Latex sentence per line
Reusable agent skills for Claude Code, OpenCode, Cursor, and the Vercel skills CLI.
npx -y skills add jacobleft/techang --skill latex-sentence-per-lineAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use when writing, revising, or polishing prose in LaTeX `.tex` files and you want one sentence per line, especially for thesis sections, paper sections, manuscript prose, or any workflow where edited LaTeX prose should be normalized before completion.
SKILL.md
3.1 KB, 601 tokens by cl100k_base, as published. Nobody here has run it
LaTeX Sentence-Per-Line
Keep prose-oriented LaTeX files in one-sentence-per-line format after writing edits.
Overview
This skill makes sentence-per-line formatting a required finishing step for LaTeX writing work. It is for prose-heavy .tex files, not for bibliography files, style files, or TeX fragments dominated by equations, macros, or tables.
When to Use
Use this skill when the user asks to:
- write or revise a LaTeX section,
- polish thesis or paper prose in
.texfiles, - edit introduction, method, experiments, discussion, or conclusion text,
- keep LaTeX prose in one-sentence-per-line style,
- normalize sentence-per-line formatting after content edits.
Do not use this skill for:
.bib,.sty, or.clsfiles,- generated files,
- table-heavy, macro-heavy, or equation-heavy TeX fragments,
- tasks that are not editing prose.
Default Workflow
- Identify which touched files are prose-oriented
.texfiles. - Make the requested writing edits first.
- Run the bundled formatter on the touched prose files:
python3 scripts/apply_sentence_per_line.py path/to/file.tex
For multiple files:
python3 scripts/apply_sentence_per_line.py path/to/intro.tex path/to/conclusion.tex
- Review the resulting diff.
- Repair edge cases manually if abbreviations, citations, math-adjacent prose, or command-heavy sentences were split awkwardly.
- Only then report the task complete.
Safety Rules
- Preserve LaTeX structure and commands.
- Do not run the formatter on non-prose files just because they end in
.tex. - Do not claim completion before the formatter step for qualifying prose edits.
- LaTeX comments beginning with
%are formatter-excluded and should remain untouched. - If the script creates suspicious breaks, fix those lines manually instead of skipping review.
Quick Reference
| Situation | Action |
|---|---|
Editing prose in section.tex | Edit first, then run formatter |
| Editing multiple prose sections | Run formatter on all touched prose files |
| Editing a macro-heavy file | Skip formatter unless the edited region is clearly prose-heavy |
| Suspicious output after formatting | Manually repair affected lines before finishing |
Formatter Behavior
The bundled script inserts a newline after ., !, or ? when the next token begins with an uppercase letter or a LaTeX command. This preserves the existing project behavior instead of broadening scope.
Formatter path:
scripts/apply_sentence_per_line.py
Common Mistakes
- Editing LaTeX prose and forgetting to run the formatter.
- Running the formatter on
.bib,.sty, or.clsfiles. - Assuming every
.texfile is prose-oriented. - Skipping the diff review after formatting.
- Leaving awkward splits around abbreviations or citations uncorrected.
What ships with it: 1 file
1.7 KB alongside SKILL.md, 1 of them executable
scripts/
- apply_sentence_per_line.pyruns1.7 KB