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: vega-lite

Annuaire en anglais

Applications self-hosting and DevOps platform for running open source, web-based linux Panel of lite PaaS

2.1K
Stars
77/100
Confiance
Catégorie: devopsAudit

超轻量级中文ocr,支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M

12K
Stars
86/100
Confiance
Catégorie: document-processingAudit

Query git repositories with SQL. Generate reports, perform status checks, analyze codebases. 🔍 📊

3.5K
Stars
77/100
Confiance
Catégorie: data-analysisAudit

Fathom Lite. Simple, privacy-focused website analytics. Built with Golang & Preact.

8.0K
Stars
84/100
Confiance
Catégorie: legal-complianceAudit

The best browser for both you and your AI agents work in parallel.

7.9K
Stars
74/100
Confiance
Catégorie: agent-frameworksAudit

可能是最深度的 AI 投研报告 Skill:九章个股深研 + 九章财报深度分析,脚本化 DCF/EPV 与可复算估值

234
Stars
75/100
Confiance
Catégorie: utilityAudit

Two Claude Skills that turn agents into AI film directors, providing cinematic dramaturgy and exact prompt syntax for major video/image models.

118
Stars
76/100
Confiance
Catégorie: design-creativeAudit

A hardware-aware Codex/WorkBuddy skill that automates local MiniMax H3 video generation through ComfyUI, handling model selection, installation, and low-VRAM configuration.

126
Stars
80/100
Confiance
Catégorie: design-creativeAudit

Kodezi Chronos is a debugging-first language model that achieves state-of-the-art results on SWE-bench Lite (80.33%) and 67% real-world fix accuracy, over six times better than GPT-4. Built with Adaptive Graph-Guided Retrieval and Persistent Debug Memory. Model available Q1 2026 via Kodezi OS.

4.9K
Stars
73/100
Confiance
Catégorie: ml-automationAudit

🤖📈 EA31337 Lite, Advanced and Rider - Forex multi-strategy trading robot for MT4/MT5 platforms

1.2K
Stars
78/100
Confiance
Catégorie: financeAudit

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.

34K
Stars
77/100
Confiance
Catégorie: researchAudit

A curated collection of battle-tested Claude Code skills for product, content, writing, presentations, and workflow automation.

130
Stars
75/100
Confiance
Catégorie: coding-agentsAudit