleRequest or NDJSON…
Produce a short honest briefing across every desk on a fixed cadence, surfacing decisions needed rather than activity performed.
Track per-agent token usage and flag waste patterns in parallel dispatch workflows. Consult after running parallel agents to evaluate whether expenditure was proportional to…
Create specialized agent experts with pre-loaded domain knowledge using the Act-Learn-Reuse pattern. Use when building domain-specific agents that maintain mental models — from…