探索开发、内容、数据与办公效率等 AI 技能。先比较用途和仓库热度，再查看技能说明与来源。
Deconstruct problems to fundamental truths and rebuild solutions from scratch. Use when conventional solutions feel wrong, costs seem fixed, you hear 'that's how it's done,' or need breakthrough rather than inc...
Generate game-ready sprites for the Claude Office Visualizer using Nano Banana MCP and ImageMagick. Uses 45-degree front/top-down perspective (NOT isometric) with retro 16-bit pixel art style. Includes validati...
Reference of non-obvious Cardano ledger behaviors that have caused bugs in Dolos. Consult when debugging epoch pots mismatches or implementing new ledger logic.
Read and write files in the shared session workspace. Use this to access files created by any skill — code-agent outputs, office documents, images, and more. All within the same isolated session.
Create a new version release by analyzing changes, bumping version, updating changelogs, committing, tagging, and pushing
Auto-generate OpenAPI 3 documentation for Spring Boot 4.x REST APIs using springdoc-openapi v3.0. Use when API endpoints change, controllers are modified, or user mentions API docs, Swagger, or OpenAPI. Trigger...
Auto-generate OpenAPI 3 documentation for Spring Boot REST APIs using springdoc-openapi. Use when API endpoints change, controllers are modified, or user mentions API docs, Swagger, or OpenAPI. Triggers on @Res...
Monitor Discord channel activity and persist notable items to memory. Run from main session during heartbeat.
Analyze GitHub and Discord signals to prioritize maintainer attention. Use when asked about priorities, what's hot, what needs attention, or project status.
Use when implementing any feature or bugfix, before writing implementation code
Use before ANY git add or git commit — mandatory, no exceptions for subagents, other skills, or automation. Applies when completing implementation, when the user asks to commit, or when changes need separate lo...
Use when the user wants to understand the codebase, find streamlining opportunities, explore architecture, or map module dependencies.
Deep nightly reflection. Self-improvement, research, pattern recognition. Runs in background with no user interaction.
Use this skill when faced with a difficult debugging task where you need to replicate some bug or behavior in order to see what is going wrong.
Auto-fix security issues — remediate hardcoded secrets and common vulnerabilities (TLS bypass, debug mode, XSS, shell injection, Docker :latest). Use when the user wants to automatically fix security findings.
Guide new users through macrodata setup. Creates identity, human profile, and workspace files. Use when get_context returns isFirstRun true, or user asks to set up their profile.
Guide new users through macrodata setup. Creates identity, human profile, and workspace files. Use when get_context returns isFirstRun true, or user asks to set up their profile.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Use only when the user explicitly requests brainstorming, evaluating architecture choices, or comparing options where no single concern dominates
Comprehensive code review methodology with severity classification and confidence thresholds
Criteria for reviewing implementation plans against quality standards
Internal logic and data flow philosophy (The 5 Laws of Elegant Defense). Understand deeply to ensure code guides data naturally and prevents errors.
Guidelines for creating and managing implementation plans with citations
Criteria for reviewing implementation plans against quality standards
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。