技能目录

为 AI Agent 发现可复用技能。

按任务搜索真实的 GitHub 技能,并在使用前查看 Stars、信任、审计、分类和安装路径。

每个推荐都保留与其仓库、审计和安装路径的明确关联。

搜索结果: human-activity-recognition

英文目录

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

23K
Stars
87/100
信任
分类: media-automation审计

Break a plan, spec, or conversation into independently actionable tracer-bullet tickets with explicit blocking relationships.

177K
Stars
81/100
信任
分类: coding-agents审计

React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.

30K
Stars
88/100
信任
分类: coding-agents审计
Cli75

A versatile command-line tool for interacting with Google Workspace APIs, designed for both human users and AI agents.

30K
Stars
75/100
信任
分类: utility审计

AKShare is an elegant and simple financial data interface library for Python, built for human beings! 开源财经数据接口库

22K
Stars
83/100
信任
分类: data-analysis审计

The world's simplest facial recognition api for Python and the command line

57K
Stars
77/100
信任
分类: ml-automation审计
Cli85

Official Lark/Feishu CLI tool with 200+ commands and 26 AI agent skills, designed for agent-native operation and easy integration with AI runtimes.

17K
Stars
85/100
信任
分类: productivity审计

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

15K
Stars
87/100
信任
分类: media-automation审计

Open-source & free — Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.

21K
Stars
86/100
信任
分类: development审计

Multilingual speech understanding: ASR + emotion recognition + audio event detection. 50+ languages, 15x faster than Whisper, non-autoregressive.

8.6K
Stars
77/100
信任
分类: media-automation审计

Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), reduced-motion, or the design foundations (feedback, spatial consistency, restraint) behind Apple-style interfaces.

18K
Stars
87/100
信任
分类: design-creative审计

A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python

23K
Stars
87/100
信任
分类: ml-automation审计