latex-exporter
Skill10 starsChanged 6 days agoMITView on GitHub
Merges the Markdown reports in `process/` plus the graphics in `process/figures/` into one compilable `.tex` file. Pure standard library — no pandoc, no LaTeX toolchain required to produce the file.
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/chelate-shell.mdcCursor rule
- 3d-modelerSkill
- ai-trace-removerSkill
- bibtex-normalizerSkill
- capstone-labmateSkill
- conflict-detectorSkill
- data-profilerSkill
- document-evolution-trackerSkill
- formula-validatorSkill
- fulltext-extractorSkill
- literature-retrieverSkill
- longitudinal-analysisSkill
- ml-auditorSkill
- multi-dim-managerSkill
- quantitative-validatorSkill
- reference-auditorSkill
- sci-visualizerSkill
- security-guardSkill
- task-organizerSkill
- video-trackerSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
Run this exact form — do not read the source tree:
- Distinctive: line 54
Stdlib only: Never introduce a pandoc dependency.
- Distinctive: line 64
No Markdown to merge fails the gate with a clear message.
- Distinctive: line 70
Only Markdown and the common image formats are handled.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
latex-exporter
Assembles the deliverable .tex. It does not compile it and does not typeset
content you did not write.
- Stage:
processors· Sandbox: no · Dependencies: stdlib only (no pandoc)
Quick Execution
Run this exact form — do not read the source tree:
python scripts/run.py --root <WS> --action export--action processis an alias;--name report.texsets the filename (defaultmerged_report.tex).- The
.texlands in<WS>/results/; the gate in<WS>/process/gates/.
When to use
- The final deliverable must be a single LaTeX file.
- Reports and figures already live under
process/.
When NOT to use
- The document must be compiled to PDF — that needs a LaTeX install.
- The sources are Word or HTML.
Actions
--action | Does | Extra arguments |
export | Merge reports + figures into one .tex | [--name report.tex] |
process | Alias of export | [--name report.tex] |
Hard constraints
- Stdlib only. Never introduce a pandoc dependency.
- Never rewrite the prose — the Markdown is embedded as authored.
Outputs
<WS>/results/merged_report.tex(or--name) — the merged document.<WS>/process/gates/latex-exporter_<ts>.json— the gate result.
Failure handling
- No Markdown to merge fails the gate with a clear message.
- A missing figure file is reported, and the include is written commented out.
Limitations
- No compilation step.
- Only Markdown and the common image formats are handled.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.