Annuaire de skills

Découvrez des skills réutilisables pour les AI agents.

Recherchez de vrais skills GitHub par tâche et vérifiez Stars, confiance, audit, catégorie et chemin d’installation avant de les utiliser.

Chaque recommandation reste clairement reliée à son dépôt, son audit et son chemin d’installation.

Résultats de recherche: bun

Annuaire en anglais
Bun76

SQL-first Golang ORM

4.9K
Stars
76/100
Confiance
Catégorie: data-analysisAudit

Opinionated macOS development environment automation that packages agent skills, rules, and CLI tooling for AI coding agents like Claude Code and Codex.

124
Stars
73/100
Confiance
Catégorie: coding-agentsAudit

搜索、安装和协调创建 Claude Code Agent Skills。当用户想要搜索技能、安装工具、创建自定义 Skill,或者说"find a skill"、"搜索技能"、"帮我做个 skill"、"create a skill"时触发。也适用于用户说"有没有做 X 的工具"、"我想扩展 Agent 能力",或当前能力不足需要先查找可复用方案的场景。

51K
Stars
70/100
Confiance
Catégorie: researchAudit

Local-only web GUI for inspecting agent skills (SKILL.md) across user, project, plugin, cache, and marketplace sources

65
Stars
69/100
Confiance
Catégorie: utilityAudit

⚡ High-performance job queue for Bun. SQLite persistence, DLQ, cron jobs, S3 backups. Built for AI agents and automation

480
Stars
69/100
Confiance
Catégorie: agent-frameworksAudit

Plug-in vision for text-only models. Hard rule: when a file path or URL with an image extension (.png, .jpg, .jpeg, .webp, .gif, .heic, .heif) appears anywhere in the conversation (typed by the user, injected as a `[Image: source: <path>]` line, or inside a tag) and you cannot see that image's content, run this skill on it before any other approach: no self-built OCR, no PIL, no tesseract. Also triggers on pasted-image placeholders such as `[Image #1]` and `[Unsupported Image]`. If you can actually see the image, do not use this skill. When unsure, run `modlens guard` before the first read of a session: a deny verdict means the active model has native vision and must read the image itself. Runs the modlens CLI to convert the image into structured JSON evidence: every word transcribed, layout regions, semantics, visual clues. Also use when the user asks how to install, configure, or switch modlens providers (Gemini API key, OpenAI-compatible endpoints, Claude API or Claude Code CLI).

3.3K
Stars
59/100
Confiance
Catégorie: researchAudit

Set up your GitHub Actions workflow with a specific version of Bun

703
Stars
69/100
Confiance
Catégorie: github-automationAudit

CrewMeld — Enterprise AI Digital Workforce Platform. Manage AI employees like real team members. Visual SOP orchestration, 13 LLM providers (including China-native models), 8+ messaging channels(WeCom/DingTalk/Feishu/Telegram), knowledge base with RAG, and full private deployment support. Built with Next.js, React, TypeScript & Bun.

144
Stars
66/100
Confiance
Catégorie: support-automationAudit

Collection of reusable AI agent skills for code review, planning, research, and automation tasks.

37
Stars
69/100
Confiance
Catégorie: coding-agentsAudit

Upyo is a simple and cross-runtime library for sending email messages using SMTP and various email providers. It works on Node.js, Deno, Bun, and edge functions.

521
Stars
71/100
Confiance
Catégorie: productivity-automationAudit

Desktop application for discovering, installing, and managing AI agent skills across multiple coding tools.

84
Stars
69/100
Confiance
Catégorie: utilityAudit