GitHub
multi-model
Multi-model orchestration for ARIA. Activate when dispatching tasks to different LLM providers (OpenAI, local models, cloud providers) or when optimizing cost/latency tradeoffs.
Skills IA tools llm ai
Découvrez les skills tools llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: tools llm ai
tools llm ai Effacer les filtres
Explorer
GitHub
aios-cerebrum
AIOS Agent Operating System and Cerebrum SDK for building, deploying, and orchestrating AI agents
GitHub
llama
AI model inference and serving. Activate when: (1) Setting up LocalAI or vLLM, (2) Configuring model serving, (3) Working with GGUF/GGML models, (4) Implementing inference pipelines, or (5) Optimizing model per...
GitHub
llm-evaluation
LLM testing and evaluation tools including promptfoo, trulens, and evals frameworks
GitHub
transcript-condenser
Condenses Claude Code session transcripts into readable summaries by filtering metadata, system notifications, and command artifacts. Use when the user wants to review, analyze, or understand what happened in a...
GitHub
session-analyzer
Discovers and lists Claude Code session transcripts from .claude/logs/ for analysis. Use when the user wants to find available sessions, view session timelines, identify which sessions to analyze for workflow i...
GitHub
readathon-workflow-detector
Meta-skill that detects workflow patterns and suggests creating skills to automate them
GitHub
sync-specs-from-session
This skill should be used when the user asks to "sync specs", "update specs from work", "record what we did", "add to speclan", "document implemented features", or wants to capture session work as SPECLAN speci...
GitHub
do-foundation-claude
Claude Code 공식 Skill 작성 키트 - Skills, sub-agent, slash command, hook, memory, settings, IAM 권한 관리
GitHub
do-ai-nano-banana
콘텐츠 생성, 이미지 생성 및 AI 기반 워크플로우를 위한 Nano-Banana AI 서비스 통합. AI 서비스를 콘텐츠 생성에 통합할 때 사용
GitHub
agent-communication
Principles for writing token-efficient, action-oriented instructions to agents. Use when creating agent prompts, rules, documentation, or improving agent communication.
GitHub
skill-authoring
Guide for creating effective agent skills. Use when users want to create a new skill (or update an existing skill) that extends an agent's capabilities with specialized knowledge, workflows, or tool integration...
GitHub
skillcreator-codex
Codex-native skill creator. Self-contained 4-phase methodology for creating production-ready Claude Code skills. Adapted from SkillCreator v3.2 for Codex agents with embedded methodology and simulated synthesis...
GitHub
skillcreator
Ultimate meta-skill for creating production-ready Claude Code skills. Uses deep iterative analysis with 11 thinking models, regression questioning until exhausted, evolution and timelessness as core lens, and m...
GitHub
pipeline-insights
AI-powered pipeline diagnostics. Explains why faces weren't detected, tracked, embedded, or clustered using OpenAI GPT-4o analysis. Use when debugging pipeline issues, reviewing unclustered tracks, or understan...
GitHub
using-grok
Integrate xAI's Grok models for multi-model collaboration. Triggers on "Ask Grok", "What does Grok think", "Have Grok analyze", or similar phrases. Provides access to grok_query, grok_analyze_code, grok_reason,...
GitHub
subagent-creator
Create, configure, and document custom Claude Code subagents, including choosing scope, defining YAML frontmatter, selecting tools, model, permission mode, hooks, and usage examples.
GitHub
self-check
Adversarial self-validation skill for verifying outputs before delivery. Applies systematic counter-argument challenges including "why is this wrong", "prove this is incorrect", and "why doesn't this make sense...
GitHub
safe-agent-selective
Agent with selective Gemini safety settings for specific categories
GitHub
safe-agent-minimal
Agent with minimal Gemini safety settings using default threshold only
GitHub
safe-agent-comprehensive
Agent with comprehensive Gemini safety settings configured for all categories
GitHub
research-agent
Read-only code exploration and documentation search agent
GitHub
codex-exec
Execute codex CLI as sub-agent for thorough code reviews (codex's specialty), alternative approaches when stuck, or complex problems requiring extended investigation. Note that inference takes significant time.
GitHub
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Copilot should use this skill whenever asked to write some sort of internal communicatio...
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.