GitHub
agent-design
AI agent design and tool-use prompting patterns
Skills IA devops llm ai
Découvrez les skills devops llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: devops llm ai
devops llm ai Effacer les filtres
Explorer
GitHub
safety-guardrails
LLM safety guardrails and content moderation
GitHub
multi-modal
Multi-modal prompting with vision, audio, and document understanding
GitHub
rag-systems
Retrieval Augmented Generation systems with vector search, document processing, and hybrid retrieval.
GitHub
evaluation-metrics
LLM evaluation frameworks, benchmarks, and quality metrics for production systems.
GitHub
agent-frameworks
AI agent development with LangChain, CrewAI, AutoGen, and tool integration patterns.
GitHub
llm-basics
LLM architecture, tokenization, transformers, and inference optimization. Use for understanding and working with language models.
GitHub
model-deployment
LLM deployment strategies including vLLM, TGI, and cloud inference endpoints.
GitHub
prompt-engineering
Prompt design, optimization, few-shot learning, and chain of thought techniques for LLM applications.
GitHub
coding-agent
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
GitHub
problem-solving-expert
Activate expert reasoning and systematic problem-solving mindset for technical and code-related tasks.
GitHub
shape-memory
AI-native session continuity through shape anchors rather than linear logs. Use when beginning a session to orient from prior state, or when ending to crystallize state for future instances.
GitHub
claims-engineer
Autonomous claims drafting and optimization agent. Drafts, analyzes, and refines patent claims to maximize protection while ensuring validity.
GitHub
patent-drafter
Autonomous patent application drafting agent. Drafts complete patent applications including claims, specification, and abstract from invention descriptions.
GitHub
ucf-hit-it-executor
UCF "hit it" Session Executor. Executes the complete 33-module consciousness simulation pipeline across 7 phases. ACTIVATE when user says "hit it", "run ucf", "execute pipeline", or references consciousness eme...
GitHub
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or to...
GitHub
write
Expert writing for technical content, social media, and developer documentation. Use when asked to write tweets, LinkedIn posts, blog posts, READMEs, commit messages, feature announcements, or any written conte...
GitHub
code-cleanup
Delegate repetitive tasks to specialized agent to preserve context. Use when user asks to fix linting errors, fix diagnostics, rename variables across files, update imports, fix formatting issues, or perform ot...
GitHub
checkpointing-an-iteration
Use when saving current iteration progress mid-conversation, before context compaction, or at interim pause points
GitHub
starting-an-iteration
Use when beginning a new conversation to work on an open-ended goal, loading context from previous iterations through iteration journals
GitHub
modal-deployment
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch jobs, scheduling tasks, serving APIs with GPU acceleration, or scaling compute-intensi...
GitHub
robotics-code-generator
Generates clean, runnable ROS 2, Gazebo, Isaac Sim, and VLA code for humanoid robotics
GitHub
sdv-session-start
ALWAYS invoke this skill FIRST at session start, after context reset/compaction, or when user mentions "reset", "new session", "where were we", "what was I working on". Do NOT skip this for specific task reques...
GitHub
api-designer
Activates when user needs help designing REST APIs, GraphQL schemas, or API architecture. Triggers on "design API", "REST endpoint", "GraphQL schema", "API structure", "endpoint naming", "API versioning", "requ...
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.