Done in one command: read paper → generate interpretation → mint into card. Supports multiple papers in parallel.
Parameters
| Parameter | Description |
|---|---|
| No parameters | Paper links/files already provided in the conversation |
-c |
Switch the card template to multi-card mode (default -l long image) |
-i |
Switch the card template to infographic mode |
Execution
1. Collect the paper list
Extract all paper sources from the user message (arXiv URLs, PDF paths, paper titles, etc.).
2. Process each paper in parallel
For each paper, start an Agent subagent; each subagent executes two steps in sequence:
Step A — Read the paper (paper-interpretation):
Call the Skill tool to execute paper-interpretation, passing in the paper's source. Wait for completion and obtain the generated org file path.
Step B — Mint the card (card):
Read the org file generated in Step A, call the Skill tool to execute card(default -l, or per the template parameters 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 sequential (paper first, then card), but multiple papers run in parallel
- The respective quality standards, red lines, and taste guidelines of ljg-paper and ljg-card remain unchanged
- The card content comes from the generated org file, not the original paper