Каталог навыков агентов

Master controller for complete autonomous operation. Use when starting full autonomous projects, managing end-to-end wor...

Manage persistent memory for autonomous coding. Use when storing/retrieving knowledge, managing Graphiti integration, pe...

Coordinate parallel autonomous operations. Use when running parallel features, managing concurrent work, coordinating mu...

Analyze context and decide on continuation via Stop hook. Use when determining if work should continue, analyzing comple...

Use when a medical AI paper should be found and cited by AI search engines and RAG tools. Optimizes the title, abstract,...

Create, revise, or audit academic data/result figures for CS/AI/ML papers. Data/result plots default to Python-generated...

科研方法与论文发表 (Academic Research and Publishing) Master OS — automated mastery of Academic Research and Publishing: top buil...

Self-review, audit, or verify CS/AI/ML paper drafts as a critical peer reviewer. Three-round review (evidence→argument→s...

科研工作台统一入口。根据任务所处阶段（选题/文献/查新/数学验证/故事动机/实验矩阵/参数优化/绘图/写作/示意图/排版/三轮审查/去AI味）路由到对应技能，并执行阶段协议。触发词：科研工作台、research workbench、开始科研...

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/F...

Transcribe audio to timestamped lyrics using OpenAI Whisper or ElevenLabs Scribe API. Outputs LRC, SRT, or JSON with wor...

Use when the user wants to customize Claudikins Automatic Context Manager behavior, configure trigger threshold, snooze...

Use when resuming work from a previous session that reached context threshold, or when a handoff summary exists. Reads h...

Agent-actionable reference for ACM-AI's 6-tool observability stack. Teaches how to query traces, inspect graph state, de...

Route plain-language requests for Pi, Claude Code, Codex, OpenCode, Gemini CLI, or ACP harness work into either OpenClaw...

Use ACP as the trigger mechanism for agents to inspect and act on external context such as GitHub issues, PRs, and wiki...

Acceptance & Commitment Therapy (ACT) nach Steven Hayes: Hexaflex-Modell mit den sechs Kernprozessen psychischer Flexibi...

动作打戏 AI 视频提示词设计技能。当用户需要设计具备电影级运镜、节奏感、打击感的武打/战斗片段提示词时使用——覆盖双角色对打、女主 vs 怪兽、近身格斗、载具追逐战、群战、一镜到底、巨型生物/机甲大场面等场景。核心方法论：时序拆段（15...

Active Interleave Skill

Эксперт active learning. Используй для ML с участием человека, uncertainty sampling, annotation workflows и labeling opt...

Ada, your Executive Assistant. Runs planning and reflection rituals by coordinating domain assistants.

Act as the LLM variant proposer inside the Step-12 optimize-adapter loop: given the current adapter and the behaviour te...

Generate a cascading hint sequence for a problem type, revealing progressively without giving answers. Use when designin...

Hierarchical memory management for AI agents across sessions. Maintains three layers — daily notes (raw logs), active co...

Tier: Tier 0 (Meta-Generation Framework)

Add new Agent templates to the meta-agent-skills framework.

Add a new AI image model to myimageupscaler.com, including model costs, provider configuration, model registry, quality...

Use Codex (CLI + AppServer) as the full agent provider — planning, tool orchestration, native compaction, MCP tools, ses...

Add /compact command for manual context compaction. Solves context rot in long sessions by forwarding the SDK's built-in...

Guide for adding a new dataset loader to AReaL. Use when user wants to add a new dataset.

Add another phone number to an existing Dial channel — a second (or third) public line for the agent, so one NanoClaw in...

Curate and add documents to the golden dataset with multi-agent validation. Use when adding test data, creating golden d...

Add image vision to NanoClaw agents. Resizes and processes WhatsApp image attachments, then sends them to Claude as mult...

Add a persistent wiki knowledge base to a NanoClaw group. Based on Karpathy's LLM Wiki pattern. Triggers on "add wiki",...

Use this to add safety and security guardrails to an LLM/agent app - blocking prompt injection, PII leakage, jailbreaks,...

Add persistent graph-based memory via mnemon. Agents recall past context before responding and remember insights after e...

Checklist and automation guide for adding a new skill to the OPC Skills project. Ensures all required files, metadata, l...

Add Ollama MCP server so the container agent can call local models for cheaper/faster tasks like summarization, translat...

Add a Dimagi teammate to a Connect organization by email so they can see ACE's programs there. Use for @dimagi.com staff...

Guide for adding a new reward function to AReaL. Use when user wants to create a reward function.

Generate project-specific Claude Code skills from codebase patterns or framework best practices

Add an external skill from a GitHub repository to the current workspace. Use when users want to import, install, or add...

Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram cha...

Use when adding new multi-agent coordination patterns to agent-relay - provides checklist for types, schema, templates,...

ADHD-optimized code explainer. Generates layered, scannable explanations with hooks, maps, and progress markers.

a set of guidelines to build with Botpress's Agent Development Kit (ADK) - use these whenever you're tasked with buildin...

Adecuar un proyecto Python YA EXISTENTE (legacy o con motor viejo embebido) al motor portable, orquestando las skills y...

Discover ADR candidates across Specvital platform repositories with multi-agent collaboration

Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsi...

This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation ru...

Guides users through creating production-ready Claude skills via interactive dialogue. Use when user wants to build a ne...

Advanced patterns for creating complex, multi-step skills with error handling and state management.

Context-efficient tool management via search, deferred loading, and programmatic calling

Generative-adversarial coordination — locks a generator and critic agent in an escalating quality loop. The critic activ...

Adversarial auditor that red-teams technical plans, asserts fail-closed factual provenance, decomposes cognitive token s...

Committee of personas with opposing propensities forcing genuine debate

Esta skill deve ser usada para tarefas de machine learning em séries temporais, incluindo classificação, regressão, clus...

Agent Farm CLI quick reference. Use when running af commands to check correct syntax, subcommands, and flags. Prevents g...

Orchestrate AgentFlow's 4-phase development process with agent delegation patterns. Use when coordinating phase transiti...

Detailed orchestration workflows for coordinating AgentFlow's 4-phase development process. Load this skill for deep guid...

Present content visually via the Agentview canvas with markdown and diagrams. Use when rendering mermaid diagrams, table...

Recover work context after session restart, context compaction, or interruption. Use when resuming after a break, restor...

Guides creation of high-quality Agent Skills with domain expertise, anti-pattern detection, and progressive disclosure b...

The single dashboard for the active profile's semantic model — browse, curate, AND sign off the trust layer in one surfa...

Independent model QA expert who audits ML and statistical models end-to-end - from documentation review and data reconst...

Imported skill agent from langchain

Especialista en configuración de agentes de IA: templates, tools, models, prompts y seed data.

Agent skill for adaptive-coordinator - invoke with $agent-adaptive-coordinator

Agent skill for agentic-payments - invoke with $agent-agentic-payments

Expert en RAG agentique (retrieval multi-étapes, self-query, chunking adaptatif, tool-augmented generation)

Create, inspect, and safely update project-scoped ReachAI Agents; edit and publish Supervisor config drafts; discover pu...

Use when designing an autonomous agent, planning agent architecture, building a scheduled automation, or creating a Clau...

Agent assistance skill that provides stuck detection, memory management, and session learning capabilities for AI agents...

When reviewing, optimizing, or inheriting an LLM agent, systematically identify what's actually load-bearing vs. cruft....

Validates agent configurations for model selection, tool permissions, focus areas, and approach quality. Use when review...

机器学习与人工智能科研子 skill。用于地理学+体育学项目中的 classical ML、深度学习、时间序列、模型评估、数据泄露检查、基线设计、超参数搜索、SHAP/可解释 AI、公平性诊断、实验复现和论文方法写作。触发于 machine...

Agent skill for automation-smart-agent - invoke with $agent-automation-smart-agent

Create and manage Databricks Agent Bricks: Knowledge Assistants (KA) for document Q&A, Genie Spaces for SQL exploration,...

Browse the web for any task — research topics, read articles, interact with web apps, fill forms, take screenshots, extr...

Agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, na...

Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selectio...

Creates Claude Code agent files (.claude/agents/*.md) with YAML frontmatter, tool permissions, and system prompts. Use w...

Build custom AI agents in Claude Code from a user's problem statement. This skill analyzes the user's use case, asks sma...

Used to create a new agent. Used when a user wants to create a new agent

sofware para nesesidades de galeri

Use when evaluating, designing, or pressure-testing the business model of an AI agent product. Triggers on "agent busine...

Agent skill for byzantine-coordinator - invoke with $agent-byzantine-coordinator

Interactive element picker for web pages. Opens a browser with click-to-select UI overlay. Use when you need to let user...

Dependency checker and installer for agent-canvas, agent-eyes, and canvas-edit skills. Use BEFORE running any canvas ski...

Validate custom agent file format and structure

Use when mapping audit targets to appropriate config or domain agents. Analyzes file types, patterns, and content to det...

Chat with AI agents via the Agent Client Protocol directly from your vault.

Generates Agent definitions (.md files) based on user intent and standard templates.

Agent skill for code-goal-planner - invoke with $agent-code-goal-planner

Agent skill for code-review-swarm - invoke with $agent-code-review-swarm

Design effective collaboration between humans and AI agents where strengths combine and weaknesses complement. Use when...