GitHub
qa-agent-testing
QA harness for agentic systems: scenario suites, determinism controls, tool sandboxing, scoring rubrics, and regression protocols covering success, safety, latency, and cost.
☆ 31Voir le skill
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
data-analytics-engineering
Analytics engineering for reliable metrics and BI readiness. Build transformation layers, dimensional models, semantic metrics, data quality tests, and documentation. Use when you need dbt or SQL transformation...
☆ 31Voir le skill
GitHub
ai-llm
Production LLM engineering skill. Covers strategy selection (prompting vs RAG vs fine-tuning), dataset design, PEFT/LoRA, evaluation workflows, deployment handoff to inference serving, and lifecycle operations...
☆ 31Voir le skill
GitHub
router-engineering
Master orchestration for routing technical problems through 33 engineering skills - AI/ML, software development, data, APIs, and Claude Code framework
☆ 31Voir le skill
GitHub
claude-code-commands
Create slash commands for Claude Code with $ARGUMENTS handling, agent invocation patterns, and template best practices. Reference for building user-triggered workflow shortcuts.
☆ 31Voir le skill
GitHub
ai-llm-inference
Operational patterns for LLM inference: latency budgeting, tail-latency control, caching, batching/scheduling, quantization/compression, parallelism, and reliable serving at scale. Emphasizes production-grade p...
☆ 31Voir le skill
GitHub
help-center-design
Design AI-first help centers, knowledge bases, FAQs, and learning materials using 2025-2026 best practices
☆ 31Voir le skill
GitHub
ai-mlops
Complete MLOps skill covering production ML lifecycle and security. Includes data ingestion, model deployment, drift detection, monitoring, plus ML security (prompt injection, jailbreak defense, RAG security, p...
☆ 31Voir le skill
GitHub
ai-rag
Complete RAG and search engineering skill. Covers chunking strategies, hybrid retrieval (BM25 + vector), cross-encoder reranking, query rewriting, ranking pipelines, nDCG/MRR evaluation, and production search s...
☆ 31Voir le skill
GitHub
claude-code-agents
Create and configure Claude Code agents with YAML frontmatter, tool selection, model specification, and naming conventions. Reference for building specialized AI subagents that handle complex, multi-step tasks.
☆ 31Voir le skill
GitHub
docs-ai-prd
Write PRDs, specs, and project context optimized for coding assistants (Claude Code, Cursor, Copilot, Custom GPTs). Includes CLAUDE.md generation, session planning, and templates for creating documentation that...
☆ 31Voir le skill
GitHub
claude-code-skills
Comprehensive reference for creating Claude Code skills with progressive disclosure, SKILL.md structure, references/ organization, frontmatter specification, and best practices for modular capability developmen...
☆ 31Voir le skill
GitHub
ai-agents
Production-grade AI agent patterns with MCP integration, agentic RAG, handoff orchestration, multi-layer guardrails, observability, token economics, ROI frameworks, and build-vs-not decision guidance (modern be...
☆ 31Voir le skill
GitHub
context-compression
Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task rather than tokens-...
☆ 31Voir le skill
GitHub
tool-design
Design tools that agents can use effectively, including when to reduce tool complexity. Use when creating, optimizing, or reducing agent tool sets.
☆ 31Voir le skill
GitHub
book-sft-pipeline
End-to-end system for creating supervised fine-tuning datasets from books and training style-transfer models. Covers text extraction, intelligent segmentation, synthetic instruction generation, Tinker-compatibl...
☆ 31Voir le skill
GitHub
project-development
Design and build LLM-powered projects from ideation through deployment. Use when starting new agent projects, choosing between LLM and traditional approaches, or structuring batch processing pipelines.
☆ 31Voir le skill
GitHub
chat-history
Extract and organize Claude Code session history into project .chats directory. Use when users want to document their Claude sessions, export conversation inputs, or maintain a log of instructions given to Clau...
☆ 31Voir le skill
GitHub
mastra-embeded-docs-look-up
Look up Mastra API documentation embedded in node_modules/@mastra/*/dist/docs/ for accurate API signatures. Use for Agent, Workflow, Tool, Memory configuration questions and code validation.
☆ 31Voir le skill
GitHub
create-mastra
Skill for creating AI agent projects using Mastra framework. Guide for adding agents/workflows to TypeScript/JavaScript apps.
☆ 31Voir le skill
GitHub
claude-agent-ruby
Implement or modify Ruby code that uses the claude-agent-sdk gem, including query() one-shot calls, Client-based interactive sessions, streaming input, option configuration, tools/permissions, hooks, SDK MCP se...
☆ 31Voir le skill
GitHub
claudeconnect
Manages ClaudeConnect for sharing context between Claude instances. Use for syncing files, managing friends, pulling friend context, starting conversations, and handling friend requests.
☆ 30Voir le skill
GitHub
reviewing-a11y
Accessibility review orchestrator. Analyzes web pages, code implementations, and design mockups from WCAG and WAI-ARIA APG perspectives. Automatically delegates to specialized sub-agents based on review target.
☆ 30Voir le skill
GitHub
kql-query-authoring
Use this skill when asked to write, create, or help with KQL (Kusto Query Language) queries for Microsoft Sentinel, Defender XDR, or Azure Data Explorer. Triggers on keywords like "write KQL", "create KQL query...
☆ 30Voir le skill
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.