viz
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseViz Pack — Multi-Mode Visual Dispatcher
Viz Pack — 多模式可视化调度工具
Transform any content into a professional visualization via one of four output modes. This skill is a dispatcher: it resolves the active mode, loads the mode-specific workflow from , and executes it.
references/可通过四种输出模式将任意内容转换为专业可视化内容。该技能作为调度工具:它会解析激活模式,从加载对应模式的工作流并执行。
references/Step 1: Resolve the active mode
步骤1:解析激活模式
Inspect the invocation in this priority order:
-
Positional argument. The first positional argument is. If
$0matches$0,diagram,infographic, orvisualize, use it as the mode. Remaining arguments (publishafter the mode token) are the optional content reference (URL, file path, or inline text).$ARGUMENTS -
Keyword trigger. Ifis empty or not a valid mode, scan the most recent user message for a trigger keyword and map it to a mode:
$0Trigger keyword(s) Mode "diagram it", "excalidraw this", "draw a diagram of this" diagram"nano this" infographic"vis it" visualize"ver it", "hey it", "heygenverse this", "put this on heygenverse as a visual" publish -
Ask the user. If neither signal yields a mode, stop and ask which output to produce —(Excalidraw),
diagram(Swiss Pulse PNG via Gemini),infographic(inline Visualizer widget), orvisualize(interactive Swiss Pulse app on HeyGenverse). Do not guess.publish
Invocation context injected at render time: mode token is , content reference is .
$0$ARGUMENTS按以下优先级检查调用指令:
-
位置参数。第一个位置参数为。若
$0匹配$0、diagram、infographic或visualize,则将其作为模式。剩余参数(模式标识后的publish)为可选的内容引用(网址、文件路径或内嵌文本)。$ARGUMENTS -
关键词触发。若为空或不是有效模式,则扫描用户最新消息中的触发关键词并映射到对应模式:
$0触发关键词 模式 "diagram it"、"excalidraw this"、"draw a diagram of this" diagram"nano this" infographic"vis it" visualize"ver it"、"hey it"、"heygenverse this"、"put this on heygenverse as a visual" publish -
询问用户。若以上两种方式均无法确定模式,则停止操作并询问用户需要生成哪种输出——(Excalidraw图表)、
diagram(通过Gemini生成Swiss Pulse PNG图片)、infographic(内嵌式Visualizer组件)或visualize(在HeyGenverse上发布交互式Swiss Pulse应用)。请勿自行猜测。publish
渲染时注入的调用上下文:模式标识为,内容引用为。
$0$ARGUMENTSStep 2: Load the mode workflow
步骤2:加载模式工作流
Read the reference file for the resolved mode and follow its workflow end-to-end:
| Mode | Workflow file |
|---|---|
| |
| |
| |
| |
Read the file on every invocation — do not execute from memory — so any updates to the workflow are applied.
读取对应模式的参考文件并完整执行其工作流:
| 模式 | 工作流文件 |
|---|---|
| |
| |
| |
| |
每次调用时都需读取文件——请勿依赖内存执行——确保工作流的任何更新都能生效。
Step 3: Acquire the content (shared across modes)
步骤3:获取内容(所有模式通用)
All four modes accept content from the same sources. Resolve the content target in this priority order:
- If contains a URL → retrieve via
$ARGUMENTS. If blocked (429/403), fall back toweb_fetchwith key phrases to get the content from search snippets.web_search - If points to an uploaded file → read from
$ARGUMENTSusing/mnt/user-data/uploads/for PDF,pdfplumberfor DOCX,python-docxfor CSV/TSV, direct read for TXT/MD/HTML.pandas - If is inline text → use it directly.
$ARGUMENTS - Else scan the current conversation for a referenced source (uploaded file, URL previously shared, meeting transcript at , pasted text) and use that.
/mnt/transcripts/
Summarize to core structure if the content exceeds 3,000 words for modes that pipe text into an LLM () or 5,000 words for modes that assemble visuals client-side (, , ).
infographicdiagramvisualizepublish四种模式均支持从以下来源获取内容。按以下优先级解析内容目标:
- 若包含网址 → 通过
$ARGUMENTS获取。若请求被拦截(429/403状态码),则回退至web_fetch,通过关键短语从搜索片段中获取内容。web_search - 若指向已上传文件 → 使用对应工具读取
$ARGUMENTS路径下的文件:PDF用/mnt/user-data/uploads/,DOCX用pdfplumber,CSV/TSV用python-docx,TXT/MD/HTML直接读取。pandas - 若是内嵌文本 → 直接使用该文本。
$ARGUMENTS - 否则,扫描当前对话中的引用来源(已上传文件、之前分享的网址、下的会议记录、粘贴的文本)并使用该来源。
/mnt/transcripts/
若内容超过指定字数,需提炼核心结构:对于将文本输入LLM的模式(),字数上限为3000字;对于客户端侧生成可视化的模式(、、),字数上限为5000字。
infographicdiagramvisualizepublishStep 4: Execute the loaded workflow
步骤4:执行加载的工作流
Follow the steps in the loaded workflow file exactly. Do not substitute tools, colors, typography, or output formats across modes.
严格按照加载的工作流文件中的步骤执行。请勿跨模式替换工具、颜色、排版或输出格式。
Non-Negotiable Rules
不可违反的规则
- Never respond with a plain-text summary instead of the requested visual output.
- Never swap output format across modes (e.g., do not emit Excalidraw when was requested).
mode=publish - Never skip reading the mode-specific workflow file — every mode has non-obvious tool contracts and design constraints.
- Never use colors outside each mode's palette (Excalidraw: 2–3 neutrals; Swiss Pulse modes: black/white + #0066FF only).
- 切勿以纯文本摘要替代请求的可视化输出。
- 切勿跨模式调换输出格式(例如,当请求时,请勿生成Excalidraw内容)。
mode=publish - 切勿跳过读取模式专属工作流文件——每个模式都有非显性的工具约定和设计约束。
- 切勿使用超出各模式调色板的颜色(Excalidraw:2-3种中性色;Swiss Pulse模式:仅黑白+#0066FF)。
Error Handling
错误处理
- Mode unresolved → execute Step 1.3 and ask the user.
- Missing workflow file → stop and report the missing path ().
references/mode-<mode>.md - Missing tool integration (,
Excalidraw:*,visualize:*) → report the specific missing integration and ask whether to proceed with an alternative mode.HeyGenverse:* - Missing (mode
GEMINI_API_KEYonly) → stop and ask for the key before continuing.infographic - Content acquisition fails (empty, unreadable, blocked URL) → report the specific failure and request a different source.
- 模式未解析 → 执行步骤1.3,询问用户。
- 工作流文件缺失 → 停止操作并报告缺失的文件路径()。
references/mode-<mode>.md - 工具集成缺失(、
Excalidraw:*、visualize:*)→ 报告具体缺失的集成,并询问是否改用其他模式继续。HeyGenverse:* - 缺失(仅
GEMINI_API_KEY模式)→ 停止操作并请求提供密钥后再继续。infographic - 内容获取失败(内容为空、无法读取、网址被拦截)→ 报告具体失败原因,并请求提供其他来源。