jimezsa/opencolab/projects/SKILLS/latex-paper-writer/SKILL.md
latex-paper-writer
Create, edit, Git-version, compile, and deliver scientific LaTeX papers, reports, and research-derived PDF summaries. Use for venue-aware templates such as ICLR, NeurIPS, ICML, CVPR, ACL, ACM, and IEEE; experiment-result tables; architecture figures or diagrams; deep-research/pro-research/fast-research to PDF summaries; and .tex to PDF builds with latexmk.
- Source repository stars
- 11
- Declared platforms
- 0
- Static risk flags
- 1
- Last source update
- 2026-08-04
- Source checked
- 2026-08-04
Decision brief
What it does—and where it fits
Use this skill when the user wants a scientific paper, survey, technical report, research-derived PDF summary, LaTeX experiment table, or edits to an existing LaTeX document.
Not for
- Tasks that require unconfirmed production actions or broad system permissions.
- Environments where the pinned source and install steps cannot be inspected.
Compatibility matrix
Platform support, with evidence labels
| Platform | Status | Evidence | What to check |
|---|---|---|---|
| Codex | Not declared | No explicit evidence | Portability before use |
| Claude Code | Not declared | No explicit evidence | Portability before use |
| Cursor | Not declared | No explicit evidence | Portability before use |
| Gemini CLI | Not declared | No explicit evidence | Portability before use |
Installation
Inspect first. Install second.
The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.
npx skills add https://github.com/jimezsa/opencolab --skill "projects/SKILLS/latex-paper-writer"Inspect the Agent Skill "latex-paper-writer" from https://github.com/jimezsa/opencolab/blob/f647b8e4c37a18b4bd3443bd4a8f5470ea1b9d09/projects/SKILLS/latex-paper-writer/SKILL.md at commit f647b8e4c37a18b4bd3443bd4a8f5470ea1b9d09. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.
Workflow
What the source asks the agent to do
- 01
Workflow
If the user provides a conference, map it with references/conference-map.md. If no venue is known, use generic-paper, generic-survey, or generic-technical-report.
new paper draft: create a workspace and templateexisting paper edit: inspect and preserve the current structureresearch-to-PDF summary: use findings.md, paper summaries, diagrams, and PDFs - 02
Mission
Given source material for a scientific document:
Select or preserve the right LaTeX template.Create or reuse a Git-controlled paper workspace.Draft or edit the LaTeX sources with grounded claims and citations. - 03
Prerequisites
If latexmk is missing, read references/document-types.md for install guidance and do not claim that compilation succeeded. Only run install commands after the user explicitly approves installing system packages.
git is installed and available in PATH.python3 is installed and available in PATH.latexmk is preferred for PDF builds: - 04
Hard Requirements
Read references/conference-map.md before choosing a venue template.
Read references/conference-map.md before choosing a venue template.Read references/citation-policy.md before writing claims from papers.Read references/deep-research-integration.md when converting research outputs - 05
1. Classify the task
If the user provides a conference, map it with references/conference-map.md. If no venue is known, use generic-paper, generic-survey, or generic-technical-report.
new paper draft: create a workspace and templateexisting paper edit: inspect and preserve the current structureresearch-to-PDF summary: use findings.md, paper summaries, diagrams, and PDFs
Permission review
Static risk signals and limitations
Runs scripts
The documentation asks the agent to run terminal commands or scripts.
python3 projects/SKILLS/latex-paper-writer/scripts/init_paper_workspace.py \Runs scripts
The documentation asks the agent to run terminal commands or scripts.
git -C <paper-root> status --shortEvidence record
Why each signal appears
| Signal | Value | Evidence type | Meaning |
|---|---|---|---|
| Quality score | 88/100 | Computed | Documentation, specificity, maintenance, and trust rules |
| Repository stars | 11 | Source | Repository attention, not individual Skill quality |
| Compatibility | 0 platforms | Source | Declared in the catalog source record |
| Usage guide | automated source guide | Editorial | Generated or reviewed according to the visible evidence level |
Pinned source
Provenance and original SKILL.md
- Repository
- jimezsa/opencolab
- Skill path
- projects/SKILLS/latex-paper-writer/SKILL.md
- Commit
- f647b8e4c37a18b4bd3443bd4a8f5470ea1b9d09
- License
- MIT
- Collected
- 2026-08-04
- Default branch
- main
View the original SKILL.md
LaTeX Paper Writer Skill
Use this skill when the user wants a scientific paper, survey, technical report, research-derived PDF summary, LaTeX experiment table, or edits to an existing LaTeX document.
This is the canonical OpenColab path for paper production. Research, grounding, figure extraction, and architecture diagrams stay delegated to the existing shared skills; this skill owns the LaTeX workspace, document structure, template selection, scoped Git version control, PDF compilation, validation, and final delivery packaging.
Mission
Given source material for a scientific document:
- Select or preserve the right LaTeX template.
- Create or reuse a Git-controlled paper workspace.
- Draft or edit the LaTeX sources with grounded claims and citations.
- Generate experiment tables when useful.
- Add user-supplied, extracted, or generated figures when they clarify the paper.
- Build and validate the PDF.
- Create scoped Git checkpoints when the paper has meaningful changes.
- Return the final PDF path, and emit a raw Telegram file directive when needed.
Prerequisites
gitis installed and available inPATH.python3is installed and available inPATH.latexmkis preferred for PDF builds:
latexmk -v
If latexmk is missing, read references/document-types.md for install
guidance and do not claim that compilation succeeded. Only run install commands
after the user explicitly approves installing system packages.
Hard Requirements
- Read
references/conference-map.mdbefore choosing a venue template. - Read
references/citation-policy.mdbefore writing claims from papers. - Read
references/deep-research-integration.mdwhen converting research outputs into a PDF summary or survey. - Read
references/experiment-tables.mdbefore generating result tables. - Use the existing paper's template and macros when editing an existing paper.
- Treat
ICLRas the canonical venue name; infer it from near misses such asICRLonly when context makes that clear, and mention the correction briefly. - Do not claim official venue-template compliance unless the official template is bundled, user-supplied, or otherwise verified.
- Keep every generated or managed paper workspace under Git version control.
- Never stage or commit unrelated files outside the paper workspace.
- Inspect
git statusbefore editing an existing paper repository. - Use
pdf-figure-extractfor figures from already-downloaded local PDFs. - Use
block-diagramfor synthesized architecture, taxonomy, pipeline, or literature-map diagrams. - Use
pageindex-groundedfor exact local evidence checks over downloaded papers when a technical claim needs verification. - Do not fabricate citations, metadata, benchmark values, or architecture details.
- When sending a PDF through Telegram, emit a raw
@telegram-file {"kind":"document","file":"<path>","caption":"optional"}line on its own line with no code fence. Keep the JSON on one line, keepkindasdocument, and on Windows write the path with forward slashes.
Workflow
1. Classify the task
Choose the path:
- new paper draft: create a workspace and template
- existing paper edit: inspect and preserve the current structure
- research-to-PDF summary: use
findings.md, paper summaries, diagrams, and PDFs - experiment report: generate tables/plots and cite the experiment artifacts
- table-only task: generate
.textable fragments undertables/
If the user provides a conference, map it with
references/conference-map.md. If no venue is known, use generic-paper,
generic-survey, or generic-technical-report.
2. Initialize or inspect the workspace
For a new paper:
python3 projects/SKILLS/latex-paper-writer/scripts/init_paper_workspace.py \
--template iclr \
--output research/latex/<slug> \
--title "<paper title>" \
--author "<author line>" \
--venue "ICLR"
Use --dedicated-git only when the user explicitly wants the paper folder to
be its own repository even if it is inside a parent worktree.
For an existing paper, inspect files first:
git -C <paper-root> status --short
find <paper-root> -maxdepth 3 -type f | sort
Do not overwrite user changes or replace an existing template.
3. Write or edit the paper
Use the document type guidance in references/document-types.md.
Default new-paper tree:
main.tex
references.bib
sections/
figures/
tables/
main.pdf
Keep the document source-first. The PDF is a derived deliverable, but it may be tracked when the user wants deliverable history.
4. Generate experiment tables
For CSV, JSON, markdown table, or simple key=value logs:
python3 projects/SKILLS/latex-paper-writer/scripts/make_results_table.py \
--input research/results.csv \
--output tables/results.tex \
--caption "Main benchmark results." \
--label tab:main-results
Include the generated fragment from main.tex with \input{tables/results}.
5. Build and validate the PDF
bash projects/SKILLS/latex-paper-writer/scripts/build_pdf.sh \
--root research/latex/<slug> \
--main main.tex
The build script prefers latexmk, falls back to a bounded pdflatex plus
bibliography flow when possible, and then runs validation. If the compiler is
missing, return install guidance instead of pretending the PDF exists.
6. Commit scoped checkpoints
After a successful meaningful edit or build:
python3 projects/SKILLS/latex-paper-writer/scripts/git_checkpoint.py \
--root research/latex/<slug> \
--message "draft: add method section"
The checkpoint script stages only the paper workspace and aborts when unrelated pre-staged files would be included in the same commit.
Output Contract
For a full paper or report task, return:
- paper workspace path
- primary
.texpath - final PDF path when built
- important warnings from validation
- Git checkpoint commit hash when one was made
- raw
@telegram-fileline when Telegram delivery was requested
Canonical Assets
- Skill doc:
projects/SKILLS/latex-paper-writer/SKILL.md - Conference map:
projects/SKILLS/latex-paper-writer/references/conference-map.md - Document types:
projects/SKILLS/latex-paper-writer/references/document-types.md - Citation policy:
projects/SKILLS/latex-paper-writer/references/citation-policy.md - Research integration:
projects/SKILLS/latex-paper-writer/references/deep-research-integration.md - Experiment tables:
projects/SKILLS/latex-paper-writer/references/experiment-tables.md - Templates:
projects/SKILLS/latex-paper-writer/assets/templates/ - Workspace initializer:
projects/SKILLS/latex-paper-writer/scripts/init_paper_workspace.py - PDF builder:
projects/SKILLS/latex-paper-writer/scripts/build_pdf.sh - PDF validator:
projects/SKILLS/latex-paper-writer/scripts/validate_latex.sh - Table generator:
projects/SKILLS/latex-paper-writer/scripts/make_results_table.py - Git checkpoint helper:
projects/SKILLS/latex-paper-writer/scripts/git_checkpoint.py
Alternatives
Compare before choosing
alirezarezvani/claude-skills
app-store-optimization
App Store Optimization (ASO) toolkit for researching keywords, analyzing competitor rankings, generating metadata suggestions, and improving app visibility on Apple App Store and Google Play Store. Use when the user asks about ASO, app store rankings, app metadata, app titles and descriptions, app store listings, app visibility, or mobile app marketing on iOS or Android. Supports keyword research and scoring, competitor keyword analysis, metadata optimization, A/B test planning, launch checklist
wanshuiyin/Auto-claude-code-research-in-sleep
citation-audit
Use it for operations and research tasks; the detail page covers purpose, installation, and practical steps.
K-Dense-AI/scientific-agent-skills
dask
Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars.
K-Dense-AI/scientific-agent-skills
neurokit2
Use NeuroKit2 to build or audit reproducible research workflows for physiological time-series preprocessing, event/interval analysis, multimodal alignment, variability, and complexity. Trigger when code imports neurokit2 or needs its current APIs, schemas, and method-aware validation—not for diagnosis or device validation.