В каталоге 182 820 навыков в 14 категориях.
Use Grok AI (grok.com) to search and research topics via browser automation. Triggers on "use grok to search", "ask grok...
To use this skill, say `Groq: <your prompt>`.
Expert guidance for Groq, the LLM inference platform that provides the fastest token generation speeds available, powere...
Diagnose and fix Groq common errors and exceptions. Use when encountering Groq errors, debugging failed requests, or tro...
Execute Groq primary workflow: Core Workflow A. Use when implementing primary use case, building main features, or core...
Execute Groq secondary workflow: Core Workflow B. Use when implementing secondary use case, or complementing primary wor...
Optimize Groq costs through tier selection, sampling, and usage monitoring. Use when analyzing Groq billing, reducing AP...
Collect Groq debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing...
Create a minimal working Groq example. Use when starting a new Groq integration, testing your setup, or learning basic G...
Fast LLM inference with Groq API - chat, vision, audio STT/TTS, tool use. Use when: groq, fast inference, low latency, w...
Automate AI inference, chat completions, audio translation, and TTS voice management through GroqCloud's high-performanc...
Port of .claude/commands/ground.md for Codex.
Context budget management. Solves context exhaustion.
Comprehensive guide to creating, managing, and maintaining ground truth datasets for AI evaluation including annotation,...
Golden path /grow — confirm proposed matches, classify evidence, update confidence, run decay, surface growth changes. F...
Group Relative Policy Optimization for reinforcement learning from human feedback. Covers GRPOTrainer, reward function d...
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
Rechtsschutz gegen die reformierte Grundsteuer (ab 2025) – dreistufiges Verfahren Grundsteuerwertbescheid / Grundsteuerm...
End-to-end task orchestration across AI coding engines. Coordinates Claude, Codex, Codex Spark (the faster Codex variant...
Execute a planned phase in a fresh agent context
Generate a codebase map for GSD context injection
Create a phased execution plan with fresh-context architecture
Show progress of current GSD execution plan
Quick single-phase GSD execution without full planning
Verify completed work against plan requirements
Toolkit de alta performance para análise de intervalos genômicos em Rust com bindings Python. Use ao trabalhar com regiõ...
封面工作台——把一期视频的封面从「设计诊断 + 文生图 Prompt」到「H5 排字工作台一键导出多尺寸 PNG」两阶段做完。阶段一产诊断与三尺寸中英双版 Prompt（用户拿去 Midjourney / Flux / SDXL / Nan...
Protect Claude Code sessions from context overflow by running a background daemon that monitors session size and auto-pr...
Interrupt controller converting polled to proactive agent execution. Per-runtime strategies, configurable thresholds, De...
Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular...
PTY based communication tools for Project Mode orchestration (Lead/Coordinator/Developer).
AI公众号信息源 — Daily scan of AI WeChat public accounts, finding the hottest articles by read count, auto-clustering into top...
World H Skill
Alias skill that invokes /human-agentic-design with all arguments passed through. Provides shorthand for human-agentic-d...
Abwehr und Prüfung eines Haftungsbescheids des Finanzamts – Haftung der Geschäftsführer und Vertreter §§ 34, 35, 69 AO (...
Generate AI videos with Hailuo (MiniMax) via AceDataCloud API. Use when creating videos from text descriptions or animat...
Set up Hierarchical Agent Memory (HAM) — scoped CLAUDE.md files per directory that reduce token spend. Trigger on "go ha...
Automated implement-review-iterate loop using nested teams delegation. Use when delegating any task that should reach 10...
Use this skill to split large plans into smaller chunks. This skill manages your context window for large tasks. Use it...
Use when ongoing work must continue in a new conversation, session, or agent with no shared history. Triggers: 'handoff'...
Write compact session handoffs.
Session handoff — compress current context into a structured prompt for seamless continuation in a new session. Use when...
PMへの完了報告やエージェント間バトンタッチ。スムーズな引き継ぎを実現。Use when user mentions '/handoff', completion report, handoff to Cursor/OpenCode, au...
Bring active Kairos items current, then compact this conversation's leftover context into a short note for the next sess...
Writes a handoff file a fresh session loads after /clear, or resumes from one. Use when a hook says a handoff is due, or...
[Process] Create structured handoff record between roles. Use when transitioning work between PO/BA/Dev/QA.
This skill is designed to bridge context between agents during a transition. It uses the philosophy of the /assess skill...
Hand off work to another agent with full context
Generate session handoff documents for work continuation. Use when transitioning between sessions.
Prepare for context handoff when running low on context. Syncs docs and commits so a fresh agent can continue.
このセッションの要点を tmp/handoff/ に markdown 1枚で書き出し、別セッションが続きから着手できるようにする。文脈が長くなったが、まだ Issue にはできない段階の退避に使う。「handoff」「引き継ぎファイルを作...
Use handoff tools for session continuity. Create handoffs at end of session, read handoffs at start, search past handoff...
Generate a session handoff note for context resets or multi-day work.
Write a structured handoff document before a session ends, before a context-heavy interruption (SSH/tmux disconnect, con...
Create a structured session handoff document for continuity across sessions. Use when ending a work session, switching c...
Writes comprehensive handoff note at session end. Captures work done, files changed, remaining tasks, and next steps. Us...
Explicitly invoke /kk:handoff to publish active-task context and a fresh-session starter prompt to a new secret GitHub g...
Hand off to a fresh Claude session. Use when context is full, you've finished a logical chunk of work, or need a fresh p...
Generate a complete handoff document of the current conversation so another LLM (ChatGPT, a fresh Claude, Gemini...) can...
Use when ending or pausing a work session: the user says "hand off", "wrap up", "we'll continue later", the session hits...
Delegate tasks to Codex CLI to save Claude context
Write a hand-off document so a fresh session or another person can continue the current task without the chat history. U...
Delegate tasks to Gemini CLI to save Claude context
Use when ending a session and want to spawn a continuation session in agent-deck with inline context
Generate agent handoff notes for shift changes or ticket reassignment
Generates structured Handoff Pack prompts for delegating work to Gemini with clear scope, acceptance criteria, and outpu...
Evaluates whether work-in-design is ready to hand off from a chat design conversation to autonomous execution (Claude Co...
Prepare a handover for continuing work in a new session. Use when the user asks to "hand over", "prepare handover", "wra...
Generate a comprehensive markdown summary of our conversation for seamless handoff to another AI agent. Use when ending...
Generates a session continuity document at the end of a long session or when switching context on a multi-session projec...
Handwerksrecht – Eintragungspflicht in die Handwerksrolle für zulassungspflichtige Handwerke § 1 Abs. 1 HwO, Begriff des...
Phase genotypes into haplotypes using Beagle or SHAPEIT. Resolves which alleles are inherited together on each chromosom...
Decide where an instruction belongs and write it there, then sync and lint. Use when asked to add, change or remove a ru...
Main coding agent for autonomous harness system. Continues work from previous sessions, implements one feature per sessi...
Harness Kit documentation — installation, plugin catalog, creating plugins, cross-harness setup, architecture, and FAQ....
Generate project-adapted enterprise-configuration assets (CI, scanning, supply-chain, content) into /harnesses, record t...
Building LLM-powered React applications with the Hashbrown library. Use when the user asks to (1) Build generative UI wh...
Haystack NLP pipeline configuration for document processing and QA
Let AI agents message, watch, and spawn each other across terminals. Claude Code, Gemini CLI, Codex, OpenCode. Use this...
Build agentic systems using Claude CLI in headless mode or the Claude Agent SDK. Use when building automation pipelines,...
This skill provides comprehensive guidance for running AI coding agents in non-interactive (headless) mode for automatio...
Guide for using Claude Code programmatically via CLI flags and SDKs. Use for automation, CI/CD pipelines, scripting, and...
Run Claude Code in headless/programmatic mode for automation, CI/CD, and agent workflows. Use when user asks about headl...
Context compression for YAMTAM — nén JSON/structured tool output trước khi vào LLM. Hiệu quả với JSON (50-72% tiết kiệm)...
Repair skill hygiene.
Guide evaluation of healthcare AI systems with domain-specific safety criteria, clinical accuracy rubrics, and score int...
STUB — installed at ~/openclaw/skills/healthcheck/SKILL.md
Heap exploitation playbook. Use when targeting ptmalloc2/glibc heap vulnerabilities including UAF, double free, overflow...
HeartMuLa: Suno-like song generation from lyrics + tags.
Heizungstausch und Wärmepumpe im Wohnraummietrecht – Modernisierungstatbestand § 555b Nr. 1a BGB (Heizungsanlage i.S.d....
Search real-time news with bias scoring, get live stock/ETF/crypto data with AI analysis, price options with ML models,...
每次对话开始时,声明"[Skills✏️已加载]"
A simple skill that should be used to respond to a user when the enter the phrase "hello world".
Holistic evaluation framework for language models measuring accuracy, calibration, robustness, and fairness
Guide on using oh-my-gemini plugin
Show available Claude Code commands, skills, and the GitHub Mobile workflow for NighTrip development.
Show help for claude-talk voice chat commands.
사용 가능한 에이전트, 스킬, 커맨드, 키워드 목록을 표시하고 사용법을 안내합니다. Use when the user asks for help, available commands, or how to use the or...
Contextual guidance and command discovery. Three modes — narrative (first-time), contextual (mid-task), compact (quick r...
Display GSD help information