发现 数据与 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。
Runs performance benchmarks for SDL3 HammerEngine and detects regressions by comparing metrics against baseline. Use when testing performance-sensitive changes to AI, collision, pathfinding, particle systems, o...
Run Intent validation and sync checks. Triggers intent-validate and intent-sync agents. Use /intent-check for full check, or /intent-check --validate/--sync for specific checks.
Assess if IDD fits your project and learn about Intent-Driven Development. Use /intent-assess to evaluate project suitability or /intent-assess --learn for IDD education.
Generate human-readable report from Intent files. Converts technical Intent specs into readable documents for stakeholders, team members, or documentation. Supports multiple output formats.
Share your IDD adoption story. Through structured interviewing, create blog posts about Intent-Driven Development experiences, lessons learned, and best practices. Supports multiple languages and formats.
Initialize IDD structure in a project. Checks existing state, creates directory structure, and generates templates. Use /intent-init to set up Intent-driven development in current project.
Transform vague ideas into implementation-ready specifications through structured interviewing. Use when user describes a new feature/product idea, has a problem to solve, or needs to document requirements. Pro...
Interactive Intent approval. Review sections and mark status (locked/reviewed/draft). Use /intent-review to review a specific file, or /intent-review to review Intent in current directory.
Expert Go developer guide. Use when writing, debugging, or reviewing Go code.
Helps choose the right Claude Code extension mechanism (slash commands, skills, subagents, or hooks) for a given use case. Use when discussing how to extend Claude Code, automate workflows, or implement custom...
Generate and manage cross-platform Ansible playbooks for development environment setup across macOS, Linux, and Termux. Use when working with development environment automation, package installation configurati...
Comprehensive code review checklist. Use when asked to review code, PRs, pull requests, or before committing changes.
Run and verify backend tests for the FastAPI/Python application.
Explains code with visual diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when the user asks "how does this work?"
Start, stop, and manage the Orchestra application and its services.
Systematically explore codebases using search and LSP to understand code structure, intent, and behavior. READ_ONLY mode - no file modifications.
Meta-improvement skill that analyzes conversation context and uncommitted git changes to propose improvements to the AI agent ecosystem itself (agents, skills, commands). Use when the user asks to reflect on th...
Run and verify frontend tests for the React/Vite application.
This skill should be used when the user asks to "create UI component", "build Blazor page", "add MudBlazor component", "style MudBlazor", "fix CSS isolation", "use ::deep selector", "customize theme", "support...
This skill should be used when the user asks to "create module", "add module", "module structure", "use Res type", "return Res", "Res.Ok", "Res.Fail", "IsFailed pattern", "module registration", "module dependen...
Fetch video metadata from YouTube URLs using yt-dlp. Use when the user provides a YouTube URL or asks to get details from a YouTube video.
Monitor a PR through CI, reviews, and merge conflicts until ready for human review. Use when user says "monitor PR", "watch PR", "wait for CI", or wants automated PR workflow. Creates PR if needed, then monitor...
Explains how Claude Code works in containers with zero credentials via the clauderon proxy. Use when testing Claude in containers, debugging authentication issues, or understanding the zero-trust proxy architec...
Systematically bump package versions in pnpm monorepos by analyzing pnpm-lock.yaml, walking dependency trees, and finding the optimal parent package to upgrade. Use when the user asks to bump a package to meet...
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。