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。
Specialized guidance for developing 2D farming RPG games in Unity with C#. Use when working on farm simulation mechanics, crop systems, NPC interactions, inventory management, day/night cycles, seasonal systems...
Git operations mastery. Atomic commits, rebase/squash, history search (blame, bisect, log -S). Triggers on 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'.
ULTRAWORK MODE - Maximum capability activation. Use when you need parallel agent orchestration, strict verification, and zero tolerance for incomplete work. Triggers automatically on 'ultrawork' or 'ulw' in mes...
Maximum search effort mode. Launch multiple parallel agents for exhaustive codebase and documentation search. Use when you need comprehensive search results.
Deep analysis mode. Gather comprehensive context before diving deep. Use for investigation, debugging, and understanding complex systems.
Access Figma designs, extract design systems, and retrieve component specifications. Use when implementing UI from Figma mockups, extracting design tokens, or analyzing design files.
Monitor applications, investigate performance issues, and analyze observability data in New Relic. Use when the user needs APM metrics, error tracking, infrastructure monitoring, or incident analysis.
Comprehensive code review methodology. 4 layers (Correctness, Security, Performance, Style), severity classification, 80% confidence threshold.
Terminal orchestration via tmux. Use for long-running processes, server management, parallel terminal sessions, and background task monitoring.
Enforce cost-aware MCP usage. Use when a task might trigger heavy external tools, web search, or broad context expansion. Prevents token burn by ensuring MCPs are only used when local context is insufficient.
Visual & UI philosophy (The 5 Pillars of Intentional UI). Apply to styling, layout, colors, typography, animations. Avoid "AI slop" aesthetics.
Browser automation via Playwright MCP. Use for verification, browsing, web scraping, testing, screenshots, and all browser interactions.
Token optimization and context window management strategies. Load for long sessions, complex tasks, or when approaching context limits.
4-phase debugging framework preventing "guess-and-check" fixing. Load when debugging fails or for complex bug investigation.
Internal logic and data flow philosophy (The 5 Laws of Elegant Defense). Apply to backend, hooks, state management, and any code where functionality matters.
This skill should be used when users need to scrape content from websites, extract text from web pages, crawl and follow links, or download documentation from online sources. It features concurrent URL processi...
Search previous Claude Code conversations for facts, patterns, decisions, and context using semantic or text search
Clean code principles, error handling patterns, and coding standards for PACT Code phase. Use when: implementing features, refactoring code, reviewing code quality, establishing coding conventions, or handling...
Persistent memory for PACT agents. Save context, goals, lessons learned, decisions, and entities. Semantic search across sessions. Use when: saving session context, recalling past decisions, searching lessons....
Run the full CI pipeline (format, lint, typecheck, test, validate-docs)
Run comprehensive live API tests against Honeycomb. Manages test environments, validates documentation snippets, and tests CRUD operations. Use when you need to verify the SDK against the real API.
Execute comprehensive end-to-end tests for the Meal Planner application using Claude in Chrome browser automation. Supports regression testing (checklist-based) and exploratory testing (discovery-focused). Use...
Show status of all active ClickUp agents and worktrees
Add a new task to ClickUp directly (no AI processing)
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。