Python · For developers

Analyzes a video file with Google Gemini and returns a structured markdown report covering top-level summary, scene-by-scene breakdown, audio transcript (or honest "silent" note), visual details…

mikefutia/claude-vision

幫 Leo 看影片。當 Leo 丟影片連結（YouTube/IG/TikTok）或本機影片檔，要摘要、分析、拆解對標時使用——Claude 不能直接吃影片，先用這個工具抽關鍵幀＋逐字稿＋運鏡節奏＋聲音/語氣/手勢時間軸再讀。

HUANGCHIHHUNGLeo/claude-real-video

Picks the next CPython standard library module ready for a RustPython upgrade, skipping modules that already have an open upgrade pull request.

RustPython/RustPython

Migrate Python applications from the Claude Agent SDK to Pydantic AI and, only when needed, Pydantic AI Harness.

pydantic/pydantic-ai

Run a multi-agent deep analysis of a codebase, producing AI-readable analysis documents in .ai/docs/ covering structure, dependencies, data flow, request flow, and APIs.

divar-ir/ai-doc-gen

Port a component or feature that already exists in one protocol client template to sibling clients under packages/templates/clients/<protocol/ that are missing it.

asyncapi/generator

Builds podcast-style audio narration from text with Azure OpenAI's GPT Realtime Mini over WebSocket, from a Python FastAPI backend to a React player.

microsoft/skills

Generates UiPath Studio projects, REFramework scaffolds, XAML workflows and expressions through 104 deterministic Python generators instead of hand-written XAML.

marcelocruzrpa/uipath-ai-skills

CAD modeling with build123d Python library. An agent skill from rawwerks/VibeCAD.

rawwerks/VibeCAD

Read and act on a personal Telegram account from the terminal with the tlgr CLI (MTProto user account, not a bot).

tlgrcli/tlgr

This skill should be used when the user mentions Unraid, asks to check server health, monitor array or disk status, list or restart Docker containers, start or stop VMs, read system logs, check…

dinglebear-ai/unraid

A skill your agent uses when a user wants guidance on starting, contributing to, growing, governing, funding, securing, or sustaining an open source project, or asks about contributor onboarding…

calf-ai/calfkit-sdk

Runs the ONNX Runtime transformers Python tests against a GPU wheel and proves the cuDNN flash attention path was used rather than a silent fallback.

microsoft/onnxruntime

Shows how to organize PyTorch training with Lightning's LightningModule and Trainer, covering validation, DDP, callbacks and learning-rate scheduling.

Orchestra-Research/AI-Research-SKILLs

Develop, debug, and manage Temporal applications across Python, TypeScript, Go, Java, .NET, Ruby, and Rust.

temporalio/skill-temporal-developer

PaddlePaddle (飞桨) C++ 算子开发指南。提供从 YAML 配置、InferMeta 函数、Kernel 实现、Python API 封装、单元测试到编译验证的完整算子开发流程指导。在以下场景使用此 skill：(1) 为 Paddle 框架新增 C++ 算子 (2) 修改或调试已有 Paddle 算子 (3) 编写算子的 YAML…

PaddlePaddle/Paddle

Produces a scorecard evaluating a pyrefly change on correctness and quality.

facebook/pyrefly

微信发信能力：通过 Windows 桌面微信发送文本、图片URL或本地文件。适合各类 Agent 在本机直接发送一次性消息。触发词：给[某人]发微信、通知[某人]、把这个用微信发给[某人]、用微信发个图片、把本地文件发给[某人]

LAVARONG/wechat-automation-api

Update the streamlit/docs repo for a new Streamlit release. An agent skill from streamlit/docs.

streamlit/docs

Shows how to add Deepgram analytics such as diarization, summaries, sentiment, topics, redaction and language detection to speech transcription in Python.

deepgram/deepgram-python-sdk

Migrate Python apps from Azure OpenAI Chat Completions to the Responses API.

microsoft/ai-agents-for-beginners

A skill your agent uses when adding a new LLM provider to chatlas (a new Chat<Name() / <NameProvider in chatlas/provider.py) — covers the research phase, class and function structure, the standard…

posit-dev/chatlas

A skill your agent uses whenever writing, modifying, reviewing, or debugging code involving Celeste, celeste-ai, celeste-python, import celeste, src/celeste, or withceleste app integrations.

withceleste/celeste-python

Send and receive transactional emails with Cloudflare Email Service (Email Sending + Email Routing).

hodgef/apiker

A skill your agent uses when you need to run the unslop repo, analyze a domain for repetitive AI defaults, generate a reusable skill file, and verify that the output is specific and materially…

mshumer/unslop

Run the GraalPy ROTA import update workflow. An agent skill from oracle/graalpython.

oracle/graalpython

PDF files: create, read, merge, fill, OCR, edit text. An agent skill from NousResearch/hermes-agent.

NousResearch/hermes-agent

Expert-level Ghidra reverse engineering for firmware binaries with emphasis on stripped binary analysis, automated function discovery, cryptographic routine identification, authentication logic…

OrbitCurve/firmware-reverse-engineering

Gives patterns, a tool design checklist and an architecture decision tree for building agent harnesses, tools and multi-agent setups around a model.

FareedKhan-dev/claude-code-from-scratch

Write, run, test and package Edge Python programs with the edge CLI.

dylan-sutton-chavez/edge-python

Apollo-Lite lint and formatting workflow. An agent skill from wheelos/apollo-lite.

wheelos/apollo-lite

GAN-style iterative improvement loop for any text artifact. An agent skill from crimeacs/auto-improve.

crimeacs/auto-improve

Call vision models (Doubao, Qwen, DeepSeek, OpenAI) to analyze images.

xiincs/claude-code-vision-skill

Search, filter, download, and analyze Copernicus Data Space products with the phidown project.

ESA-PhiLab/phidown

Validates SQL schema files for compliance with internal safety and naming policies.

rominirani/antigravity-skills

Commit validated changes, calculate an annotated stable/beta/alpha version tag, and push the release to the publishing remote.

AliceJump/ok-end-field

Build voice AI agents with ElevenLabs. An agent skill from tadaspetra/loop.

tadaspetra/loop

Installs, tunes and enforces Sponsio contracts that block unsafe tool calls in LLM agents, covering setup, auditing, observe mode and flipping to enforce.

SponsioLabs/Sponsio

Write a short implementation plan or a longer execution plan before coding.

owainlewis/youtube-tutorials

Build multimodal AI apps with Pixeltable. An agent skill from pixeltable/pixeltable.

pixeltable/pixeltable

Define metrics from Kayba insights, implement them as Python measurement code, run against traces, and iterate until the metrics are clean and meaningful.

kayba-ai/agentic-context-engine

Convert binary documents (PDF, DOCX, XLSX, PPTX, HTML, EPUB, images) to clean LLM-friendly Markdown using Microsoft's markitdown Python tool.

Team-Commonly/commonly

Launch an installed Bello supervisor in the background for a repository coding task, or inspect an existing Bello run.

Makson179/Bello

Selectively monitor important long-running or resource-intensive commands with Haoleme by prefixing them with hao, so status, output, and completion notifications sync to the mobile app.

HaolemeApp/Haoleme

A skill your agent uses when building a local Windows WebCode installer from this repo for machine testing, especially when the package must bundle the Kokoro or sherpa-onnx Reply TTS service, model…

shuyu-labs/WebCode

Tests JavaScript embedded in an HTML file in two layers: pytest checks of the logic ported to Python, and Playwright runs in a real browser for the DOM.

liaohch3/claude-tap

Final checklist before handing work back in the herdr-auto-title repo: review the diff, run make check, apply the comment and AGENTS.md rules, then report.

kryptamine/herdr-auto-title

Use OpenBiliClaw's versioned Agent Bridge CLI to read multi-source recommendations, profile state, dialogue, probes, saved lists, and submit explicit feedback.

whiteguo233/OpenBiliClaw