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: blind-face-restoration

英文目录

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

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

Low-code platform allows you to build business apps, enables you to quickly create internal tools such as dashboard, crud app, admin panel, crm, cms, etc. Supports PostgreSQL, MySQL, Supabase, GraphQL, MongoDB, MSSQL, Rest API, Hugging Face, Redis, etc. Automate workflows with schedule or webhook. Open source Retool.

12K
Stars
84/100
信任
分类: coding-agents审计

The official Python client for the Hugging Face Hub.

3.7K
Stars
80/100
信任
分类: ml-automation审计

A curated collection of 13 tested Claude Code agent skills for producing decks, research briefs, PRDs, articles, audits, and other finished work.

626
Stars
83/100
信任
分类: presentation审计

A DeepSeek Harness plugin that equips text-only agents with vision capabilities for image Q&A, long-screenshot OCR, UI restoration, grounding, and pixel diff, packaged as an installable skill with a Web UI.

491
Stars
80/100
信任
分类: utility审计

:rocket: An open source alternative to searx which provides a modern-looking :sparkles:, lightning-fast :zap:, privacy respecting :disguised_face:, secure :lock: meta search engine

1.1K
Stars
84/100
信任
分类: legal-compliance审计

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

34K
Stars
71/100
信任
分类: ml-automation审计

A meta-skill that creates, evaluates, and improves other AI agent skills with multiple modes and evidence-based validation.

133
Stars
77/100
信任
分类: utility审计

Test Cherry Studio PRs by resolving and checking out a PR, statically inspecting its changes, running interactive UI tests against a safely tracked Electron instance through CDP, producing a structured report, cleaning up only the owned test instance, and restoring the original branch.

51K
Stars
77/100
信任
分类: research审计

Adversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.

25K
Stars
77/100
信任
分类: engineering / code quality审计