Que fait gestion-fenêtre-contexte ?
Stratégies de gestion des fenêtres de contexte LLM incluant la synthèse, le rognage, le routage et la prévention de la pourriture du contexte.
Stratégies de gestion des fenêtres de contexte LLM incluant la synthèse, le rognage, le routage et la prévention de la pourriture du contexte.
Cette compétence, sickn33/gestion-fenêtre-contexte, est conçue pour les développeurs et utilisateurs d'agents IA qui travaillent avec des modèles de langage de grande taille (LLM) tels que Claude, GPT et autres. Sa fonction principale est d'enseigner comment gérer efficacement la fenêtre de contexte, cette mémoire limitée qui détermine la quantité d'informations qu'un modèle peut traiter à la fois. L'utilisateur apprendra des techniques cruciales comme la *synthèse* (résumer des dialogues longs), le *rognage* (supprimer des informations redondantes ou obsolètes), le *routage* (diriger les requêtes vers le bon sous-ensemble de contexte) et la *prévention de la pourriture du contexte* (éviter que des informations anciennes ne polluent les réponses). L'utilité est immense pour des applications complexes où la gestion de longs historiques de conversation ou de multiples sources de données est essentielle. Basée sur la documentation SKILL.md, elle est compatible avec des plateformes comme Claude Code, Cursor et Codex, et fonctionne en fournissant des stratégies pratiques et des exemples de code (comme des scripts Python) pour implémenter ces méthodes dans vos propres pipelines. En bref, cette compétence transforme un problème récurrent en une compétence maîtrisée, rendant vos agents IA plus précis, réactifs et fiables.
npx skills add https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/context-window-managementInstalled? Explore more Développement et programmation skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →
Stratégies de gestion des fenêtres de contexte LLM incluant la synthèse, le rognage, le routage et la prévention de la pourriture du contexte.
This repo contains 20 individual skills — each has its own dedicated page.
Expert in building 3D experiences for the web - Three.js, React Three Fiber, Spline, WebGL, and interactive 3D scenes. Covers product configurators, 3D portfolios, immersive websites, and bringing depth to web experiences.
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them.
Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration.
Generate comprehensive, developer-friendly API documentation from code, including endpoints, parameters, examples, and best practices
API design principles and decision-making. REST vs GraphQL vs tRPC selection, response formats, versioning, pagination.
Implement secure API design patterns including authentication, authorization, input validation, rate limiting, and protection against common API vulnerabilities
Complete App Store Optimization (ASO) toolkit for researching, optimizing, and tracking mobile app performance on Apple App Store and Google Play Store
Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design.
Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration
Specialized skill for building production-ready serverless applications on AWS. Covers Lambda functions, API Gateway, DynamoDB, SQS/SNS event-driven patterns, SAM/CDK deployment, and cold start optimization.
Expert backend architect specializing in scalable API design, microservices architecture, and distributed systems.
You are a senior backend engineer operating production-grade services under strict architectural and reliability constraints. Use when routes, controllers, services, repositories, express middleware, or prisma database access.
Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.
Bash scripting workflow for creating production-ready shell scripts with defensive patterns, error handling, and testing.
Use before creative or constructive work (features, architecture, behavior). Transforms vague ideas into validated designs through disciplined reasoning and collaboration.
Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns.
Expert in building browser extensions that solve real problems - Chrome, Firefox, and cross-browser extensions. Covers extension architecture, manifest v3, content scripts, popup UIs, monetization strategies, and Chrome Web Store publishing.
BullMQ expert for Redis-backed job queues, background processing, and reliable async execution in Node.js/TypeScript applications.
Fast, modern JavaScript/TypeScript development with the Bun runtime, inspired by [oven-sh/bun](https://github.com/oven-sh/bun).
Send and manage iMessages via BlueBubbles, including attachments, tapbacks, edits, replies, and groups.
Control Eight Sleep pods (status, temperature, alarms, schedules).
BluOS CLI (blu) for discovery, playback, grouping, and volume.
Create, search, and manage Bear notes via grizzly CLI.
Capture frames or clips from RTSP/ONVIF cameras.
Search GIF providers with CLI/TUI, download results, and extract stills/sheets.