Skill-Verzeichnis

Wiederverwendbare Skills für AI Agents entdecken.

Durchsuche reale GitHub-Skills nach Aufgabe und prüfe Stars, Trust, Audit, Kategorie und Installationspfad vor der Verwendung.

Jede Empfehlung bleibt mit ihrem Repository, Audit und Installationspfad nachvollziehbar.

Suchergebnisse: contents

Englisches Verzeichnis
Cli75

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

30K
Stars
75/100
Trust
Kategorie: utilityAudit

A comprehensive C code style guide packaged as an AI agent skill with clang-format integration, enabling agents to write, edit, and format C code consistently.

1.3K
Stars
86/100
Trust
Kategorie: coding-agentsAudit

Curated collection of reusable agent skills for AI coding assistants like Cursor, Claude Code, and GitHub Copilot.

612
Stars
79/100
Trust
Kategorie: coding-agentsAudit

A comprehensive resource for skills and tools tailored for AI coding agents.

5.8K
Stars
73/100
Trust
Kategorie: developmentAudit

A collection of 66 game-development agent skills with a master router for AI coding agents, supporting multiple engines and tasks.

459
Stars
74/100
Trust
Kategorie: coding-agentsAudit

Dump the contents of a database

1.2K
Stars
76/100
Trust
Kategorie: data-analysisAudit

UmaDev orchestrates multiple AI coding CLIs to act as a team of roles for software development.

241
Stars
78/100
Trust
Kategorie: coding-agentsAudit

Curated collection of 14 domain-specific agent skills covering the CesiumJS API, installable as a Claude Code plugin or via the Agent Skills standard.

112
Stars
76/100
Trust
Kategorie: coding-agentsAudit

Claude skill: Prototype → Figma. Analyzes a Claude Code prototype, maps components to your Figma design system via search + Code Connect, explodes each interaction flow into state-by-state frames, and annotates triggers, transitions, and edge cases, making prototypes reviewable by PMs, designers, and engineers without running code.

138
Stars
76/100
Trust
Kategorie: utilityAudit

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
Trust
Kategorie: engineering / code qualityAudit

Markdown parser, done right. Commonmark support, extensions, syntax plugins, high speed - all in one. Gulp and metalsmith plugins available. Used by Facebook, Docusaurus and many others! Use https://github.com/breakdance/breakdance for HTML-to-markdown conversion. Use https://github.com/jonschlinkert/markdown-toc to generate a table of contents.

5.8K
Stars
73/100
Trust
Kategorie: document-processingAudit