В каталоге 182 820 навыков в 14 категориях.
Show available BMAD commands, agents, and workflows
Interactive workspace discovery - learn what tools, workflows, agents, and hooks are available
Control Herdr, a terminal multiplexer for coding agents. Use proactively for pane-based delegation, parallel work, and t...
Heretic — automatic censorship removal (abliteration) for local LLMs via transformer weight manipulation. Removes refusa...
Ingest Hermes agent history into the Obsidian wiki. Use this skill when the user wants to mine their past Hermes session...
Use when repeated delivery failures, disputed acceptance, weak evidence patterns, owner-routing mistakes, or trial obser...
Diagnose Hermes `hermes skills list` source labels (`builtin` vs `local`) and avoid false sync decisions.
Safe referencing of real people's traditions without impersonation
Generate persistent, named perspectives custom-built for a specific project or inquiry. Each heteronym is a sustained di...
Automate AI video generation, avatar browsing, template-based video creation, and video status tracking through HeyGen's...
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Lea...
Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Huggin...
Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, impo...
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets...
Scoped CLAUDE.md memory system that reduces context token spend. Creates directory-level context files, tracks savings v...
Hierarchical memory architecture combining short-term, long-term, and episodic memory layers. Based on Mem0 research sho...
Apple HIG guidance for Apple technology integrations: Siri, Apple Pay, HealthKit, HomeKit, ARKit, machine learning, gene...
ALWAYS apply these hints automatically in your responses. No need to invoke this skill - just follow its rules when your...
Background memory organ for AI agents. Runs separately from the main agent—encoding, decaying, and reinforcing memories...
Align RNA-seq reads with HISAT2, a memory-efficient splice-aware aligner. Use when STAR's memory requirements are too hi...
Digital pathology image processing toolkit for whole slide images (WSI). Use this skill when working with histopathology...
Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, sta...
Build comprehensive histone mark maps by aggregating narrowPeak data across multiple ENCODE experiments, donors, and lab...
Multi-step workflow for human approval integration in ccswarm agent operations.
Complete workflow for building, implementing, and testing goal-driven agents. Orchestrates hive-* skills. Use when start...
Core concepts for goal-driven agents - architecture, node types (event_loop, function), tool discovery, and workflow ove...
Step-by-step guide for building goal-driven agents. Qualifies use cases first (the good, bad, and ugly), then creates pa...
Set up and install credentials for an agent. Detects missing credentials from agent config, collects them from the user,...
Interactive debugging companion for Hive agents - identifies runtime issues and proposes solutions
The official technical stack for achieving "Best in World" concurrency and parallelism in the Sovereign Hive.
Best practices, patterns, and examples for building goal-driven agents. Includes client-facing interaction, feedback edg...
Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling i...
Neo4j-backed MCP server providing a shared consensus-aware knowledge graph for multi-model AI coordination. Acts as the...
Hızır'ın kullanım kılavuzu. Tüm komutlar, agent'lar, workflow'lar, sistemler burada. /hizir yaz, her şeyi gör.
Add content to Hole Island - a new edible item (catalog row + procedural builder + tests + lineup check) or a whole new...
This prompt directs an image-generation system to create an ultra-realistic indoor scene where the subject views an elec...
Home lab AI — turn your spare machines into a local AI home lab cluster. LLM inference, image generation, speech-to-text...
Framework architecture map for The Homie. Use when an agent needs to understand the framework's vertical slice structure...
Graceful memory compression with integrity — summarize before forgetting, never fabricate
Guide creating Claude Code hooks with security-first design. Use for validation, logging, and policy enforcement.
This skill should be used when the user asks to "create a hook", "write hook config", "add hooks.json", "configure event...
创建和配置 Claude Code 钩子以自定义代理行为。当用户需要以下操作时使用：(1) 创建新钩子，(2) 配置自动格式化、日志记录或通知，(3) 添加文件保护或自定义权限，(4) 设置工具执行前后的操作，(5) 询问钩子事件如 Pre...
Use when creating, modifying, or debugging Claude Code hooks — PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart...
Diagnose Claude Code hook installation, delivery, and ingestion issues. Checks hook configuration, connectivity, event f...
Design hook-based event systems for ADW observability. Use when implementing real-time event broadcasting, creating hook...
Claude Code 훅 사용 패턴과 작성 표준
Pull-based work assignment channel implementing GUPP (Get Up and Push Protocol). Manages single-active-work-item hooks p...
Generate hook script from template
Hook Development Rules
Claude Code の Hook 作成・管理ガイド。
Author AgentOps runtime hooks.
Use to draft non-clinical internal hospital documents, announcements, requests, reports, FAQs, training invitations, sur...
This skill should be used when the user asks to "build background agent", "create hosted coding agent", "set up sandboxe...
Build hosted agents using Azure AI Projects SDK with ImageBasedHostedAgentDefinition. Use when creating container-based...
Use when the user has a spicy or risky draft and wants a second opinion before publishing — returns a verdict (SHIP IT /...
Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user as...
Builds a 12-month HR Calendar with an owner and lead time per item, statutory and reporting dates marked to confirm with...
---name: hrd-analysis-agent
Create or explain fixed-format HSB FPGA_top.sv wrappers from validated HOLOLINK_def.svh files. Do not use for def genera...
Use when generating branded HTML pages and components from a design system. Creates standalone HTML components and compo...
Generate HTML-based presentations with reveal.js or similar frameworks. Use when creating web-based presentations.
Generate an interactive single-file HTML visualization (mockup, wireframe, ERD, flowchart, chart, slides, architecture d...
GPT-image-2 的 prompt 工程方法论，**公众号配图的唯一入口**。任何 AI 生图任务（封面 banner、海报、信息图、UI mockup、产品包装、slides、批量 icon/角色/卡牌、中文书法对联、视频参考板）的...
自动识别Prompt类型并分类保存（技术/内容/教学/产品/通用）。当用户提到"保存prompt"、"记录prompt"、"整理prompt"时使用。
演讲与分享教练。基于Patrick Winston（MIT AI教授）的How to Speak方法论，帮助准备线下培训、技术分享、B站教程视频等演讲场景。当用户提到"演讲"、"分享"、"培训"、"讲课"、"PPT演讲"、"开场"、"结尾"...
基于MrBeast策略检查视频标题、封面和开头钩子。当用户提到"视频标题"、"封面图"、"点击率"、"CTR"、"观看时长"时使用。
为微信公众号文章生成高质量配图。支持封面图（2.35:1）、正文插图（16:9/4:3）、信息图。提供两条路径：AI生成（视觉创意型）和HTML渲染（文字精确型）。当用户提到"公众号配图"、"公众号封面"、"文章配图"、"正文插图"、"公众...
微信读书高阶顾问。在底层 weread skill 的原子 API 之上，提供四类工作流：基于已读做个性化进阶推荐（advisor）、给方向规划入门到前沿的阶梯书单（path）、把零散划线想法提炼成读书笔记总结（alchemy）、做季度/年...
Orchestrate a multi-agent collaboration demo on the Thoughtbox Hub. Spawns MANAGER, ARCHITECT, and DEBUGGER agents that...
Use when routing user prompts to the right skill or agent. Senses git state, detects platform, classifies intent, and ap...
**Memory Infrastructure for Autonomous Agents**. Use when the user needs hub1 functionality.
Execute Hugging Face Hub operations using the `hf` CLI. Use when the user needs to download models/datasets/spaces, uplo...
Execute Hugging Face Hub operations using the hf CLI. Covers authentication, downloading models and datasets, uploading...
Use the Hugging Face Hub CLI (`hf`) to download, upload, and manage models, datasets, and Spaces.
Run local evaluations for Hugging Face Hub models with inspect-ai or lighteval.
Train or fine-tune TRL language models on Hugging Face Jobs, including SFT, DPO, GRPO, and GGUF export.
Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API) or retri...
Train or fine-tune vision models on Hugging Face Jobs for detection, classification, and SAM or SAM2 segmentation.
Use when the user is doing AI/ML work in a scientific domain — biology, chemistry, physics, astronomy, climate, genomics...
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports...
Use Hugging Face Transformers for local model inference, embeddings, and fine-tuning. Covers pipelines, model selection,...
Convert any song into a persona's humming voice. Downloads audio, stems vocals,
Human-in-the-Loop (HITL) workflows integrate human judgment into AI systems, ensuring that critical decisions receive hu...
GPU-accelerated pipeline for detecting, tracking, and classifying humans in dashcam footage. This skill should be used w...
Designs human-in-the-loop review points for DAG workflows. Determines what to present to the human, how to collect feedb...
去除 NSFC 标书中的 AI 机器味，覆盖词语、句法、段落和章节层，尤其处理伪对立、工程协议腔、规格书式字段串、术语漂移、定义后连续否定排除项、边界声明过重和研究动作不清（不适用：非标书内容/需修改格式/需补充新内容）；兼容旧名 nsfc...
AI가 쓴 한글 텍스트를 자연스럽게 윤문하는 진입 명령. humanize-korean 파이프라인을 shim 의 route_hint 가 정한 경로(light 1콜 · standard 2콜 · heavy 3+콜)로 실행...
AI가 쓴 한글 텍스트를 자연스럽게 윤문하는 진입 명령. humanize-korean 파이프라인을 Fast 모드(기본)로 실행하고 `--strict`면 정밀 3콜(진단→겨냥 윤문→finalize). 트리거 — "/h...
Применять при переписывании текстов, сгенерированных LLM-агентами (отчеты, README, доки, письма, посты), в живой человеч...
将 AI 生成的文本人性化，使其听起来更自然、更像人类写的。用于编辑或审查文本时使用。可检测并修复以下 AI 写作模式：过度夸大的象征意义、促销性语言、肤浅的 -ing 分析、模糊的归因、破折号过度使用、三段式结构、AI 词汇、否定平行结构...
Strip AI-generated tells from a draft and rewrite it in your own voice. Fire on "humanize this", "de-AI this", "clean up...
가장 최근 윤문 결과를 2차로 다시 다듬는다 — 특정 카테고리·문단·강도 조정도 가능. humanize-korean strict 윤문(Phase B)을 기존 run_id에 재실행해 잔존 finding을 처리한다. 트...
한글 글에 AI 티가 얼마나 있는지 재고, 실제로 고치면 어떻게 되는지 표본으로 보여주는 정찰 스킬. 실측 판별력 상위 6개만 본다. 워크스페이스·진단·게이트·서브에이전트 없이 이 대화 안에서 끝낸다(파일 0개, 서...