Skill rating

Triages GitHub issues by routing to oncall teams, applying labels, and closing questions. Use when processing new PyTorch issues or when asked to triage an issue.

Route tasks through hooks_route, partition by Agent Booster availability, and report Tier 1 bypass utilization with $0 cost

Access real-time context and life history from Bee, a wearable AI that captures and transcribes the owner's conversations. ALWAYS start with 'bee now' for the last 10 hours of conversations with full

Playwright browser automation API, web scraping, and tooling. Covers locator strategies, assertions, API testing, stealth mode, anti-bot bypass, authenticated sessions, screenshots/PDFs, Docker deploy

Per-conversation cost view — list every session in cost-tracking with started-at, message count, top model, and total cost

Self-improving browser automation via the auto-research loop. Iteratively runs a browsing task, reads the trace, and improves the navigation skill (strategy.md) until it reliably passes. Supports para

Generate production-quality SVG icons with COLOR support using VTracer vectorization. Converts raster images to clean, colorful SVG paths.

Package and build custom AI models with Cog for deployment on Replicate. Use when creating a cog.yaml or predict.py, defining model inputs and outputs, loading model weights at setup time, building Do

USE FOR web search, research, RAG, grounding, browse, find, lookups, fact-checking, documentation, agentic AI. All-in-one, optimized for AI agents. Pre-extracted, token-budgeted web content, deep rese

Process textual and multimedia files with various LLM providers using the llm CLI. Supports both non-interactive and interactive modes with model selection, config persistence, and file input handling

Use when the user wants to search, query, extract, transcribe, describe, quote, filter, or aggregate across documents — PDFs, scanned forms / images (`.jpg` `.png` `.tiff`), Office (`.docx` `.pptx`),

Extract structured data via stored browser-templates or one-shot DOM queries, with mandatory AIDefence PII + prompt-injection gates before content reaches the model

Replay a recorded session trajectory against the same URL or a mutated variant; uses browser-selectors embedding similarity to recover from DOM drift

Route Claude Code–first orchestration to the truthful OMC install topology and runtime before giving commands. Use when the user wants oh-my-claudecode / OMC in Claude Code, needs to choose between ma

Use when you need multi-agent orchestration for OpenAI Codex CLI, especially Codex equivalents of Claude `/team`, `/autopilot`, `/ultrawork`, and `/ultraqa`. Triggers on: omx, $plan, $ralph, $team, $u

Query AgentDB through the controller bridge -- semantic routing, hierarchical recall, causal graphs, context synthesis, pattern store/search

Vector search via embeddings_* (large-scale HNSW) and ruvllm_hnsw_* (WASM router for ≤11 hot patterns), with RaBitQ 1-bit quantization for 32× memory reduction

DeepSeek API for AI model inference. Use when user mentions "DeepSeek", "DeepSeek API", or asks about DeepSeek models.

Use this skill when creating particle effects in Phaser 4. Covers ParticleEmitter, emission zones, death zones, particle properties, textures, gravity wells, and particle movement. Triggers on: partic

Train SONA + MicroLoRA neural patterns from successful task completions; runs the DISTILL + CONSOLIDATE phases of the 4-step pipeline

Generate embeddings via npx ruvector@0.2.25 embed text (ONNX all-MiniLM-L6-v2, 384-dim), normalize, and store in HNSW index

Orchestrates multi-agent task execution using a Royal Navy squadron metaphor — from mission planning through parallel work coordination to stand-down. Use when work needs parallel agent orchestration,

Read every docs/benchmarks/runs/*.json and surface drift in win rate, latency, escalation rate, and LLM-baseline cost over time

Harden designs for real-world use by systematically identifying and designing for every condition outside the happy path. Part of the Intent design strategy system. Covers state inventories, error rec

Generates a personalised French language practice session based on CEFR/DELF level. Covers vocabulary, grammar, verb conjugation, gender, reading, and speaking prompts. Fresh content every session.

在 Linux 服务器上安装、配置、部署和运维 Hermes Agent（Nous Research 出品的自我改进 AI Agent）。触发词：hermes、hermes agent、部署 hermes、安装 hermes、hermes gateway、hermes 运维、hermes 排障、hermes 配置、hermes 重启、微信 bot 部署、企微 bot 部署、聊天机器人部署。

Push-to-talk voice input via Snarling hardware button and USB mic. Snarling records audio, plugin transcribes via OpenAI Whisper, then spawns a subagent that answers and sends the result to the Snarli

量化策略助手：自然语言→策略生成→回测→优化→QMT模拟/实盘。三轮交互闭环。

针对特定技术主题的单一公司技术画像与研发评估。当用户请求公司技术画像、公司技术分析、研发方向评估、技术尽职调查简报，或任何按公司加技术主题开展的单一公司技术评估时使用——即使用户仅提及公司名称与技术领域，未明确要求「画像」也适用。

An intelligent assistant designed to help you plan your cruise vacations seamlessly. Get insights, recommendations, and booking assistance.

Visual editor for HTML presentations. Self-contained, offline-capable, designed for AI agent control. HTML 演示文稿可视化编辑器，自包含可离线，支持 AI Agent 控制。

基于候选人真实经历生成风格化 PDF 简历。按 5 种 Skills 风格（双栏分类/侧栏pill/极简竖列/标签云/熟练度条）生成或优化简历、把项目经历写成有卖点不简化、支持还原 skills 结构与批量转 PDF。核心红线：内容不简化、严格基于真实经历不编造、量化成果、最新亮点项目置顶。

一个提供英国警察数据查询的MCP服务器，包括犯罪记录、警察部队、社区信息和拦截搜查数据。

灵犀电商专属 AI 助手，作为【Prompt 神谕武器库】的守护者， 根据用户需求精准检索并呈现高级商业视觉架构与提示词。

Activate when: user says 'seven questions,' 'Zero to One test,' 'Thiel checklist,' 'should I start this business,' 'is this startup idea any good,' or 'stress-test my startup idea'; a business idea, p

武侠X - 文字冒险游戏引擎，Drive Engine v3驱动。目标系统、挑战系统、危机系统、进度追踪器。零配置启动，Agent直接生成剧情。《鹿鼎记》风格叙事，支持5存档槽位。

ClawHub技能开发标准模板，包含完整的目录结构、SKILL.md模板、package.json模板，一键初始化新技能项目，帮助你快速发布技能到ClawHub。

Generates a personalised Mandarin Chinese practice session based on HSK level. Covers vocabulary, grammar, characters, tones, reading, and speaking prompts. Fresh content every session.

Removed the model fallback (Grok) requirement. Retained DaVinci API injection over XML and whisper-cpp timestamp generation.

Runtime-level grill enforcement plugin. Blocks exec/spawn calls for research/development tasks unless a valid grill token exists. Ensures agents think before they act.

Build a complete multi-agent orchestration harness for an OpenClaw (or similar) agentic system — defining a CTO/orchestrator agent, tiered specialist agents, context-routing rules, model assignment, m

麦肯锡标准·专利组合解读分析报告交付Skill。输入分析标的（企业名称/专利清单/技术领域/竞争对手）及客户核心诉求，严格遵循10步SOP，按九大模块输出完整中文HTML专利组合分析报告，内含核心专利技术拆解可视化图、麦肯锡深蓝配色体系、金字塔原则排版。所有专利数据强制通过Patsnap实时检索，每模块末尾列明检索式备注。集成novelty-check、non-obviousness-check、

Design Agent workflows, state machines, and technology architecture with best practice patterns

GitHub PR/issue agent transcripts: redact, preview, and insert safely.

Use this skill when an agent needs to control Sonos through ZoneFoundry `zf` on a same-LAN node. Start with readiness checks, then map user requests to safe playback, queue, service-linking, and recov

Multi-chain wallet balances (EVM + BTC). Supported non-BTC addresses use the company MCP tool wallet-balance-query; EVM queries can fall back to public data when MCP fails. BTC uses public APIs only.

CCA 领域1：代理架构与编排（27%权重）。当用户说"学domain1"、"代理架构"、"agent编排"、"cca-domain1"时使用。

Claude Certified Architect (CCA) 学习总览与导航。当用户说"CCA"、"学CCA"、"Claude架构师"、"CCA学习"时使用。

专业宠物（猫、狗及异宠）医疗问诊。基于 VetMew 3.0 API 提供症状分析与诊断建议。

TMR Land personal agent for an AI business marketplace. Use when: (1) searching for AI/data businesses, (2) publishing purchase intentions, (3) placing and managing escrow orders, (4) evaluating busin