浏览 Qredence 维护的已发布 AI 技能，比较用途与说明，并通过来源仓库了解安装方式。
已收录技能
23收录技能的仓库 Stars 合计
1,013仓库 Forks
122平均每个技能的仓库 Stars
44同一仓库中的多个技能可能共享 Stars，合计包含重复仓库数据。
Comprehensive guide for initializing or reorganizing agent memory and project context. Use when setting up a new project, when the user asks you to learn about the codebase, or when you need to create effective...
Quick reference card for DSPy + Agent Framework integration patterns: typed signatures, assertions, routing cache, and agent handoffs.
Ingest new procedural memory (skills, patterns, docs) into the vector database.
Analyze the current session and consolidate learnings. Use at the end of a session or task.
Semantic search for memory. Use to find solutions, patterns, or context from Chroma Cloud.
Complete guide to the AgenticFleet memory system. Read this first.
Context-aware development assistant for AgenticFleet with auto-learning and dual memory (NeonDB + ChromaDB). Handles development workflows with intelligent context management.
Initialize or hydrate the agent's memory system and verify configuration.
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of ma...
Expert Python backend code reviewer that identifies over-complexity, duplicates, bad optimizations, and violations of best practices. Use when asked to review Python code quality, check for duplicate code, anal...
Comprehensive guide to integrating DSPy with Microsoft Agent Framework in AgenticFleet, covering typed signatures, assertions, routing cache, GEPA optimization, and agent handoffs.
Use when building FastAPI apps with async database operations, complex dependency injection, partial update endpoints, async testing, or converting Python utilities to API endpoints
Comprehensive guidance for FastAPI, Typer, and SQLModel development including patterns, best practices, API design, CLI development, database integration, testing, and common workflows. Use this skill when buil...
Core DSPy fundamentals for signature design, basic modules (Predict, ChainOfThought), and program composition patterns. Use when creating new signatures, building simple DSPy programs, or learning foundational...
Creates and manages ephemeral Neon databases for testing, CI/CD pipelines, and isolated development environments. Use when building temporary databases for automated tests or rapid prototyping.
Rapidly prototype and build modern, responsive web applications from scratch using current frameworks and libraries. Use when you want to quickly create a new web app with full local control, creative flow, and...
Assist with core product management activities including writing PRDs, analyzing features, synthesizing user research, planning roadmaps, and communicating product decisions. Use when you need help with PM docu...
DSPy optimizers (teleprompters), evaluation metrics, and optimization workflows. Use when compiling programs with BootstrapFewShot, KNNFewShot, MIPROv2, GEPA, or defining custom metrics.
DSPy configuration, LM setup, caching, and version management. Use when configuring language models, enabling caching, managing dependencies, or setting up multi-provider configurations.
Use when optimizing DSPy programs in skills-fleet, implementing quality improvements, using optimization API endpoints, or troubleshooting DSPy issues. Complete 3-phase implementation guide (signatures → traini...
Refine prompts for Claude models (Opus, Sonnet, Haiku) using Anthropic's best practices. Use when preparing complex tasks for Claude.
Advanced DSPy modules including ReAct agents, tool calling, output refinement (BestOfN, Refine), and adapters. Use when building agent systems, integrating external tools, or implementing multi-step reasoning.
Implement or extend a user-facing workflow in a web application, integrating with existing backend APIs. Use when the feature is primarily a UI/UX change backed by existing APIs, affects only the web frontend,...
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。