Merge supplemental textbook sections into a primary book JSON using Python fingerprinting.
npx skills add https://github.com/shuff57/agent-evo --skill book-merge
Please help me install this Agent Skill. Skill: book-merge Source: https://github.com/shuff57/agent-evo/tree/main/skills/.archive/book-merge Command: npx skills add https://github.com/shuff57/agent-evo --skill book-merge
This Skill simplifies the process of merging content from multiple textbook sources into a single chapter, especially after section matching has produced a mapping file and before remastering.
Run the book-merge skill with the primary and supplemental JSON files:
python3 scripts/workflows/merge_from_placement.py \
--primary ".../ahss_ch1.json" \
--supplemental ".../os_ch1.json" \
--placement ".../placement_ch1_v2.json" \
--output ".../merged_ch1_v2" \
--chapter 1
High-intent search queries and answers about installing and using this skill.
You can merge textbook content without AI by using Python-based fingerprinting to detect duplicate sections and placement rules to integrate supplemental book JSON files into a primary textbook.
The best way to detect duplicate sections during academic content merging is to use Python fingerprinting, which identifies matching content across supplemental and primary book JSON files to prevent redundant insertions.
You integrate supplemental textbook sections into a primary book JSON by running a Python script that applies a placement map, inserting unique content while skipping duplicates identified by fingerprinting.
Yes, you need a placement map file to merge textbook chapters because it provides the specific insertion rules required to place unique supplemental sections into the primary book JSON accurately.
Yes, you can use Python scripts to combine textbook JSON files for academic publishing by executing the merge workflow to process primary, supplemental, and placement inputs into a single output file.
You skip AI for section matching during textbook content integration to avoid AI reliance, instead using deterministic Python fingerprinting and placement rules to achieve accurate and reproducible section merges.
shuff57Determine optimal insertion points for supplemental textbook content within primary sections.
Embers-of-the-FireAutomate NeurIPS-format academic paper reviews using three personas and aggregated JSON reports.
felipemlanna1Parse Google Maps leads CSV and insert them into a SQLite database.
shuff57Match textbook sections between primary and supplementary JSON files.