llm-evaluation
自動メトリクス、人間によるフィードバック、およびベンチマークを使用して、LLMアプリケーションの包括的な評価戦略を実装します。LLMのパフォーマンスをテストし、AIアプリケーションの品質を測定し、または評価フレームワー...
发现 content media llm ai 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
自動メトリクス、人間によるフィードバック、およびベンチマークを使用して、LLMアプリケーションの包括的な評価戦略を実装します。LLMのパフォーマンスをテストし、AIアプリケーションの品質を測定し、または評価フレームワー...
Creates audio podcasts from text using browser text-to-speech. Use when user mentions podcast, audio conversation, dialogue, spoken content, voice narration, audio book, or text-to-speech generation. Supports m...
Guide Claude through creating well-structured Agent Skills following best practices. Use when creating new Skills, authoring SKILL.md files, or when the user asks to build a Skill for Claude Code.
Establishes SDD methodology - workflow routing, process discipline, spec-first principle, and skill discovery. Use when starting any SDD conversation to determine which workflow skill to invoke.
Transform markdown knowledge repositories into Claude skills. Analyzes knowledge bases, generates SKILL.md files with appropriate loading strategies, and packages distributable skills. Use when creating skills...
Use when starting from rough ideas - refines concepts into executable specifications through collaborative questioning, alternative exploration, and incremental validation, use this skill when called from a com...
Transforms technical documents into adaptive learning sessions with just-in-time prerequisite assessment, foundation building via web search, and verified understanding through quizzes and exercises. Use when u...
A guide to creating Claude Code Skills.
Analyze and optimize skill frontmatter for reliable automatic invocation. Use this skill when: (1) improving an existing skill's description for better triggering, (2) diagnosing why a skill isn't being invoked...
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...
专业的LangGraph AI应用开发技能,提供从概念到生产的完整开发指导。基于Context7最新调研,涵盖StateGraph设计、多代理协作、RAG系统实现、生产部署等核心场景。使用此技能构建有状态、多参与者、长期运行的AI代理应用。
Execute WASM-based skills mounted to virtual paths. Use this skill when the user requests skill execution such as "Execute the RAG skill", "Run the analytics skill", or "Call the skill at this path".
Use this skill when asked to create, refine, analyze, or optimize prompts for Large Language Models (LLMs). This skill ensures adherence to prompt engineering best practices and enforces a rigorous design workf...
Prompt engineering expert that helps users craft optimized prompts using 57 proven frameworks. Use when users want to optimize prompts, improve AI instructions, create better prompts for specific tasks, or need...
{ { description } }
The reference framework to generate, compile, and lint greenfield prompts that conform to the Agnostic Prompt Standard (APS) v1.0.
Add a new AI provider to agentconfig.org's comparison system. Use when integrating a new coding assistant (e.g., Cursor, Claude Desktop, GitHub Copilot alternative) with proper type system updates, implementati...
AI collaboration workflow plugin - Implements automated collaborative development process between Claude and Copilot through structured 5-stage workflow
Expert technical writer for Logseq Template Graph project. Generates comprehensive, accurate, and well-structured documentation for modules, features, guides, and APIs. Activates when asked to "write docs", "do...
AI-powered media production pipeline using Nano Banana Pro (images), KLING AI (video/transitions), and ElevenLabs (voiceover). Use when creating video content, product demos, social media assets, or any multime...
Summarize conversation to start a new one
Autonomous iteration execution guide for PRP Ralph loops. Use when .claude/prp-ralph.state.md exists, when continuing Ralph iterations, or when executing plans autonomously until all validations pass. Provides...
Comprehensive LLM audit. Model currency, prompt quality, evals, observability, CI/CD. Ensures all LLM-powered features follow best practices and are properly instrumented. Auto-invoke when: model names/version...
Create and manage reusable agent skills with proper structure and frontmatter
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。