Done in one command: read paper → generate interpretation → mint into card. Supports multiple papers in parallel.
Mode
Force NATIVE mode. This workflow is a pure skill pipeline (ljg-paper → ljg-card) and does not need the Algorithm's seven-step process. Directly call the skills according to the execution steps below; do not go through OBSERVE/THINK/PLAN/BUILD/EXECUTE/VERIFY/LEARN.
Parameters
| Parameter | Description |
|---|---|
| No parameters | Paper links/files already provided in the conversation |
-l |
Card mold switches to long-image mode (default -v visual note) |
-i |
Card mold switches to infographic mode |
-c |
Card mold switches to comic mode |
Execution
1. Collect the paper list
Extract all paper sources from the user message (arxiv URL, PDF path, paper name, etc.).
2. Process each paper in parallel
For each paper, start one Agent subagent; each subagent executes two steps in sequence:
Step A — Read paper (ljg-paper):
Call the Skill tool to execute ljg-paper, passing in the source of that paper. Wait for completion, and obtain the path of the generated org file.
Step B — Mint card (ljg-card):
Read the org file generated in Step A, call the Skill tool to execute ljg-card(default -v, or according to the mold parameter specified by the user), using the org file content as input. Wait for completion, and obtain the PNG file path.
3. Summary report
After all papers are processed, output a summary:
════ 论文流完成 ═══════════════════════
📄 {论文标题1}
📝 解读: {org 文件路径}
🖼️ 卡片: {PNG 文件路径}
📄 {论文标题2}
📝 解读: {org 文件路径}
🖼️ 卡片: {PNG 文件路径}
...
Key constraints
- The two steps for each paper must be serial (paper first, then card), but multiple papers run in parallel
- The respective quality standards, red lines, and taste criteria of ljg-paper and ljg-card remain unchanged
- The card content comes from the generated org file, not the original paper