GitHub
error-recovery
Handle errors, timeouts, and failures in multi-agent workflows. Use when dealing with external model timeouts, API failures, partial success, user cancellation, or graceful degradation. Trigger keywords - "erro...
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
spec-task-management
This skill should be used when the user asks to "analyze a specification", "break down a spec", "create tasks from a PRD", "decompose requirements", "generate a task list from a design document", or mentions wo...
GitHub
codex-agent
Run Codex tasks via the ai_cli Task Tool runner.
GitHub
dspy-optimization-workflow-for-skills-fleet
Use when optimizing DSPy programs in skills-fleet, implementing quality improvements, using optimization API endpoints, or troubleshooting DSPy issues. Complete 3-phase implementation guide (signatures → traini...
GitHub
llm-ops-engineer
Specialist in deploying, fine-tuning, and monitoring Large Language Models (LLMs). Expert in RAG pipelines, vector databases, prompt engineering, and maintaining robust AI infrastructure.
GitHub
agents-md-guidelines
Guidelines for writing small, stable AGENTS.md files. Use when creating, refactoring, or reviewing AGENTS.md.
GitHub
claudeception-setup
How to set up Claudeception continuous learning in a project. Use when: (1) User asks to install or set up Claudeception (2) User wants automatic skill extraction (3) "embedded git repository" warning when addi...
GitHub
voice-command-intelligence
Design and optimize voice commands, handle speech recognition, execute smart actions with context awareness
GitHub
prompt-engineering-specialist
Expert in crafting, optimizing, and evaluating effective prompts for Large Language Models. Specializes in advanced prompting techniques (CoT, ReAct, Few-Shot) to maximize model performance and reliability.
GitHub
xml-standards
XML tag structure patterns for Claude Code agents and commands. Use when designing or implementing agents to ensure proper XML structure following Anthropic best practices.
GitHub
claude-code-memory
Maintain Claude Code memory hygiene by auditing, organizing, updating, and optimizing memory files in `.claude/memory/`. Use when users request memory cleanup, organization, updates, or want to reduce context p...
GitHub
prompt-refiner-claude
Refine prompts for Claude models (Opus, Sonnet, Haiku) using Anthropic's best practices. Use when preparing complex tasks for Claude.
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.
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.