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: evals

Annuaire en anglais

🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

29K
Stars
79/100
Confiance
Catégorie: developmentAudit

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
Confiance
Catégorie: presentationAudit

AI system design guide for engineers building production AI systems and evals.

2.2K
Stars
74/100
Confiance
Catégorie: dataAudit

Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

1.2K
Stars
85/100
Confiance
Catégorie: devopsAudit

Awesome QA Skills — a bilingual (zh/en) AI testing Agent Skills library for Codex, Cursor, Claude Code, Kiro, OpenCode, and Trae. Ships 4 testing workflows and 25 testing-type skills (58 skill folders with language parity): independently installable, composable, and eval-ready with skill-up. Covers requirements, strategy, cases, API/performance/sec

151
Stars
79/100
Confiance
Catégorie: utilityAudit

A collection of agent skills that inject team-specific context into coding agents at session start, improving collaboration and adherence to conventions.

124
Stars
73/100
Confiance
Catégorie: coding-agentsAudit

Create a new skill in the current repository. Use when the user wants to create/add a new skill, or mentions creating a skill from scratch. This skill follows the workflow defined in .agents/skills/README.md and helps scaffold, validate, and sync new skills.

51K
Stars
80/100
Confiance
Catégorie: automationAudit

OpenSource Production ready Customer service with built in Evals and monitoring

1.5K
Stars
76/100
Confiance
Catégorie: rag-knowledgeAudit

🪢 Langfuse documentation -- Langfuse is the open source LLM Engineering Platform. Observability, evals, prompt management, playground and metrics to debug and improve LLM apps

233
Stars
72/100
Confiance
Catégorie: devopsAudit

Create, edit, or fix Lottie/Bodymovin JSON animations for the local Skia Skottie player. Use for text-to-Lottie, SVG/logo/type animation, loaders/icons, state feedback, UI microinteractions, lower thirds, diagrams, data/stat/chart animations, product promos, scene/camera motion, visual effects, scene edits, slots/controls, and Skottie debugging.

5.3K
Stars
75/100
Confiance
Catégorie: design-creativeAudit

A composable catalog of production-grade engineering workflows and expert capabilities for AI coding agents, covering planning, TDD, debugging, review, and more.

90
Stars
70/100
Confiance
Catégorie: coding-agentsAudit