GitHub
prompt-refiner-claude
Refine prompts for Claude models (Opus, Sonnet, Haiku) using Anthropic's best practices. Use when preparing complex tasks for Claude.
Skills IA documentation llm ai
Découvrez les skills documentation llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: documentation llm ai
documentation llm ai Effacer les filtres
Explorer
GitHub
dspy-advanced
Advanced DSPy modules including ReAct agents, tool calling, output refinement (BestOfN, Refine), and adapters. Use when building agent systems, integrating external tools, or implementing multi-step reasoning.
GitHub
runpod-ops
Provision, manage, and terminate RunPod GPU instances for LLM training. Use when user says "spin up GPU", "create RunPod instance", "terminate pod", "check GPU status", "provision training server", or needs clo...
GitHub
model-tracking-protocol
MANDATORY tracking protocol for multi-model validation. Creates structured tracking tables BEFORE launching models, tracks progress during execution, and ensures complete results presentation. Use when running...
GitHub
agent-creator
Interview-based system for creating specialized Claude Code agents. Use when users want to create a Claude Code agent, need help defining agent roles and responsibilities, mention "create an agent" or "build an...
GitHub
managing-cross-repository-configuration
Use when user asks where to put configuration, skills, or learnings, or discusses sharing config across projects. Provides decision criteria for the three-tier architecture (global ~/.claude, plugin, project-lo...
GitHub
llm-app-architecture
Automatically applies when building LLM applications. Ensures proper async patterns for LLM calls, streaming responses, token management, retry logic, and error handling.
GitHub
reviewing-llama-stack-code
Use when reviewing code or PRs in the llama-stack repository (llamastack/llama-stack on GitHub). Provides specialized knowledge about Llama Stack's architecture, testing patterns (recordings folders), backward...
GitHub
tool-design-pattern
Automatically applies when creating AI tool functions. Ensures proper schema design, input validation, error handling, context access, and comprehensive testing.
GitHub
brainstorm
Use when the user is exploring possibilities, asking for ideas, or expressing uncertainty. Trigger cues include "ideas", "alternatives", "what could we do", "brainstorm", "different approaches", "I'm not sure y...
GitHub
troubleshooting-gpt-oss-and-vllm-errors
Use when diagnosing openai_harmony.HarmonyError or gpt-oss tool calling issues with vLLM. Identifies error sources (vLLM server vs client), maps specific error messages to known GitHub issues, and provides conf...
GitHub
claude-tools
This skill provides knowledge about Claude tools (Prompts, Skills, Subagents, Commands, and MCPs). Use this skill when knowledge about Claude tools is needed, when the user mentions Claude tools or when the use...
GitHub
prompting-patterns
Automatically applies when engineering prompts for LLMs. Ensures proper prompt structure, templates, few-shot examples, context management, and injection prevention.
GitHub
rag-design-patterns
Automatically applies when building RAG (Retrieval Augmented Generation) systems. Ensures proper chunking strategies, vector database patterns, embedding management, reranking, and retrieval optimization.
GitHub
agent-orchestration-patterns
Automatically applies when designing multi-agent systems. Ensures proper tool schema design with Pydantic, agent state management, error handling for tool execution, and orchestration patterns.
GitHub
creating-skills
Creates new Agent Skills with proper YAML frontmatter, progressive disclosure architecture, and best practices. Use when the user asks to create a new skill, generate a skill template, or build custom capabilit...
GitHub
pocketflow
PocketFlow framework for building LLM applications with graph-based abstractions, design patterns, and agentic coding workflows
GitHub
placeholderapi
PlaceholderAPI - Minecraft plugin expansion system for placeholder text replacement
GitHub
validating-openai-api-implementations
Use when reviewing OpenAI API usage, answering questions about OpenAI endpoints, or validating implementations against the official API specification. Provides expert knowledge on chat completions, embeddings,...
GitHub
module-author
Generates module README.md with exercise planning table for CopilotTraining workshop modules. Researches URLs to understand new capabilities and creates strategic content outline. Use exercise-author skill to i...
GitHub
databricks-apps
Databricks Apps deployment, debugging, and configuration management. Use when working with Databricks Apps issues including deployment failures, app configuration (app.yaml), granting permissions to SQL warehou...
GitHub
documentation-loader
Automatically load and cache OnoCoro mandatory documentation (AGENTS.md, coding-standards.md, etc.) for AI agents. Supports manual triggers via /readmd command and auto-load on session start. Prevents context g...
GitHub
human-resources
Human Resources skill for recruiting, onboarding, employee engagement, policies, performance management, and HR operations. Use when handling HR processes, recruiting, employee relations, or organizational deve...
GitHub
trekker
Persistent task memory for AI agents across sessions
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.