全部能力

Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO,…

Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet…

Work with Dynatrace notebooks - create, modify, query, and analyze notebook JSON. Derives from the dt-app-dashboards skill with notebook-specific differences…

Build and run evaluators for AI/LLM applications using Phoenix.

Create and manipulate PowerPoint PPTX files programmatically. Use when the user needs to generate presentations, modify PPTX templates, extract slide content,…

Convert HTML and Markdown content into Portable Text blocks for Sanity. Use when migrating content from legacy CMSs, importing HTML or Markdown into Sanity,…

Coordinates multi-session, delegated, or long-running work with persistent state, recovery checks, and explicit status transitions. Use when a task spans…

Implement, review, or improve photo picking, camera capture, and media handling in iOS apps. Use when working with PhotosPicker, PHPickerViewController, camera…

此技能用于通过 AnkiConnect 与 Anki 进行交互，当用户要求与 Anki 交互时（包括读取或修改牌组等操作）应使用此技能。

NTLM relay and authentication coercion playbook. Use when capturing and relaying NTLM authentication to escalate privileges via SMB, LDAP, HTTP, or MSSQL relay targets, combined with PetitPotam, PrinterBug, and other coercion methods.

Guide users through configuring key MongoDB MCP server options. Use this skill when a user has the MongoDB MCP server installed but hasn't configured the…

Set up a repository for local GitHub Actions verification using act, so Jules can validate CI before pushing

Guide to using Ionic Framework components for beautiful native-looking Capacitor apps. Covers component usage, theming, platform-specific styling, and best…

terraform-diagrams — an installable skill for AI agents, published by eraserlabs/eraser-io.

Transcribe audio to text with ElevenLabs Scribe and Whisper models via inference.sh CLI. Models: ElevenLabs Scribe v2 (98%+ accuracy, diarization), Fast…

使用并行代理团队进行实现与审计循环，包含结构化的简化、加固和文档化阶段。生成实现代理执行工作，随后…

Remove backgrounds from images with BiRefNet via inference.sh CLI. Model: BiRefNet (high accuracy background removal). Use for: product photos, portraits,…

Generate images with FLUX models (Black Forest Labs) via inference.sh CLI. Models: FLUX Dev LoRA, FLUX.2 Klein LoRA with custom style adaptation. Capabilities:…

Microsoft/Bing Ads 深度分析，涵盖搜索广告、Performance Max、受众网络和 Copilot 集成。评估 24 项检查，重点关注 Google 导入…

playwright-recording — an installable skill for AI agents, published by digitalsamba/claude-code-video-toolkit.