Eddie0521

When the global wiki root is not bound yet, the user asks to set up or switch the knowledge-base folder, or invokes /wiki-init. Not for ingesting documents, querying existing wiki content, capturing chat, or restructuring.

Full wiki housekeeping pipeline: lint, then consolidate duplicates/stale atoms, then restructure taxonomy if needed. User confirms before each write phase. Not for routine read, capture, or ingest.

Draft an executable skill from wiki procedure/decision atoms. Writes to skills/_drafts/ only — user reviews before merging into skills/ and install.sh. Not for capture, query, or auto-installing skills.

Read from the bound wiki: restore session context before a task, or answer a question from ingested sources and atoms. Uses index, search, peek, and limited full reads. Not for writing to wiki, ingesting files, or taxonomy maintenance.

Write to the bound wiki: save conversation tips, decisions, and preferences, or compile an attached document, paper, codebase, dataset, or image. Not for read-only queries or bulk taxonomy maintenance.

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

Use this skill when the user wants intellectual understanding — learning how or why something works, not getting a task done or soliciting Claude's judgment. Trigger for: - Explicit learning requests: teach, explain, ELI5, walk me through, quiz me, flashcards, "I'm rusty on"; definitions ("what is X") - Terse concept names implying "help me understand this": "Galois theory," "transformers, from scratch" - Confusion signals: "won't stick," "keep mixing these up," "not getting it" - Learning-path questions: prerequisites, sequencing, what to study before X - Conceptual questions about mechanisms, causes, or dynamics Don't trigger for: - Tasks: coding, writing, calculation, translation, factual lookup, news updates - Personal troubleshooting; resource/textbook recommendations - Claude's evaluative verdict: opinion prompts ("do you think X", "settle this", "honest take", "is X dead / still taken seriously") and interpretive takes ("was X really as harsh as people say")

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

跨 AI Coding Agent 会话同步工具。在 OpenCode、Claude Code、Codex 之间迁移会话历史，保留完整对话上下文。 触发条件： - 用户说"迁移会话"、"导出到 XX"、"同步历史" - 用户说"把 X 的会话迁移到 Y" - 用户需要在不同 Agent 之间切换工作 - 用户说"备份会话"或"迁移到 [OpenCode/Claude Code/Codex]" - 用户询问"怎么在另一个 Agent 里继续这个对话" 使用前必须确认： 1. 源 Agent（会话来源） 2. 目标 Agent（会话去向，可多选） 3. 要同步的会话 ID（最多 10 个） 注意：agentsync 是一个独立的 CLI 工具，需要已安装到系统 PATH 中。

OpenRouter Fusion-style deliberation for complex tasks that benefit from independent parallel subagents and comparative judging. Use when the user explicitly asks for Fusion, OpenRouter Fusion, parallel subagents, panel review, multi-agent deliberation, judge synthesis, or when complex research, architecture, product, paper review, high-stakes reasoning, critique, or multi-sided comparison would be materially improved by fan-out, collect, judge, and final synthesis.

搜索互联网与抓取 URL 内容。搜索级联 Exa→AnySearch→Tavily；抓取支持网页/PDF/GitHub/arXiv 论文全文级联。供其他 skill 或 agent 通过 CLI 调用。