transformers
Supports Hugging Face Hub model loading, pipeline inference, text generation, and Trainer fine-tuning. Covers AutoModel, tokenizers, pipelines, and TrainingArguments within the Transformers library.
Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Supports Hugging Face Hub model loading, pipeline inference, text generation, and Trainer fine-tuning. Covers AutoModel, tokenizers, pipelines, and TrainingArguments within the Transformers library.
Converts office documents, PDFs, HTML, spreadsheets, structured data, images, audio, ZIP archives, YouTube URLs, and EPubs into Markdown. Supports image OCR and audio transcription for LLM processing or text analysis.
Guides selection of SHAP explainers and maskers and computation and validation of feature attributions. Covers multi-output explanations and local or global visualizations.
Extracts, normalizes, and standardizes financial data from CIMs, offering memorandums, SEC filings, web searches, or MCP servers. Produces investment committee-ready Excel workbooks with consistent formatting and documented assumptions for due diligence, private equity analysis, and portfolio reporting.
Detects host inventory and effective CPU, memory, disk, scheduler, container, and accelerator limits. Produces redacted JSON snapshots and conservative planning helpers without stress testing or assuming all visible hardware is available.
Gstack provides a team of specialist AI workflows for Claude Code. They cover CEO review, engineering planning, code review, shipping, QA testing, and browser automation.
Uses Nano Banana Pro for infographic creation and Gemini 3.6 Flash for quality review. Integrates research and web search, with support for ten infographic types, eight industry styles, and colorblind-safe palettes.
Extract DEX files from a running Android application's memory, including decrypted DEX files. Supports APK unpacking, deobfuscation, and analysis of class-loading packing.
Covers dependency upgrades, component themes, styleable custom components, and migration of existing layout properties. Replaces hard-coded design system parameters with Style attributes and uses Modifier.styleable for interaction states.
Fine-tunes vision, vision-language, and language models in NGC PyTorch containers when no dedicated TAO skill applies. Covers inspection, research, smoke testing, training, evaluation, inference, Hub publishing, and generation of a reusable rerun skill.
Establishes version control practices for design assets, components, and libraries. Covers branching, naming, and releases to organize file history.
Provides .NET timezone guidance using TimeZoneInfo, DateTimeOffset, and NodaTime. Covers UTC conversion, daylight saving time, scheduling, Windows/IANA IDs, and location-based timezone lookup with ready-to-use C# code.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name