Loading...
Loading...
Found 1,204 Skills
Control and automate real browser sessions through CDP, preserving login state and cookies for LLM-driven interactions
Initialize, diagnose, or migrate a project into the LLM wiki pattern with AGENTS/CLAUDE instructions, QMD MCP wiring, Claude/Codex/OpenCode hooks/plugins, guardrails, and QMD doctor checks. Use when the user asks to set up wiki infrastructure, check if a project needs migration, install wiki hooks, or validate QMD.
Serve a quantized or unquantized LLM checkpoint as an OpenAI-compatible API endpoint using vLLM, SGLang, or TRT-LLM. Use when user says "deploy model", "serve model", "start vLLM server", "launch SGLang", "TRT-LLM deploy", "AutoDeploy", "benchmark throughput", "serve checkpoint", or needs an inference endpoint from a HuggingFace or ModelOpt-quantized checkpoint. Do NOT use for quantizing models (use ptq) or evaluating accuracy (use evaluation).
OpenClaw Chinese localized AI assistant platform with CLI, dashboard, multi-platform chat integration (WhatsApp/Telegram/Discord), and LLM provider support
Deploy and operate SecurityClaw, an autonomous SOC agent with RAG-based threat detection, LLM-powered anomaly analysis, and skill-based security automation
Firecrawl v2.5 API for web scraping/crawling to LLM-ready markdown. Use for site extraction, dynamic content, or encountering JavaScript rendering, bot detection, content loading errors.
Cloudflare Workers AI for serverless GPU inference. Use for LLMs, text/image generation, embeddings, or encountering AI_ERROR, rate limits, token exceeded errors.
Answer ZenMux questions by reading the latest official docs. Use for product features, APIs, integration, pricing, models/providers, routing, fallback, streaming, multimodal, structured output, tool calling, reasoning, prompt caching, image/video generation, web search, long context, observability, logs, cost tracking, subscriptions, PAYG, invoices, FAQ, privacy, terms, compliance, and tool guides for Claude Code, Cursor, Cline, Codex, Gemini CLI, opencode, Cherry Studio, Obsidian, Sider, Open-WebUI, Dify, and GitHub Copilot. Trigger on "ZenMux docs", "ZenMux API", "how to use ZenMux", "models", "pricing", "ZenMux 怎么用", "文档", "快速开始", "API 参考", "模型路由", "供应商路由", "订阅", "按量计费", "接入", "配置". Also use when ZenMux is the project context and the user asks about LLM API aggregation, model routing, or provider fallback.
Inspect LLM torch profiler traces at forward-pass, layer, and kernel level. Use when you need layer timings, anchor-kernel boundaries, representative kernel flows, or Perfetto time ranges.
Eight-axis judgment code review for the current diff — Correctness, Simplification, Tests, Documentation, Style, Intent, Design/API, Performance (+ Coherence on metadata changes). Five-phase pipeline scope → deterministic tool battery (npx/uvx-preferred, zero-install for the JS + Python majority) → 8 parallel LLM axis reviewers → Haiku validators on sub-80 findings (verbatim rubric, ≥80 threshold) → synthesis with no-silent-drop + Conventional Comments JSONL. Every report closes with "What I did NOT check" (security → /security-review, runtime perf, flaky detection). Opt-in flags `--verify-build`, `--mutation-test`, `--reconcile`, `--apply-safe`. Public-skill posture — zero auto-install, graceful skip on missing native tools.
Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.
Human-in-the-loop safety controls — approval routing via human, LLM judge, or auto-approve with guardrail overrides.