using-llm-specialist
LLM specialist router to prompt engineering, fine-tuning, RAG, evaluation, and safety skills.
发现 部署与运维 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。
LLM specialist router to prompt engineering, fine-tuning, RAG, evaluation, and safety skills.
Router for simulation math - ODEs, state-space, stability, control, numerics, chaos, stochastic
Route to the right UX skill based on your task and platform context
Routes to appropriate Python specialist skill based on symptoms and problem type
The architecture selection router for CNNs, Transformers, RNNs, GANs, GNNs by data modality and constraints
Mandatory protocol for all SME (Subject Matter Expert) agents. Defines fact-finding requirements, output contracts, confidence/risk assessment, and qualification of advice.
Use when user asks about E2E testing, performance testing, chaos engineering, test automation, flaky tests, test data management, or quality practices - routes to specialist reference sheets with deep expertise...
Customize the retail agent for different use cases. Use when adapting for different business types, industries, or output formats, or when modifying prompts, adding verticals, or changing the analysis focus.
Troubleshoot ADK errors and issues. Use when encountering API errors, model overloaded errors, state issues, tool failures, authentication problems, or unexpected agent behavior.
Learn ADK concepts and understand the retail agent pipeline. Use when asking how the agent works, what ADK is, wanting to understand the architecture, state flow, or individual agent purposes.
Guide for creating custom ADK tools. Use when adding new function tools, working with ToolContext, saving artifacts, or integrating external APIs into the agent pipeline.
Guide for adding new agents to the ADK pipeline. Use when creating a new LlmAgent, SequentialAgent, or ParallelAgent, or when extending the pipeline with additional processing stages.
Persistent memory system for AI agents running on Cloudflare's edge network. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when yo...
Complete Playwright test authoring workflow with Verdex MCP tools. Three phases - explore apps interactively to map user journeys, build stable role-first selectors via progressive DOM exploration, write idioma...
Write technical Q&A responses as markdown files to Claude Overflow. Use for programming questions, code explanations, debugging help, API usage. The response becomes a permanent archived answer viewable in a we...
Automates reading, searching, drafting, and sending emails AND calendar events in Classic Outlook on Windows using local COM automation. Use this skill when the user asks to process Outlook emails, create draft...
Frontend development skill for Quest Keeper AI Tauri application. Use when working on React components, Zustand stores, Three.js battlemaps, TailwindCSS styling, or Tauri shell integration. Triggers on mentions...
Test-Driven Development combined with emergent playtesting for Quest Keeper AI. Use when running playtest sessions, writing tests, debugging game feel issues, or following the RED-GREEN-REFACTOR cycle.
Version control discipline for Quest Keeper AI development. Enforces the "commit early, commit often" pattern.
Master orchestration skill for Quest Keeper AI development. Use when working on ANY part of Quest Keeper AI - coordinates between frontend (Tauri/React), backend (rpg-mcp), and documentation. Triggers on any me...
Quick single email analysis - read metadata, content summary, and list attachments without extracting them.
Deep attachment analysis with extraction, importance classification, and content analysis for emails and threads.
Analyze complete email thread with conversation context, timeline, participants, and attachments tracking.
Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.
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。