发现 Skills

Guide for outputting React/TSX components by prioritizing reusable sub-components, controlling length, and declaring them as const before the main component to ensure clear structure and maintainability.

[Applies to: **/*.php] Definitive guidelines for using Guzzle HTTP client in PHP, focusing on robust client configuration, effective middleware, PSR-18 interoperability, and testability.

[Mandatory reference when adding settings] Required steps when adding a new setting (e.g., v-switch / v-select) to KonomiTV. You must add entries to SettingsStore.ts, Settings.ts, config.py, and Settings/*.vue.

Interview-based system for creating specialized Claude Code agents. Use when users want to create a Claude Code agent, need help defining agent roles and responsibilities, mention "create an agent" or "build an agent", or want to generate a CLAUDE.md file for agentic coding workflows. Guides through interactive interview to gather requirements and generates complete agent configurations following Claude Code best practices.

This Skill guides users to write academic papers according to the submission requirements of Tongji Journal (2021.04 edition), covering detailed specifications for title, abstract, keywords, main text, figures, tables, equations, references, and other elements.

个人认知框架系统。当涉及目标规划、决策建议、项目方向、工作方式优化时触发，或用户显式调用"/telos"。加载完整画像提供个性化响应，支持画像进化和定期复盘。

Use when porting OpenGL/DirectX to Metal - translation layer vs native rewrite decisions, migration planning, anti-patterns

Comprehensive Clawdbot configuration and skills system management. Use when working with Clawdbot setup, configuration files, creating/modifying AgentSkills-compatible skills with YAML frontmatter, troubleshooting agent behavior, managing channels, workspace, sandbox, or multi-agent routing.

Uses TwexAPI from Hermes Agent for X research, monitoring, and approval-gated actions. Use when the user requests X data or an approved X action. Trigger with "search X", "monitor X", "post tweet", or "X trends".

This skill should be used when the user asks to "add a task for Ralph", "list Ralph tasks", "remove Ralph task", "setup Ralph tasks", or mentions ralph-tasks, task queue for AI agent, or autonomous task management. Manages a JSON-based task queue for Ralph autonomous loop.

将指定的 skill 发布到 GitHub 供他人使用。当你想要将本地创建的 Hermes skill 转换为 Claude Code/OpenCode 可用的格式，并同步到 ~/Documents/dev/skills 项目推送到 GitHub 时使用此 skill。传入要发布的 skill 名称作为参数。

Automatically synchronize README.md with actual project components. Scans the .claude directory and updates Agents, Skills, Hooks, and Commands sections.

AgenticRevit 플러그인 빌드 및 배포 자동화 스킬

Automatically execute Grafix art iterations (N runs, M parallel) with agent-authored outputs and save artifacts under sketch/agent_loop. In this mode, creating a new plan.md is not required.

Use when brainstorming ideas, stuck on a problem, exploring alternatives, or needing creative input - provides structured creativity methods (SCAMPER, Six Thinking Hats, Mind Map), Multi-Agent parallel thinking, and concept collision for unexpected sparks. Don't use for mechanical execution tasks

Create professional videos with AI at no cost — NemoVideo is the free AI video maker that produces marketing videos, social content, educational materials, product showcases, and brand stories from text descriptions, photos, or clips. No watermark on output, no subscription required to start, no editing software needed. Describe your video and receive polished content with AI visuals, voiceover, captions, music, and multi-platform export. Free video maker AI, make video free online, AI video creator no cost, free video generator, create video free, no watermark video maker, free online video editor AI.

A skill that retrieves CodeRabbit review comments, uses AI to automatically fix them, marks them as resolved, and pushes the changes.

Automatically convert arXiv papers to well-structured Markdown documentation. Invoke with an arXiv ID to fetch materials (LaTeX source or PDF), convert to Markdown, and generate implementation-ready reference documentation with preserved mathematics and section structure.

Tool selection guide and legacy mapping for Unblocked search tools. Use this skill whenever you're unsure which Unblocked tool to call; when a tool call fails because a tool isn't found or isn't available; when you encounter references to deprecated tools such as data_retrieval, research_task, or unblocked_context_engine; or when a fine-grained tool like context_search_code, context_search_prs, context_query_issues, context_query_prs, or context_get_urls isn't available in your current environment. This skill explains what's available where and how to fall back gracefully.

Content-adaptive wisdom extraction — detects what domains exist in content and builds custom sections (not static IDEAS/QUOTES). Produces tailored insight reports from videos, podcasts, articles. USE WHEN extract wisdom, analyze video, analyze podcast, extract insights, what's interesting, extract from YouTube, what did I miss, key takeaways.

Decompose problems into axioms, challenge inherited assumptions, and reconstruct from verified truths. Use when you need first-principles thinking, fundamental re-evaluation, root-cause analysis, decomposition, challenging assumptions, or rebuilding from scratch.

TAILWIND documentation assistant

나노바나나 3.0 프로를 사용해 인스타그램 카드뉴스와 유튜브 썸네일을 생성합니다. "카드뉴스 만들어줘", "썸네일 생성해줘" 요청 시 사용합니다.

Use when generating detailed, technical UI prompts for designers or AI tools (v0, Bolt) that require precise specifications, tokens, and comprehensive state definitions.