RADAR DES SKILLS · GITHUB

Des Agent Skills utiles, classés selon leur usage réel.

Comparez les Skills vérifiés par fonction, contenu, installations et fiabilité de la source avant de les ajouter.

PÉRIMÈTRE
VÉRIFIÉ
Skills
10 772
dépôts
1711
dernière synchronisation
23 sept. 2026
10 772 Skills
affaan-m
Communauté

tasteforge-video

Use for file-driven multimodal image, video, and 3D-asset discovery; taste interviews; distill or apply workflows; style-pack validation; editable EDL/FCPXML export; provenance audits; and offline planning that must fail closed before provider generation.

installations
1
GitHub Stars
255,9 k
Mis à jour
10 sept.
mastra-ai
Officiel

react-best-practices

React performance optimization guidelines from Mastra Engineering. This skill should be used when writing, reviewing, or refactoring React code to ensure optimal performance patterns. Triggers on tasks involving React components, data fetching, bundle optimization, or performance improvements.

installations
1
GitHub Stars
27,9 k
Mis à jour
10 sept.
huggingface
Officiel

huggingface-llm-trainer

Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.

installations
1
GitHub Stars
11 k
Mis à jour
10 sept.
sickn33
Communauté

api-designer

Generates complete, production-ready REST API endpoint specifications for any system or domain the user describes.

installations
1
GitHub Stars
46,3 k
Mis à jour
9 sept.
sickn33
Communauté

app-store-optimization

Complete App Store Optimization (ASO) toolkit for researching, optimizing, and tracking mobile app performance on Apple App Store and Google Play Store

installations
1
GitHub Stars
46,3 k
Mis à jour
9 sept.
sickn33
Communauté

telegram-bot-builder

Expert in building Telegram bots that solve real problems - from simple automation to complex AI-powered bots. Covers bot architecture, the Telegram Bot API, user experience, monetization strategies, and scaling bots to thousands of users.

installations
1
GitHub Stars
46,3 k
Mis à jour
9 sept.
wshobson
Communauté

code-review-excellence

Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.

installations
1
GitHub Stars
39,6 k
Mis à jour
7 sept.
wshobson
Communauté

lora-qlora-recipes

Configure LoRA and QLoRA supervised fine-tuning with current best-practice hyperparameters. Use when writing or reviewing a LoRA/QLoRA training configuration, choosing rank/alpha/target modules, or deciding between LoRA, QLoRA, and full fine-tuning.

installations
1
GitHub Stars
39,6 k
Mis à jour
7 sept.
tirth8205
Communauté

explore-codebase

Navigate and understand codebase structure using the knowledge graph

installations
1
GitHub Stars
31,3 k
Mis à jour
10 sept.
alirezarezvani
Communauté

docker-development

Docker and container development agent skill and plugin for Dockerfile optimization, docker-compose orchestration, multi-stage builds, and container security hardening. Use when: user wants to optimize a Dockerfile, create or improve docker-compose configurations, implement multi-stage builds, audit container security, reduce image size, or follow container best practices. Covers build performance, layer caching, secret management, and production-ready container patterns.

installations
1
GitHub Stars
25,8 k
Mis à jour
30 août
alirezarezvani
Communauté

senior-frontend

Frontend development skill for React, Next.js, TypeScript, and Tailwind CSS applications. Use when building React components, optimizing Next.js performance, analyzing bundle sizes, scaffolding frontend projects, implementing accessibility, or reviewing frontend code quality.

installations
1
GitHub Stars
25,8 k
Mis à jour
30 août
nvidia
Officiel

nemo-rl-session-memory

Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work, handoffs, or any session where important state should be written periodically under the repo's session directory. Do NOT use for: simple questions, short tasks, one-off commands, linting, or code review.

installations
1
GitHub Stars
3,3 k
Mis à jour
8 sept.
muratcankoylan
Communauté

context-degradation

This skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context clash, context confusion, attention-pattern issues, and agent performance degradation caused by accumulated or conflicting context.

installations
1
GitHub Stars
18 k
Mis à jour
19 août
muratcankoylan
Communauté

context-fundamentals

This skill should be used to explain or reason about the foundational concepts of context engineering: what context is, the anatomy of a context window, how attention mechanics work, the U-shaped attention curve, why context quality matters more than quantity, and the mental models needed to interpret every other context-engineering decision. Use this for conceptual explanation, onboarding, and background reading. Route operational work to the specialized skills: debugging attention failures goes to context-degradation, token-efficiency work goes to context-optimization, conversation summarization goes to context-compression, and project-shape decisions go to project-development.

installations
1
GitHub Stars
18 k
Mis à jour
19 août
muratcankoylan
Communauté

context-optimization

This skill should be used for improving context efficiency: context budgeting, observation masking, prefix or KV-cache strategy, partitioning, token-cost reduction, retrieval scoping, and extending effective context capacity without lowering answer quality.

installations
1
GitHub Stars
18 k
Mis à jour
19 août
muratcankoylan
Communauté

multi-agent-patterns

This skill should be used when designing multi-agent systems that need context isolation, supervisor or swarm coordination, explicit handoffs, parallel execution, or a decision on whether multiple agents are justified.

installations
1
GitHub Stars
18 k
Mis à jour
19 août
typescript-eslint
Communauté

code-clarity

Remove the unnecessary intermediate variables, restating comments, redundant type annotations, and imprecise names that make code longer without making it clearer. Use when writing or reviewing any TypeScript in this repository, especially code written with an AI agent's help.

installations
1
GitHub Stars
16,4 k
Mis à jour
10 sept.
typescript-eslint
Communauté

types-not-workarounds

Fix imprecise types at their source instead of papering over them with runtime checks, assertion helpers, or in narrowing. Use when reviewing or writing code that adds a guard, an assertion, or an optional chain only to satisfy the type checker.

installations
1
GitHub Stars
16,4 k
Mis à jour
10 sept.
img2threejs
Communauté

img2threejs

Turn an object or character reference image into a quality-gated, animation-ready procedural Three.js model built in code. Use for image-to-3D reconstruction, detail-accurate object rebuilds, stylized/likeness-maximized human characters, sculpt specs, and staged code generation.

installations
1
GitHub Stars
15,7 k
Mis à jour
7 sept.
trailhq
Communauté

graft

This repo is indexed by graft/. For ANY task here, whether understanding how something works, finding where code lives, tracing what calls a symbol or what a change breaks, or scoping an edit, get your context from graft before grepping or reading source files.

installations
1
GitHub Stars
7 k
Mis à jour
10 sept.
steipete
Communauté

browser-use

Control the user's existing signed-in Chrome: callable Codex Chrome plugin first, then OpenClaw extension-backed mcporter, with direct DevTools attachment only as a last fallback.

installations
1
GitHub Stars
6,6 k
Mis à jour
8 sept.
antfu
Communauté

vue-router-best-practices

Vue Router 4 patterns, navigation guards, route params, and route-component lifecycle interactions.

installations
1
GitHub Stars
5,9 k
Mis à jour
23 juin
epoko77-ai
Communauté

humanize

AI가 쓴 한글 텍스트를 자연스럽게 윤문하는 진입 명령. humanize-korean 파이프라인을 Fast 모드(기본)로 실행하고 --strict면 정밀 3콜(진단→겨냥 윤문→finalize). 트리거 — "/humanize".

installations
1
GitHub Stars
5,4 k
Mis à jour
6 sept.
epoko77-ai
Communauté

humanize-redo

가장 최근 윤문 결과를 2차로 다시 다듬는다 — 특정 카테고리·문단·강도 조정도 가능. humanize-korean strict 윤문(Phase B)을 기존 runid에 재실행해 잔존 finding을 처리한다. 트리거 — "/humanize-redo".

installations
1
GitHub Stars
5,4 k
Mis à jour
6 sept.