Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
huggingface-gradio
Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.
huggingface/skills 10,029
-
transformers-js
Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in Node.js and browsers (with WebGPU/WASM) using pre-trained models from Hugging Face Hub.
huggingface/skills 10,029
-
huggingface-datasets
Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.
huggingface/skills 10,029
-
huggingface-community-evals
Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.
huggingface/skills 10,029
-
huggingface-trackio
Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, alerts with webhooks, HF Space syncing, and JSON output for automation.
huggingface/skills 10,029
-
huggingface-papers
Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user shares a Hugging Face paper page URL, an arXiv URL or ID, or asks to summarize, explain, or analyze an AI research paper.
huggingface/skills 10,029
-
hf-cli
Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging Face infrastructure; managing Hugging Face repos; discussions and pull requests; browsing models, datasets and spaces; reading, searching, or browsing academic papers; managing collections; querying datasets; configuring spaces; setting up webhooks; or deploying and managing HF Inference Endpoints. Make sure to use this skill whenever the user mentions 'hf', 'huggingface', 'Hugging Face', 'huggingface-cli', or 'hugging face cli', or wants to do anything related to the Hugging Face ecosystem and to AI and ML in general. Also use for cloud storage needs like training checkpoints, data pipelines, or agent traces. Use even if the user doesn't explicitly ask for a CLI command. Replaces the deprecated `huggingface-cli`.
huggingface/skills 10,029
-
huggingface-jobs
This skill should be used when users want to run any workload on Hugging Face Jobs infrastructure. Covers UV scripts, Docker-based jobs, hardware selection, cost estimation, authentication with tokens, secrets management, timeout configuration, and result persistence. Designed for general-purpose compute workloads including data processing, inference, experiments, batch jobs, and any Python-based tasks. Should be invoked for tasks involving cloud compute, GPU workloads, or when users mention running jobs on Hugging Face infrastructure without local setup.
huggingface/skills 10,029
-
omnicaptions-convert
Use when converting between caption formats (SRT, VTT, ASS, TTML, Gemini MD, etc.). Supports 30+ caption formats.
lattifai/omni-captions-skills 21
-
omnicaptions-translate
Use when translating captions/captions to another language. Supports bilingual output and context-aware translation. Default uses Claude native, Gemini API optional.
lattifai/omni-captions-skills 21
-
omnicaptions-transcribe
Use when transcribing audio/video to text with timestamps, speaker labels, and chapters. Supports YouTube URLs and local files. Produces structured markdown output.
lattifai/omni-captions-skills 21
-
omnicaptions-download
Use when downloading videos, audio, or captions from YouTube and other video platforms. Supports quality selection.
lattifai/omni-captions-skills 21
-
omnicaptions-LaiCut
Use when user needs accurate/precise caption timing, or aligning captions with audio/video using forced alignment. Corrects caption timing to match actual speech. Uses LattifAI Lattice-1 model.
lattifai/omni-captions-skills 21
-
ui-review
Review UI changes against Swiss International Style design system. Checks colors, typography, borders, shadows, spacing, and anti-patterns. Use before committing any frontend UI changes.
srbhr/Resume-Matcher 26,484
-
codebase-navigator
Navigate, search, and understand the Resume Matcher codebase using ripgrep, ack, or grep. Find functions, classes, components, API endpoints, trace data flows, and understand architecture. Use FIRST when exploring code, finding files, or understanding project structure.
srbhr/Resume-Matcher 26,484
-
fastapi
Build Python APIs with FastAPI, Pydantic v2, and async patterns. Covers project structure, JWT auth, validation, database integration, and 7 documented error preventions. Use when creating Python APIs, implementing auth, or troubleshooting 422 validation, CORS, async blocking, or schema errors.
srbhr/Resume-Matcher 26,484
-
tailwind-patterns
Production-ready Tailwind CSS patterns for responsive layouts, cards, navigation, forms, buttons, and typography. Includes spacing scale, breakpoints, mobile-first patterns, dark mode, and Swiss International Style overrides for Resume Matcher.
srbhr/Resume-Matcher 26,484
-
full-stack
Full-stack development skill that coordinates backend and frontend changes together. Use for features that span both layers: new API endpoint + UI, data model changes, end-to-end flows.
srbhr/Resume-Matcher 26,484
-
code-review
Review code for correctness, security, performance, and Resume Matcher conventions. Use when receiving code review feedback or before submitting PRs. Requires technical rigor, not performative agreement.
srbhr/Resume-Matcher 26,484
-
navigator
Quick codebase orientation for Resume Matcher. Points to key directories, architecture docs, and available skills. Use as a starting point before diving into code. For advanced search, use the codebase-navigator skill.
srbhr/Resume-Matcher 26,484
-
react-patterns
React and Next.js performance optimization guidelines from Vercel Engineering, tuned for local/offline or Docker-deployed apps. Eliminates async waterfalls, reduces bundle size, optimizes server and client performance.
srbhr/Resume-Matcher 26,484
-
backend-dev
Backend development skill for Resume Matcher. Handles FastAPI endpoints, Pydantic schemas, TinyDB operations, LiteLLM integration, and Python service logic. Use when creating or modifying backend code.
srbhr/Resume-Matcher 26,484
-
design-principles
Swiss International Style for Resume Matcher. Invoke ONLY when designing new UI components or modifying existing component styles. Provides colors, typography, borders, shadows, and component patterns.
srbhr/Resume-Matcher 26,484
-
frontend-dev
Frontend development skill for Resume Matcher. Handles Next.js pages, React components, Tailwind CSS with Swiss International Style, API integration, hooks, and i18n. Use when creating or modifying frontend code.
srbhr/Resume-Matcher 26,484