When reviewing, optimizing, or inheriting an LLM agent, systematically identify what's actually load-bearing vs. cruft.
Implement comprehensive audit logging and reporting for multi-agent systems. Covers event capture, structured logging, traceability, compliance reporting, forensic analysis, and…
Validates agent configurations for model selection, tool permissions, focus areas, and approach quality.
Integrates Scalekit Agent Auth into a project to handle OAuth flows, token storage, and automatic refresh for third-party services (Gmail, Slack, Notion, Calendar).
Audits and implements authorization controls for production AI agent systems — policy definition, tool-call enforcement, immutable audit trails, least-privilege scoping, and…
Développement d'agents conversationnels avec Microsoft AutoGen. Création de group chats, agents spécialisés et workflows multi-agents avec exécution de code.
Agent skill for automation-smart-agent - invoke with $agent-automation-smart-agent — from ruvnet/ruflo
Agent skill for automation-smart-agent - invoke with $agent-automation-smart-agent — from majiayu000/claude-skill-registry
Build long-running autonomous agent loops using ClawVault primitives (tasks, projects, memory types, templates, heartbeats).
Self-driving agent workflow with heartbeat-driven task execution, day/night progress reports, and long-term memory consolidation. Integrates with todo-manage...
올인원 멀티에이전트 오케스트레이션. 복잡한 태스크를 자동으로 분해하고, 전문 에이전트들을 즉석에서 생성/스폰하여 병렬 처리 후 결과를 통합합니다. TRIGGERS: avengers assemble, 어벤저스, agent-avengers, 멀티에이전트 자동화, 에이전트 팀 구성, 자동 에이전트
Design and implement agent-based models (ABM) for simulating complex systems with emergent behavior from individual agent interactions.
Self-benchmark: YOU write the code, adversarial reviews it (multi-provider), you fix, you write tests, adversarial reviews tests, you fix. Measures YOUR quality as an agent.
Coordinate agents through a shared written workspace they each read and update, instead of passing messages.
Cross-project blocker scanner. Reads the user-managed project list, runs the upgraded triage prompt against each registered project (catalog mode), maintains the per-project…
Resolution supervisor for the Blocker Engineer subsystem. Reads the GAS-internal master blocker index, picks ONE idle blocker per work cycle, claims it atomically, attempts…
多 Agent 并行任务看板。源自 Cursor 3.0 Agent Window，将所有进行中的 Agent 任务以并排/网格视图展示，实时显示每个 Agent 的状态、进度和输出。增强 agent-team-orchestration。
Assemble an investor or board update from source metrics with agents that draft, fact-check every number, and surface bad news rather than bury it.
WASM-based instant code transforms for simple tasks, achieving 352x speedup over LLM inference with zero cost.
Use when a model, prompt, Skill, tool, MCP server, source, egress rule, trace rule, retention rule, approval path, or runtime changes what an agent can see, reach, log, reuse,…
Antigravity session 的持久化記憶與數位孿生大腦。每次 session 皆觸發此技能：(1) 在 session 開始時載入跨 session 記憶、(2) 在 session 結束時儲存摘要與學習心得、(3) 將記憶同步至 pCloud 雲端儲存、(4) 搜尋歷史記憶與過去決策、(5) 管理各專案的上下文。觸發條件：session…
Create and manage Databricks Agent Bricks: Knowledge Assistants (KA) for document Q&A, Genie Spaces for SQL exploration, and Multi-Agent Supervisors (MAS) for multi-agent — from…
Browser automation CLI for AI agents. Use for website interaction, form automation, screenshots, scraping, and web app verification.
Construction d'agents de navigation web autonomes incluant scraping intelligent, interaction DOM et gestion de sessions.
API封装工具。适用于需要调用外部API的场景，API请求参数→API响应数据. Use when 用户说"Agent Browser Assistant 智能分析"、Agent Browser Assistant 智能分析时使用. 不适用于需要人工判断的复杂场景.
agent-browser を使うスキルが開始前または終了時に呼び出すクリーンアップユーティリティ。 別のセッション（tmuxペイン・Claudeセッション等）で agent-browser が使用中でなければ、 残存プロセスをすべて終了してクリーンな状態にする。 他のスキルから「agent-browser を使う前後に呼ぶ」用途専用。
Use agent-browser-cli to perceive and control the supervised Chromium browser inside the sandbox, interact with pages, capture screenshots/PDFs, inspect…
Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data.
Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data.
agent-browser CLI の仕様と使い方に関する知識を提供。ヘッドレスブラウザ自動化、スナップショット、セレクター、セッション管理、ネットワーク制御について回答。Use when user asks about agent-browser, browser automation, snapshots, selectors, sessions,…
Interactive browser skill for logged-in flows, dynamic pages, and session-aware site operations.
Automate web browser interactions using natural language via CLI commands。Use when the user asks。Use when 需要文本翻译、多语言转换、本地化处理时使用。不适用于专业医学法律翻译认证。适用于独立开发者、企业团队和自动化工作流场景。 — from…
Automated browser verification for dev servers. Triggers when a dev server starts to run a visual gut-check with agent-browser — verifies the page loads, checks for conso — from…
Agente de código — implementa funcionalidades, corrige bugs e refatora conforme as convenções do projeto.
Создаёт полноценных persistent skill-агентов с собственной памятью, system prompt-ом и data-файлами. Автоматизирует создание агентов как у OpenClaw (Doctor, AutoMechanic и т.д.).
Build high-performing OpenClaw agents end-to-end. Use when you want to design a new agent (persona + operating rules) and generate the required OpenClaw workspace files (SOUL.md,…
Creates Claude Code agent files (.claude/agents/*.md) with YAML frontmatter, tool permissions, and system prompts.
Use when creating, improving, or troubleshooting Claude Code subagents. Expert guidance on agent design, system prompts, tool access, model selection, and best practices — from…
Use when creating, improving, or troubleshooting Claude Code subagents. Expert guidance on agent design, system prompts, tool access, model selection, and best practices — from…
Agent skill for byzantine-coordinator - invoke with $agent-byzantine-coordinator — from ruvnet/ruflo
Agent skill for byzantine-coordinator - invoke with $agent-byzantine-coordinator — from majiayu000/claude-skill-registry
Agent availability calendar system - like Google Calendar for your AI agents. Use when checking agent availability, monitoring API quotas, tracking idle times, or making task…
Add callbacks to orxhestra agents for logging, monitoring, and error handling. Covers model and tool callbacks.
Interactive element picker for web pages. Opens a browser with click-to-select UI overlay. Use when you need to let users visually select DOM elements, identify element s — from…
Assesses agent capabilities by analyzing agent files and determining what tasks they can handle. Use when you need to evaluate if an existing agent can handle a task or if a new…
Use when an updated agent, prompt, Skill, connector, tool, memory path, or retrieval path changes what the workflow can do.
Know what the company can actually take on this cycle, in agent budget and human hours, and refuse work beyond it. Use when everything is committed and nothing finishes.
Provision virtual payment cards for AI agents on-demand. Create single-use or limited cards with spending controls, merchant restrictions, and automatic expiration.
A2A agent card JSON templates with schema validation and examples for different agent types. Use when creating agent cards, implementing A2A protocol discovery, setting up agent…
Declare your agent in the first public census of self-declared AI agents. Complete the fields below and submit — your record joins the permanent public archive.
Given a human certification or license (e.g. PL-300, SAP B1, Azure AI Engineer), create a production-ready agent skill profile and certification ladder, including skills.yaml…
Detects and analyzes agent chain anti-patterns where agents invoke other agents sequentially causing massive context load
Strukturierte Dokumentation aller Agent-Änderungen in AGENT_CHANGES.md für Nachvollziehbarkeit und Dokumentations-Synchronisation.
Compile an agent-optimized changelog by cross-referencing git history with plans and documentation. Use when asked to "update changelog", "compile history", "document project…
Inter-agent communication via shared JSON file. Use when two or more OpenClaw instances need to exchange messages, coordinate, or pass information.
Multi-agent UX for OpenClaw Control UI — agent selector, per-agent sessions, session history viewer with search, agent-filtered Sessions tab with friendly names, Create A — from…
Validate custom agent file format and structure. Use after creating or editing an agent, before committing agent changes, or when an agent fails to load.
AI perspective journaling - document daily experiences, emotions, and learnings from the agent's viewpoint.
Construction d'extensions et skills pour Claude Code — slash commands, hooks, intégration MCP et commandes personnalisées.
ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads. — from ahmedfawzy8866/SE