GitHub
rag-systems
Retrieval-Augmented Generation - chunking strategies, embedding, vector search, hybrid retrieval, reranking, query transformation. Use when building RAG pipelines, knowledge bases, or context-augmented applicat...
Skills IA research llm ai
Découvrez les skills research llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: research llm ai
research llm ai Effacer les filtres
Explorer
GitHub
developing-test-driven
AI agent practices test-first development with the Red-Green-Refactor cycle for confident, well-designed code. Use when implementing features, fixing bugs, or establishing testing practices.
GitHub
foundation-models
Understanding Foundation Models - architecture, sampling parameters, structured outputs, post-training. Use when configuring LLM generation, selecting models, or understanding model behavior.
GitHub
brainstorming-ideas
AI agent generates diverse solutions through structured divergent thinking and systematic exploration frameworks. Use when exploring options, solving problems creatively, or generating alternatives.
GitHub
finishing-development-branches
AI agent completes development branches with comprehensive quality gates, clean git history, and thorough PR preparation. Use when wrapping up features, preparing for merge, or finalizing PRs.
GitHub
evaluation-methodology
Methods for evaluating AI model outputs - exact match, semantic similarity, LLM-as-judge, comparative evaluation, ELO ranking. Use when measuring AI quality, building eval pipelines, or comparing models.
GitHub
ai-system-evaluation
End-to-end AI system evaluation - model selection, benchmarks, cost/latency analysis, build vs buy decisions. Use when selecting models, designing eval pipelines, or making architecture decisions.
GitHub
solving-problems
AI agent applies a 5-phase systematic framework for tackling complex problems when conventional approaches fail. Use when stuck, blocked, or troubleshooting issues.
GitHub
managing-databases
AI agent performs database administration tasks including backup/restore, monitoring, replication, security hardening, and maintenance operations. Use when managing production databases, troubleshooting perform...
GitHub
thinking-sequentially
AI agent structures complex reasoning through numbered thought sequences with explicit dependencies. Use when facing multi-step problems, complex debugging, or architectural decisions.
GitHub
writing-plans
AI agent creates structured implementation plans with task breakdown, dependency mapping, risk assessment, and file-level detail. Use when planning features, projects, or complex implementations.
GitHub
training-data
Training data management including labeling strategies, data augmentation, handling imbalanced data, and data splitting best practices.
GitHub
infographic-creator
Create beautiful infographics based on the given text content. Use this when users request creating infographics.
GitHub
deck-creator
Create, update, and translate Dify X Reveal.js slide decks in this repo. Use when asked to draft slides, extract outlines, or maintain bilingual CN/EN parity for the ctrip/paypal/pupu/milvus/aispeech/dentsply/o...
GitHub
deployment-management
Managing LangGraph Cloud deployments through listing, filtering, and cleanup operations. Use when managing test deployments, cleaning up orphaned resources, filtering by name patterns, or handling bulk deletion...
GitHub
agent-comms
Send messages to other Claude Code sessions via tmux. Hand off complex debugging context, get second opinions, share detailed technical findings across sessions.
GitHub
alexa-cli
Control Amazon Echo/Alexa devices via the `alexacli` CLI. Use when the user asks to speak/announce on Echo devices, send voice commands to Alexa, control smart home devices, list Alexa devices, or trigger routi...
GitHub
branch-session
Branch the current Claude Code session into a new tmux session using --resume. Creates a parallel conversation that can diverge independently. Use when you want to explore an alternative approach without losing...
GitHub
project-spawn
Spawn a new Claude Code session in a project directory with context handoff. This skill should be used when discussion shifts to a different project/repo and the user wants to work on it in a dedicated session....
GitHub
exploring-knowledge-graph
Guidance for deep knowledge graph traversal across memories, entities, and relationships. Use when needing comprehensive context before planning, investigating connections between concepts, or answering "what d...
GitHub
mcp-tools-as-code
Convert MCP servers to typed TypeScript APIs for efficient code execution. Reduces token usage by 98%+ by transforming tool calls into programmatic access. Use when building agents that need to interact with mu...
GitHub
deep-research
Enables automatic deep research mode with comprehensive analysis when trigger phrases are detected
GitHub
user-memory
Long-term user profile memory that persists across Claude Code sessions
GitHub
prompt-engineering
Expert guidance for crafting effective LLM prompts using proven techniques like chain-of-thought and few-shot learning
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.