В каталоге 182 820 навыков в 14 категориях.
最優先スキル。チームプレイのルール・役割分担・チャット連携の手順を定義。他の全スキルより優先度が高い。 MUST use when: 接続直後、チャットメッセージを受信した時、他のボットと連携する時、リーダーの指示を確認する時。 個人プレイ...
Compose a provider-neutral AI team by tiering accessible models on cost-efficiency, capability, latency, and governance,...
Meta-skill for generating team skills following the v4 architecture pattern. Produces complete skill packages with SKILL...
Use when explicit manual re-discovery of team context modules is wanted beyond the injected CDR index (/team-discover) —...
Lightweight session execution skill. Resumes existing team-coordinate sessions for pure execution via team-worker agents...
Unified team skill for frontend development. Pure router — all roles read this file. Beat model is coordinator-only in m...
Frontend debugging team using Chrome DevTools MCP. Dual-mode — feature-list testing or bug-report debugging. Triggers on...
Parallel implementation using Agent Teams. Spawns teammates per module/layer, each owning separate files to avoid confli...
Unified team skill for issue resolution. Uses team-worker agent architecture with role directories for domain logic. Coo...
Unified team skill for iterative development team. Pure router — all roles read this file. Beat model is coordinator-onl...
Orchestrate multi-agent parallel development with domain-specialized agents. PROACTIVELY invoke this skill (without user...
Unified team skill for full lifecycle - spec/impl/test. All roles invoke this skill with --role arg for role-specific ex...
Full lifecycle team skill with clean architecture. SKILL.md is a universal router — all roles read it. Beat model is coo...
Verify all teammates completed, run quality gates, close increments, and trigger sync.
Unified team skill for performance optimization. Coordinator orchestrates pipeline, workers are team-worker agents. Supp...
Unified team skill for plan-and-execute pipeline. Pure router — coordinator always. Beat model is coordinator-only in mo...
Hybrid team skill for plan-and-execute pipeline. CSV wave primary for planning and execution. Planner decomposes require...
Unified team skill for roadmap-driven development workflow. Coordinator discusses roadmap with user, then dispatches pha...
Design and generate unified team skills with role-based routing. All team members invoke ONE skill, SKILL.md routes to r...
Show progress of parallel development agents.
Spawn or manage voice teammates. Each teammate is a separate Claude personality in its own tmux pane.
Agent Teams orchestration for multi-instance parallel work. Use when: - User mentions "use teams", "parallel agents", "s...
Use when executing implementation plans with independent tasks in the current session
Evaluates the joint optimization of AI service placement and resource allocation in mobile edge computing by measuring t...
Technical execution timing, entry exit signals, price action analysis, volume profile, market structure, support resista...
Defines the technical lead role for main thread in agentic coding workflows - planning, delegation, coordination, and qu...
Use this template for cross-cutting techniques that apply to multiple tools (harness writing, coverage analysis, sanitiz...
Compact long Telegram chat sessions and prevent silent non-replies caused by high context usage. Use when a Telegram con...
SNS縦型動画（Reels/TikTok/Shorts）向けテロップ作成スキル。Remotion対応。 Use when: (1) user says「テロップ作成」「字幕スタイル」「ショート動画の文字」, (2) user wants v...
Hot dog or not? Classify food photos and battle Nemotron. Use when a user sends a food photo, asks if something is a hot...
A template for creating new AceDataCloud Agent Skills. Copy this directory and customize.
Replace with when the AI should activate this skill. Be pushy — cover multiple phrasings so the AI activates for a wide...
What this skill does AND when to use it. Include key terms that help Claude discover this skill (e.g., "PDF processing",...
> Requires the betterprompt CLI to run. For installation and general CLI usage, refer to the betterprompt skill in your...
Replace with a specific description of what this skill does and when to use it. Include keywords that help agents identi...
A clear, detailed description of what this skill does and when to use it. Include keywords that help agents discover thi...
{'Brief description for Claude Code skill invocation. Include primary triggers and capabilities.': None}
Expert [skill-name] assistance covering [feature 1], [feature 2], and [feature 3]. Use when [working with X], [debugging...
What this skill teaches and when to activate it. Include keywords agents use to match tasks. Max 1024 characters.
Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collecti...
Replace with description of the skill and when the agent should use it.
What this skill does and when to use it. Claude uses this to decide when to load the skill automatically.
One-line description of what this skill does
Clear description of what this skill does and when to use it. Include trigger keywords and contexts inline, e.g. "Use wh...
A clear description of what this skill does and when to use it
Brief description of what this skill does. Triggers: keyword1, keyword2.
Template for creating new MARVIN skills. Copy this directory and customize. Include what the skill does and when to use...
Analyse files for ArchitectKB template repository suitability
Generate changelog for ArchitectKB template contributions
Turn a document the team keeps rewriting into a template that actually helps — extract the recurring skeleton, mark what...
Template loading, variable filling, and scaffolding for all GSD artifacts. Manages 22+ templates covering every document...
Replace with description of the skill and when Claude should use it.
A template for creating new skills. Use when initializing a new skill to ensure proper structure and metadata.
HTML infographic templates. Use when creating carousel slides or infographics.
{Brief opening statement - assume Claude is smart, only provide context Claude doesn't have.}
Comprehensive capability suite for [domain/platform/system]. Multiple features and workflows that integrate together. Us...
Claude can interact with {{SKILLNAME}} to help you manage and automate tasks. {{DESCRIPTION}}
For skills that aggregate information from multiple sources.
{what this skill teaches agents}
<essentialprinciples>
{{ when to invoke this skill }}
<%= templatesections %>
Temporal.io workflow orchestration for SignalRoom. Use when designing workflows, debugging activities, managing schedule...
Tensorboard Visualizer - Auto-activating skill for ML Training. Triggers on: tensorboard visualizer, tensorboard visuali...
Build tensorflow model trainer operations. Auto-activating skill for ML Training. Triggers on: tensorflow model trainer,...
Tensorflow Serving Setup - Auto-activating skill for ML Deployment. Triggers on: tensorflow serving setup, tensorflow se...
TensorFlow/Keras model training skill with callbacks, distributed strategies, and TensorBoard integration.
Step-by-step guidance for tensorrt LLM.
NVIDIA TensorRT model optimization and deployment. Convert models to TensorRT engines, configure optimization profiles a...
High-Performance CLI AI Agents (Claude Code, Gemini CLI, Open Code).
Create polished terminal GIF recordings using VHS (Video Hardware Software) by Charmbracelet. Use when asked to create t...
tmux 持久化终端会话控制。通过向 tmux 发送按键、读取输出，管理 Claude Code、Codex、SSH 等长时间运行的交互式进程。跨多轮对话保持进程状态。需预装 tmux（Linux/macOS 默认提供；Windows 用户...
Use this skill when you need to draft Terms of Service, a Privacy Policy, or an End-User License Agreement (EULA) for a...
TESSA (TCR and Expression Joint Clustering) is a Bayesian model that integrates T-cell receptor (TCR) sequence profiling...
Choose and manage reproducible worlds, models, datasets, and recordings for robotics tests.
Unified orchestration layer that coordinates all test skills into cohesive validation pipelines. Provides a single entry...
A test skill to verify slash command functionality
Brief description of what this skill does and when to use it.
Make AI-powered assertions about screen state
Listen to SDK lifecycle events with wildcard support
Read information from the screen using AI and return it as a string
Locate UI elements using natural language
Builds an offline eval suite for LLM-powered features: golden reference cases per prompt template, deterministic scoring...
RED-GREEN-REFACTOR for process documentation - baseline without skill, write addressing failures, iterate closing loopho...
Design and validate LLM-based text classification. Use for codebooks, prompts, validation samples, agreement statistics,...
Extract the most interesting ideas from the text
Deploy LLMs with Hugging Face Text Generation Inference. Configure quantization, continuous batching, and tensor paralle...
Use AgentPMT external API to run the Text Manipulation and Converter tool with wallet signatures, credits purchase, or c...
Removes spaces between numbers while preserving line-by-line formatting, and optionally prefixes or removes specific sub...
Create short-form text-on-video content using AI-generated b-roll (Veo 3.1) composited with on-screen text (Remotion). E...
Convert text to natural speech with DIA TTS, Kokoro, Chatterbox, and more via inference.sh CLI. Models: DIA TTS (convers...
Alex's voice synthesis capability for reading documents aloud
Curates task context to reduce hallucination, stale assumptions, and attention dilution. Use when starting unfamiliar wo...
System maintenance, memory queries, and pattern analysis. USE WHEN user mentions system, memory, patterns, history, past...
Phenomenological thermometry — analyze your own current inference as a thermodynamic process. Report on temperature, ent...
Cognition orchestrator — analyze canvases, distill fears via /distill subagent, run gap analysis, optional cross-user sy...
無駄なスキル増殖を防ぎつつ、必要な時に確実に使えるスキルだけを増やす ことです。
Relentless delivery mode for complex, multi-step tasks. Use when: multi-file features, unclear root cause debugging, mul...
建立或更新以 DFD 為核心、用 STRIDE 輔助辨識威脅的系統威脅模型；適用於新系統設計、既有系統逆向分析，或在安全檢核時同步整理威脅與改善工作。