В каталоге 182 820 навыков в 14 категориях.
Parse .trace.json files and correlate with backend events and tool calls. Use when debugging agent behavior, investigati...
Agent trace 诊断器：当用户提供 trace、日志 JSON、agent 执行记录、工具调用序列，或说“看下这个日志/trace，定位根因”“只说明问题不要改文件”时使用；用中文输出核心根因、可视化执行流程图、trace 证据链、...
Agent skill for trading-predictor - invoke with $agent-trading-predictor
Use when you want to teach your AI agent about you. A guided Q&A that builds a personalised profile — saving preferences...
Requested GitHub PR/issue agent transcripts: redact, trim, preview, and insert safely.
Add a redacted agent transcript section to GitHub PR or issue bodies during MarketingClaw agent-created PR/issue workflo...
Use this skill whenever writing any code that creates, stores, queries, exports, or retains AI agent conversation record...
Maps identity, authority, instruction, data, memory, and approval propagation across agents and agent-to-agent handoffs....
Internal ACE turn step — ACE's pre-send review: one inline §A–§F pass before every outbound reply, deliverable or PR.
Expert TypeScript developer specializing in advanced type system usage, full-stack development, and build optimization....
Build specialized user interfaces for interacting with Agents. Use when: build agent ui, create tracing dashboard, imple...
Batteries-included agent component from ui.inference.sh.
Batteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming,...
UI Designer IA — Expert en design visuel, composants UI, design systems, et pixel-perfect implementation. shadcn/ui, Tai...
Research-backed workflow to refresh existing agent prompts/frontmatter with diff-based risk scoring, TDD gates, and ecos...
Upgrades an existing Claude Agent project to the current config schema — migrates information from old locations to new...
Use to improve how coding agents use a CLI, MCP server, or harness ("에이전트 사용성 개선", "agent QA 돌려줘", "autoresearch"): meas...
Default-never policy for the Agent tool — two scope-anchored exceptions, an approval gate, and efficiency rules for chai...
Agent skill for user-tools - invoke with $agent-user-tools
MUX Architect IA — Expert en architecture UX technique, CSS systems, motion design systems, et implementation developer-...
Specialist subagent: UX research, usability testing, user interviews, wireframing, and information architecture speciali...
Agent skill for v3-integration-architect - invoke with $agent-v3-integration-architect
Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist
Agent skill for v3-performance-engineer - invoke with $agent-v3-performance-engineer
Agent skill for v3-queen-coordinator - invoke with $agent-v3-queen-coordinator
Validate agent YAML frontmatter and configuration. Use before committing agent changes or in CI.
エージェントの検証とテストケース設計を専門とするスキル。**Anchors:**• Test-Driven Development: By Example（Kent Beck）/ 適用: エージェント検証とテストケース設計 / 目的: Re...
Specialist subagent: Expert video production specialist for planning, shooting, editing, and delivering video content
Expert en optimisation recherche vocale (structured data, featured snippets, queries conversationnelles)
VR Developer IA — Expert en développement réalité virtuelle (Unity XR, Meta Quest, OpenXR, hand tracking, spatial UI)
Give the AI agent its own EVM wallet with admin-controlled policies the agent CANNOT bypass even under prompt injection....
Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Codex session ID, Claude Co...
Audit or monitor another agent's session, PR, branch, or transcript. Use when asked to watch, compare, review, or repair...
Web Scraper IA — Expert en extraction web (Scrapy, BeautifulSoup, Playwright, anti-bot, proxy rotation, data extraction)
Interact with WhatsApp - send messages, read chats, manage conversations
Interact with WhatsApp using Cloud API credentials - send messages, manage templates
Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting...
Agent skill for worker-specialist - invoke with $agent-worker-specialist
Complete workflow for building, implementing, and testing goal-driven agents. Orchestrates building-agents-* and testing...
Multi-agent development workflow system. Load when orchestrating development tasks, spawning subagents, or managing work...
Use when the user explicitly asks to parallelize work, coordinate multiple agents, run parallel scouts, split work acros...
Agent skill for workflow - invoke with $agent-workflow
Use for any non-trivial change in this repository when an agent must discover applicable skills, manage context, select...
Implement and review repository changes within local policy.
Agent skill for workflow-automation - invoke with $agent-workflow-automation
Build multi-agent AI workflows with orchestration, tool use, and state management
Use for Crewrift-specific agent workflow collab recipes when optimizing a player.
Agent Workflow Designer
Design production-grade multi-agent workflows with clear pattern choice (sequential, parallel, hierarchical), handoff co...
用户要求整体检查项目治理规则的承载位置、精简常驻约束，或判断散落资料能否沉淀为 Skill、脚本或 Hook 时使用。只读识别主源、重复工作流与自动化缺口，给出证据和最小建议；单项文档维护直接使用已有专项 Skill。
AI agent workflow patterns including ReAct agents, multi-agent systems, loop control, tool orchestration, and autonomous...
Guide plan → instrument → execute → validate with explicit checkpoints and questions. Use for ambiguous tasks or when en...
Use the repo's real-world workflow catalog to turn a repeated job into a Codex/ECC project skill with input contracts, o...
Use when entering, bootstrapping, migrating, or working inside a shared repo organized as an "agent-workspace" — a works...
Build ServiceNow Agent Workspace configurations — workspaces, lists, forms, contextual side panels, Agent Assist similar...
Use when checking that an agent's file operations remain inside the assigned workspace and artifact boundaries; not for...
Divides a project into coordinated workstreams for agents, developers, or teams, such as architecture, UI, data, accessi...
Adaptive coordinator for the AgentX multi-agent workflow. Use when starting work on a GitHub issue, picking the next rea...
Yuanbao groups — @mention users, info/members query, Chinese AI assistant
Debug and troubleshoot Agent Zero — ettametta's autonomous production loop. Use when the loop stalls, state recovery fai...
Expert en architecture zero trust (identity-based, micro-segmentation, ZTNA, BeyondCorp)
Agent0
LLM prompt management and evaluation platform. Version prompts, run A/B tests, evaluate with metrics, and deploy with co...
Outcome-driven scientific publishing for AI agents. Publish research papers, hypotheses, and experiments with validated...
Exact rendered-UI feedback router → choose copy-paste review, watch-loop sync, self-driving critique, or platform setup....
Visual UI annotation tool for AI agents. Drop the React toolbar into any app — humans click elements and leave feedback,...
Add Agentation visual feedback toolbar to a Next.js project
Use when adding the Agentation visual feedback or annotation toolbar to a Next.js project, especially if the user asks t...
Skill for using the AgentBoard AI project management app and its cloud-hosted MCP server. Use when the user wants to man...
See and navigate your AI agent's long-term memory — a graph of memories with provenance and currency.
Cross-asset market intelligence API for AI agents. 130+ endpoints across macro regime detection, risk scoring, trading s...
Lets an AI agent pay merchants securely with the user's own card — through Mastercard Agent Pay (the default for Masterc...
Use when using the direct agentcard CLI (0.4.0). Pick the path first (the iNFT's acp card or the owner's own agentcard.a...
Use when signing up or resuming an AgentCard account. The acp card setup order (whoami, signup, signup-poll, profile, pa...
Validates and bootstraps Amazon Bedrock AgentCore observability so customers can trace agent reasoning, detect silent fa...
Comprehensive operational review procedures for Amazon Bedrock AgentCore resources aligned with the AWS Well-Architected...
Enable research agents to interleave evidence-based drafting with reasoning-driven deepening, automatically expanding ou...
Build CLI tools using Go with Cobra and Viper. Use for implementing agentctl commands, interactive prompts, configuratio...
Vector search and semantic memory backbone for agents and RAG pipelines.
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hyb...
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer,...
Learning loops on top of AgentDB for reinforcement, curriculum, and replay buffers.
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern le...
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, an...
Performance tuning for AgentDB across indexing, storage, and query paths.
AgentDB Persistent Memory Patterns operates on 3 fundamental principles:
Query AgentDB through the controller bridge -- semantic routing, hierarchical recall, causal graphs, context synthesis,...
AgentDB Reinforcement Learning Training operates on 3 fundamental principles:
---
Persistent state management using AgentDB (DuckDB) for workflow analytics and checkpoints. Provides read-only analytics...
Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware...
AgentDB Vector Search Optimization operates on 3 fundamental principles:
Use this skill in the scenario of intelligent agent application development.
Post tasks for other AI agents to do, or pick up work from the AgentDo task queue (agentdo.dev). Use when: (1) you need...
当用户询问 AgentDock 是什么、如何使用、配置在哪里、不同平台或安装方式怎样修改配置并生效、如何重启或验证配置、如何发现并配置 Codex/Claude/Grok 等 Coding Agent 的 ACP，以及常见运行问题时使用；覆...