tech-route-maker

Tech Route Maker

Purpose

Use this skill to turn source materials into evidence-grounded editable technical route diagrams for research and engineering projects across multiple disciplines.

Primary users are researchers, students, academic writers, engineering teams and agent/tool builders preparing paper framework figures, method overview diagrams, thesis proposal routes, defense visuals, course-design diagrams, engineering system routes and workflow pipelines.

Campaign or advertising routes are legacy/experimental use cases. Do not make them the default direction unless the user explicitly asks for them.

Portability

This skill is intentionally agent-agnostic. SKILL.md is the source of truth for Codex/OpenAI-style skill loaders and any agent that understands skill folders. Other adapters in the repository point back here:

• AGENTS.md for generic coding agents.
• CLAUDE.md for Claude-style project context.
• GEMINI.md and .gemini/settings.json for Gemini CLI.
• .cursor/rules/tech-route-maker.mdc for Cursor.
• .github/copilot-instructions.md for GitHub Copilot coding agent.
• .aider.conf.yml for Aider-style workflows.

Default Interaction Policy

Do not interrupt the user with a long sequence of questions, but do not guess domain or delivery preferences from a field-agnostic request.

Before final rendering, explicitly establish the domain context and confirm the requested output format, target medium, layout family and visual style. Present one concise grouped choice with sensible defaults; allow single or multiple output formats. If the source explicitly proves a domain fact, extract it with an evidence locator instead of asking the user to repeat it.

Default behavior:

• Never render a final technical route diagram from a field-agnostic request such as "draw a technical route diagram" without first identifying the discipline, subfield, project type, research object, method family and evaluation logic.
• If source files are available, extract domain context only from explicit source evidence. Ask one concise field-specific clarification question for every material gap rather than silently inventing it.
• If the user asks for a quick draft before the field is complete, mark domain_context.confidence as low, keep missing items in unresolved_questions, and report that the output is not final.
• If the user asks in Chinese for 开题, 课题申报, 项目申请, 基金, 论文技术路线图, or a Chinese research route diagram, prefer the Chinese academic presets below.
• If the user asks for an editable presentation figure, generate pptx, svg and json.
• If the user asks for a paper or research figure, generate svg, pptx and json.
• If the user asks for a maintainable system diagram, generate drawio, svg and json.
• If the user asks for Draw.io, diagrams.net, online editing, import code, copyable code, or "能复制到draw.io的代码", include drawio-code and explain how to paste the XML into diagrams.net.
• If the user asks for documentation output, generate markdown, mermaid and json.
• If the user asks for long-term maintenance, add drawio.
• If the user asks for all formats, render pptx, svg, drawio, drawio-code, excalidraw, mermaid, html, markdown and json.