GitHub
voice-matching-wizard
Transform writing samples into a codified voice style that can be replicated consistently. This wizard guides you through analyzing samples, extracting patterns, and generating a custom voice skill.
Skills IA content media llm ai
Découvrez les skills content media llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: content media llm ai
content media llm ai Effacer les filtres
Explorer
GitHub
nano-banana-builder
Build production-ready web applications powered by Google's Nano Banana image generation APIs—creating everything from simple text-to-image generators to sophisticated iterative editors with multi-turn conversa...
GitHub
image-prompt-generator
Generate AI images using Gemini image generation API. Use this skill when content needs images - thumbnails, social posts, blog headers, or creative visuals. Follows an iterative workflow - brainstorm concepts,...
GitHub
cloud-run-deploy
Cloud Run AI Engine deployment workflow with free tier optimization. Triggers when user requests Cloud Run deployment, AI engine deploy, or production release. Use for deploying AI Engine to Google Cloud Run.
GitHub
ai-code-review
AI 코드 리뷰 결과 분석 및 개선 실행. pending 리뷰를 읽고, 개선 필요사항을 분석하여 실제 코드 수정까지 진행. 평가는 부산물.
GitHub
ai-report-export
Automated 2-AI verification result documentation and export workflow. Triggers when user requests AI verification report export, documentation of findings, or saving cross-validation results. Use after completi...
GitHub
memory-systems
Agent memory architecture including working, short-term, long-term, and temporal knowledge graphs.
GitHub
clerk-llm-docs
Fetch LLM-optimized documentation for Clerk, the complete user management platform.
GitHub
firecrawl
Web scraping, content extraction, and autonomous research agent for deep web investigation.
GitHub
advanced-evaluation
LLM-as-Judge techniques including direct scoring, pairwise comparison, rubric generation, and bias mitigation.
GitHub
healer
Healer monitoring expertise - detection patterns, API endpoints, dual-model architecture, and remediation workflows. Use when monitoring Play workflows or debugging agent failures.
GitHub
deep-research
Deep technical research using Firecrawl Agent for autonomous web investigation, competitive analysis, and implementation pattern discovery.
GitHub
openmemory
Persistent long-term agent memory for storing and querying past work, patterns, and learnings.
GitHub
evaluation
Agent evaluation methods including LLM-as-judge, rubrics, and quality gates.
GitHub
ai-ml-infra
KubeAI, GPU operators, and model serving patterns for AI/ML infrastructure on Kubernetes.
GitHub
ralph-technique
The Ralph Wiggum technique for minimal, declarative prompts that enable loop-based autonomous execution.
GitHub
skill-authoring
Meta-skill for creating and improving agent skills. Use when designing new skills, refining existing skills, or understanding skill architecture patterns. Provides progressive disclosure, context efficiency pri...
GitHub
bun-llm-docs
Fetch Bun runtime documentation via llms.txt for up-to-date API references
GitHub
project-development
Methodology for identifying LLM-suited tasks, designing pipelines, and iterating with agent-assisted development.
GitHub
linear-agent-api
Linear Agent API expertise - sessions, activities, signals, and best practices. Use when working with Linear agent integration, verifying dialogue population, or implementing two-way communication.
GitHub
llm-docs
Fetch LLM-optimized documentation from llms.txt endpoints for up-to-date API references
GitHub
mcp-development
Guide for creating MCP (Model Context Protocol) servers that enable LLMs to interact with external services. Use when building MCP servers, integrating external APIs, implementing tool servers, or creating agen...
GitHub
context-degradation
Recognize and mitigate context failures including lost-in-middle, context poisoning, distraction, confusion, and clash.
GitHub
context-fundamentals
Foundational understanding of context engineering for AI agent systems - context windows, attention mechanics, progressive disclosure, and context budgeting
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.