Agent skill

Latex

by flonat in flonat/flonat-research

Compile one specified LaTeX document, resolve build errors, audit citations, and report build quality.

MITAuto-check passedDocuments & Office

Install Latex

skills CLI
$ npx skills add flonat/flonat-research --skill latex -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install flonat/flonat-research latex --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/flonat/flonat-research.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/latex .claude/skills/latex && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
latex
GitHub stars
146
Token cost
~4.7k tokens
SKILL.md length
2,060 words
Files
28 (incl. references)
Skills in repo
83
Repo updated
First seen
Licence
MIT

At a glance

Compile one specified LaTeX document, resolve build errors, audit citations, and report build quality.

  • Works in 6 steps: Pre-flight → Compile-Fix Loop → Final Report → …
  • A .tex source must be built
  • SKILL.md covers When to Use, When NOT to Use, Quality Scoring and Critical Rules, plus 5 more sections
  • Calls uv

What it does

Latex is an agent skill from flonat/flonat-research. Compile one specified LaTeX document, resolve build errors, audit citations, and report build quality. Use when a .tex source must be built or a concrete compilation failure repaired. Not for corpus-wide build checks, visual polish after a clean build, or creating a project; use $latex-health-check, $latex-polish, or $latex-scaffold.

Its SKILL.md is about 4.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 31 other files, including reference files (for example `references/known-errors.md`, `references/latex-configs.md` and `references/quality-rubric.md`).

It sits in Documents & Office, covering LaTeX. It works with LaTeX. The repository describes itself as: Shareable Claude Code + Codex infrastructure for PhD researchers — skills, agents, hooks, and rules for academic workflows. The licence is MIT.

When your agent uses it

  • A .tex source must be built
  • A concrete compilation failure repaired

Example prompts

  • “/latex”

Requirements

  • Pre-approved tools (allowed-tools): Bash(latexmk*), Bash(xelatex*), Bash(pdflatex*), Bash(biber*), Bash(bibtex*), Bash(mkdir*), Bash(ls*), Bash(wc*), Bash(cp*), Bash(cmp*), Bash(head*), Read, Write, Edit, Grep, Glob

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Pre-flight
  2. Compile-Fix Loop
  3. Final Report
  4. Visual-Fragility Source Lint (clean builds only)
  5. Citation Audit (clean builds only)
  6. Quality Score

What it can do on your machine

Read from SKILL.md and the folder at commit da27600. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(latexmk*)
    • Bash(xelatex*)
    • Bash(pdflatex*)
    • Bash(biber*)
    • Bash(bibtex*)
    • Bash(mkdir*)
    • Bash(ls*)
    • Bash(wc*)
    • Bash(cp*)
    • Bash(cmp*)

    …and 6 more on the same allowed-tools line.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Latex loads about 4.7k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 85 tokens; SKILL.md has 2,060 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~4.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~12k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from flonat/flonat-research at commit da27600, republished under its MIT licence (© flonat). 2,060 words, ~4,709 tokens.

Download SKILL.mdSave it as .claude/skills/latex/SKILL.md (or your agent's skills folder). This skill also uses 27 other files; get the full folder from GitHub.
name
latex
description
Compile one specified LaTeX document, resolve build errors, audit citations, and report build quality. Use when a .tex source must be built or a concrete compilation failure repaired. Not for corpus-wide build checks, visual polish after a clean build, or creating a project; use $latex-health-check, $latex-polish, or $latex-scaffold.
allowed-tools
Bash(latexmk*), Bash(xelatex*), Bash(pdflatex*), Bash(biber*), Bash(bibtex*), Bash(mkdir*), Bash(ls*), Bash(wc*), Bash(cp*), Bash(cmp*), Bash(head*), Read, Write, Edit, Grep, Glob
argument-hint
[tex-file-path]

LaTeX Document Compilation

Default compilation skill for all LaTeX documents. Compiles with autonomous error detection and resolution (up to 5 iterations), runs a citation audit on clean builds, and produces a quality score.

When to Use

  • Default method for all LaTeX compilation
  • Any .tex file that should compile to PDF
  • When compilation fails and you want automatic diagnosis and repair
  • When you want a post-compilation citation audit

When NOT to Use

  • Markdown documents — use plain markdown, not LaTeX
  • Quick notes or drafts — LaTeX overhead not worth it
  • Documents that don't need citations, equations, or precise formatting
  • Documents with exotic custom classes that need manual debugging

Quality Scoring

Apply numeric quality scoring using the shared framework and skill-specific rubric:

Start at 100, deduct per issue found, apply verdict. Include the Score Block in the final report.

Critical Rules

  1. Build artifacts go to out/, PDF stays in the source directory. Use this skill's fail-closed canonical bundle at templates/build-config/.latexmkrc; do not hand-write an END { system(...) } copy block because it can mask latexmk's failure status and copy stale PDFs. For VS Code builds, use the bundled canonical recipe that explicitly loads %DIR%/.latexmkrc—-cd alone is insufficient.
  2. NEVER write BibTeX entries from memory. Verify against authoritative metadata sources such as Crossref or the DOI resolver before writing. Use an installed literature-search workflow when one is configured.
  3. Check document class before adding packages. Some classes load packages internally (e.g., elsarticle loads natbib — adding \usepackage{natbib} causes errors).
  4. Maximum 5 fix iterations. If the document still has errors after 5 auto-fix cycles, stop and report the unresolved errors to the user.
  5. Never silently swallow errors. Every fix must be reported: what was wrong, what was changed, and which file was edited.
  6. Preserve user intent. Auto-fixes should be minimal and conservative. Add packages or overrides — never remove user content.
  7. Citation audit requires clean compilation. Only run the \cite{} vs .bib cross-check after zero errors.
  8. Validate new bibliography entries. The built-in citation audit checks key cross-references. When .bib entries were added or modified, also check DOI resolution, required fields, author formatting, and whether a preprint has a published version. If a dedicated bibliography validator is installed, use it for this extended check; otherwise perform and report the direct checks.

Protocol

Phase 1: Pre-flight
  1. Locate the .tex file. Resolve the path (absolute or relative to CWD).
  2. Identify the project directory — the folder containing the .tex file.
  3. Ensure the canonical .latexmkrc exists in the project directory. Resolve templates/build-config/.latexmkrc relative to this installed skill and stop if the bundle is missing. Never recreate a partial version from memory. Compare an existing file byte-for-byte with the bundled canonical; do not overwrite divergence blindly. Move project-specific bibliography paths or custom dependencies into .latexmkrc.local; move engine selection into a % !TEX program = ... driver comment. Replacing a divergent file remains an explicit migration.
  4. Create out/ directory if it doesn't exist: mkdir -p <project-dir>/out.
  5. Identify the .bib file(s) referenced in the document (scan for \bibliography{}, \addbibresource{}, or \bibinput{}). Note their paths for Phase 5.
Phase 2: Compile-Fix Loop

Run up to 5 iterations. Each iteration:

Step 2a — Compile
bash
cd <project-dir> && latexmk -interaction=nonstopmode <filename>.tex 2>&1

Capture the full output. The log file will be at out/<filename>.log.

Step 2b — Read the log

Read out/<filename>.log in full. Parse for errors and warnings.

Step 2c — Classify errors

Check the log against the known error patterns below. If an error matches, apply the fix and go to Step 2a. If no known pattern matches, record the error as unresolved and stop the loop.

Same-error circuit breaker. Independent of the 5-iteration cap: if the same error (same line family, same pattern signature) survives 3 consecutive fix attempts, stop the loop early. Continued attempts on a stuck error compound damage rather than resolve it. Report what was tried, quote the log line, and ask the user how to proceed. A common signature: Illegal parameter number jumping between line numbers as you edit — that is the diagnostic for a parameterized TikZ style defined inside a Beamer frame; see skills/shared/tikz-rules.md Rule 11.


Known Error Patterns & Auto-Fixes

Check the log against these patterns. Full fix instructions: references/known-errors.md

#PatternKey log signature
1Missing packageFile '<pkg>.sty' not found or undefined command from known package
2Font/symbol conflictsCommand \<name> already defined
3Undefined citationCitation '<key>' ... undefined or biblatex entry not found
4Missing image/fileFile '<path>' not found (pdftex.def or LaTeX)
5Stale auxiliary filesCorrupted .aux/.bbl/.bcf, or no \bibstyle command
6Beamer/enumitem clashOption clash for package enumitem or \item already defined
7xcolor option conflictsOption clash for package xcolor or undefined \rowcolor
8TikZ reserved keysI do not know the key '/tikz/<name>' or pgfkeys error

If an error matches, read the full fix from the reference and apply it. If no pattern matches, record as unresolved and stop the loop.

2.4 PDF backup (paper directories only)

Only run if the compile-fix loop above ended with a successful compilation (PDF exists).

If the .tex file is inside a paper-{venue}/paper/ structure (where paper/ is a symlink to Overleaf):

  1. Identify the paper wrapper — the parent of the paper/ symlink (e.g., paper-jbdm/).
  2. Create the backup directory: mkdir -p <paper-wrapper>/backup
  3. Copy the PDF:
    bash
    cp <paper-wrapper>/paper/<filename>.pdf <paper-wrapper>/backup/<wrapper-name>_vcurrent.pdf

Detection logic:

  • The project directory containing the .tex file is a symlink named paper.
  • Its parent directory name starts with paper-.
  • If either condition is false, skip this sub-step silently.

Phase 3: Final Report

After the loop ends (either clean compilation or max iterations reached), report:

Compilation Status
FieldValue
StatusClean / Errors remaining
IterationsN of 5
Pages(from log: Output written on ... (N pages))
LaTeX/package warningsCount of Warning-tagged log lines (undefined refs, font subs, package warnings)
Typographic boxesOverfull/underfull h/vboxes by severity — see box report below (NOT counted by a Warning grep)
Fixes appliedList each fix: what error, what was changed, which file
Unresolved errorsList any errors that couldn't be auto-fixed
How to extract page count
bash
grep -o "Output written on .* ([0-9]* page" out/<filename>.log | grep -o "[0-9]* page"
How to count warnings and boxes

Warnings and typographic boxes are separate — box messages are not Warning-tagged, so a single Warning grep misses every overfull/underfull box. Report both, using the recipes in ../shared/overfull-boxes.md:

bash
# LaTeX/package warnings (refs, fonts, packages)
grep -c "Warning" out/<filename>.log
# Overfull/underfull boxes (the thing the Warning grep cannot see)
grep -cE 'Overfull \\[hv]box \([0-9.]+pt too (wide|high)\)' out/<filename>.log
grep -cE 'Underfull \\[hv]box \(badness [0-9]+\)' out/<filename>.log
Box report (typographic quality)

Extract the top offenders by overflow magnitude and report each box ≥ 1 pt with its location, width, and a remediation tier per the severity gradient + ladder in ../shared/overfull-boxes.md:

bash
awk -F'[()]' '/Overfull \\[hv]box/ {
    split($2, a, "pt"); w = a[1] + 0;
    loc = $0; sub(/.*too (wide|high)\) */, "", loc);
    printf "%7.1f pt  %s\n", w, loc
}' out/<filename>.log | sort -rn | head -20

Report only — do not silently reword prose to close a box (rules/manuscript-edit-budget.md). The only safe auto-fix is inserting \usepackage{microtype} when genuinely absent.

Breadcrumb: Append to .planning/state.md (if exists) or .context/current-focus.md:

### [latex] Compilation complete [YYYY-MM-DD HH:MM]
- **Done:** [Clean/Errors remaining, N iterations, N pages, N fixes applied]
- **Outputs:** [PDF at <path>]
- **Next:** [Citation audit (if clean) or manual error resolution]

Phase 4: Visual-Fragility Source Lint (clean builds only)

Only run if Phase 2 ended with zero errors. Sits between the final report (Phase 3) and the citation audit (Phase 5). Catches LaTeX source patterns that compile clean but produce visually fragile output — the failure class the title-page incident (2026-06-19) exposed.

Full detector catalogue with regex signatures, severity tiers, remediation, and false-positive caveats: references/source-pathologies.md.

What to run
  1. Nine grep-based source-pathology detectors against main.tex plus any \input/\include'd files:

    #PatternTier
    1Spacing hacks fighting global spacing (\onehalfspacing + local \\[-Xcm] / \vspace{-…})Major
    2Manual vertical-rhythm surgery (repeated \vspace/\vskip/\pagebreak in body)Moderate–Major
    3Line breaks as layout engine (\\ / \newline / \linebreak inside \section/\caption)Moderate–Major
    4Forced-float carpet bombing ([H]/[!h] pinning, \FloatBarrier overuse)Moderate
    5Shrink-to-fit tables/figures (\resizebox{\textwidth}{!}{…}, \adjustbox{width=\textwidth})Major
    6Tiny-table typography hacks (\scriptsize/\tiny in tables; negative \tabcolsep; \arraystretch<0.9)Moderate–Major
    7Absolute / overlap positioning (\raisebox, \makebox[0pt], \llap, \rlap, \smash, \hspace*) outside mathMajor
    8Fixed-width layout assumptions (p{Xcm}, \begin{minipage}{Xcm}, \parbox{Xcm})Moderate
    9Label-before-caption inside floats (\label{…} precedes \caption{…} in a figure/table block)Major
  2. chktex if installed: chktex -q -n8 -n44 main.tex 2>&1 | grep -v "^$". Advisory only — collect warnings; deduct -1 each, capped at -10. Skip if chktex not on PATH.

  3. latexindent -k if installed: latexindent -k main.tex 2>&1; echo "Exit: $?". Source-cleanliness smoke test. Non-zero exit → -3 once. Skip if latexindent not on PATH.

Show full SKILL.md (755 more words)Show less
Output

Append a Source pathologies subsection to the Phase 3 report:

markdown
### Source pathologies

| Pattern | Location | Detail | Tier |
|---------|----------|--------|------|
| 1 Spacing-hacks | titlepage, line 56 | `\\[-0.3cm]` under global `\onehalfspacing` (line 43) | Major |
| 9 Label-before-caption | tab:results, line 412 | `\label` at L410 precedes `\caption` at L413 | Major |

If no findings: "No source pathologies detected." If chktex or latexindent ran, note their PASS/N-warnings status.

Auto-fix scope

Phase 4 is report-only, with one exception: Pattern 1 ("Spacing hacks fighting global spacing") has a deterministic remediation (wrap the affected block in \begin{singlespace}…\end{singlespace}, delete the negative kerns). The skill offers this as an opt-in fix in the final report; the user accepts or declines per case. Do not auto-apply.

For Patterns 2–9 and tool findings: report only.

When to skip
  • Compile failed in Phase 2 (pathology lint is meaningless without a build).
  • User explicitly invoked latex --no-lint.

Phase 5: Citation Audit (clean builds only)

Only run this phase if Phase 2 ended with zero errors.

  1. Extract all \cite keys from the .tex file (and any \input/\include files):
    • Match \cite{...}, \citep{...}, \citet{...}, \textcite{...}, \parencite{...}, \autocite{...}, and multi-key variants like \cite{key1,key2}.
  2. Extract all bib entry keys from the .bib file(s): match @<type>{<key>,.
  3. Cross-reference:
CheckWhat it finds
Missing in .bibKeys cited in .tex but absent from .bib
Unused in .texKeys defined in .bib but never cited
Possible typosNear-matches between missing cite keys and existing bib keys
  1. Report the results as a table. Do not modify any files during the audit — report only.

Phase 6: Quality Score

After all phases complete, compute the quality score:

  1. Read references/quality-rubric.md for deduction mappings.
  2. Log every issue from Phases 2-5 (unresolved errors, remaining warnings, overfull/underfull boxes from the Phase 3 box report, citation mismatches). The rubric deducts per box by severity (>10pt: -5, 1-10pt: -2, underfull: -1) — feed it the box report, not a Warning count.
  3. Compute score (100 - total deductions), apply verdict per ../shared/quality-scoring.md.
  4. Append the Score Block to the compilation report:
markdown
## Quality Score

| Metric | Value |
|--------|-------|
| **Score** | XX / 100 |
| **Verdict** | Ship / Ship with notes / Revise / Revise (major) / Blocked |

### Deductions

| # | Issue | Tier | Deduction | Category |
|---|-------|------|-----------|----------|
| 1 | [description] | [tier] | -X | [category] |
| | **Total deductions** | | **-XX** | |
6.1 Output verification (before commit)

When the compile produced a PDF (and any backup copy), emit an outputs manifest and run the shared verifier per _shared/verify-outputs.md:

  1. Write manifest to <project>/.claude/state/outputs-manifest-<UTC-timestamp>.json listing every file written this invocation (PDF, backup PDF if 2.4 ran, log files).

  2. Run:

    bash
    uv run python "<skills-root>/_shared/verify_outputs.py" \
        --manifest "$MANIFEST" \
        --project-root "$PROJECT_ROOT"
  3. If the verifier exits non-zero, do not commit. Surface the missing-files list and stop.

Closes the "hallucinated outputs" failure class (commit b2cff75, 2026-04-18).


Configuration Reference

Output Directory

All LaTeX build artifacts (.aux, .log, .bbl, .fls, etc.) go to an out/ subfolder relative to the source file. The PDF is copied back to the source directory after each successful build, so it lives alongside the .tex file for easy access.

The PDF-copy convention is enforced in two places — keep them in sync when making changes:

  1. .latexmkrc (per-project) — the canonical success-gated copy-back logic handles terminal builds
  2. VS Code .vscode/settings.json (per-workspace) — explicitly loads the document-directory canonical before -cd

VS Code integration, engine auto-detection (pdfLaTeX/XeLaTeX/LuaLaTeX), manual override configs, reference checking scripts, and manual compilation commands:

references/latex-configs.md

Overleaf-Synced Projects

When a project is synced to Overleaf (via Dropbox or Git):

  • The out/ directory will sync to Overleaf but Overleaf ignores it — this is fine
  • Always use .latexmkrc to enforce out/ — Overleaf ignores this file too
  • Overleaf compiles independently on its server; local compilation is for verification only
  • The .bst file (e.g., elsarticle-harv.bst) lives in the source directory, not out/
Local-Only Projects (No Overleaf)

Not all projects sync to Overleaf. For local-only projects:

  • The same out/ and .latexmkrc conventions apply — this keeps the working directory clean regardless of sync method
  • There is no paper/ symlink — .tex files live directly in the project root or a subdirectory

Templates

See references/templates.md for working paper template location, files, citation style toggle, bibliography file naming conventions, and bibliography command reference.


SituationDelegate to
Need to find or verify a bibliography entryInstalled scholarly-search workflow, or direct authoritative metadata lookup
Full academic proofreading after clean compilationproofread
Detailed .bib validation beyond cite-key matchingInstalled bibliography validator, when available
Beamer presentations specificallybeamer-deck (which uses this skill internally for compilation)
Fleet-wide compilation health checklatex-health-check (project discovery, 3 iterations per project, cross-project checks)

Examples

Basic usage

"Compile my paper at ~/papers/mcdm-survey/main.tex"

Runs the full protocol: pre-flight → compile-fix loop → report → citation audit → quality score.

After fixing a known issue

"Recompile — I added the missing package manually"

Runs from Phase 2 directly (pre-flight can be skipped if .latexmkrc and out/ already exist).

Targeted fix

"My paper won't compile — something about Bbbk"

Identifies as Pattern 2 (font conflict), applies the \let\Bbbk\relax fix, recompiles.

Source format. Paper prose stays one line per paragraph; normalize edited files with .scripts/latex_paragraph_format.py --apply and recompile. Canonical: rules/latex-source-format.md.

© flonat, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 27 other files (references) in skills/latex of flonat/flonat-research.

  • SKILL.md
  • references/known-errors.md
  • references/latex-configs.md
  • references/quality-rubric.md
  • references/source-pathologies.md
  • references/templates.md
  • templates/build-config/.latexmkrc
  • templates/build-config/README.md
  • templates/build-config/vscode-settings.json
  • templates/working-paper/.gitignore
  • templates/working-paper/.latexmkrc
  • templates/working-paper/README.md
  • templates/working-paper/biblatex-preamble.tex
  • templates/working-paper/citation-placeholders.tex
  • templates/working-paper/flonat-bib.sty
  • templates/working-paper/flonat-math.sty
  • templates/working-paper/flonat-rev.sty
  • … and 11 more

Open the folder on GitHubat commit da27600

Compare with similar skills

Latex next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Latex compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Latex this skillflonat/flonat-research146—~4.7kAutomated safety check: PassMIT
Research Writingalfonso0512/research-writing-skill4881 repos~818Automated safety check: PassMIT
Paper WritingMLNLP-World/Paper-Writing-Tips4.7k—~630Automated safety check: PassNone
Evomath TaoEvoScientist/EvoSkills4762 repos~3.8kAutomated safety check: PassApache-2.0
PaperjurySpark-To-Paper-Skills/paperjury1.2k—~5.3kAutomated safety check: PassMIT
Thesis Defense PPTX Builderzouchenzhen/thesis-defense-pptx-skill266—~2.4kAutomated safety check: PassApache-2.0

Similar skills

  • Research Writing

    alfonso0512/research-writing-skill

    科研论文写作助手,提供 30 个 Prompt 模板覆盖论文写作全流程. An agent skill from alfonso0512/research-writing-skill.

    488 GitHub starsUsed in 1 repo~818 tokens
    Documents & OfficeAuto-check passed
  • Paper Writing

    MLNLP-World/Paper-Writing-Tips

    学术论文写作检查与优化助手。基于 MLNLP-World 社区整理的论文写作技巧,帮助检查和优化学术论文。Use when: (1) 检查论文 LaTeX 格式和排版, (2) 优化公式符号使用, (3) 改进图表设计, (4) 润色英文学术表达, (5) 检查参考文献格式, (6) 投稿前终稿检查, (7) 用户询问论文写作技巧或规范。

    4.7k GitHub stars~630 tokensUpdated 13 days ago
    Documents & OfficeAuto-check passed
  • Evomath Tao

    EvoScientist/EvoSkills

    A skill your agent uses whenever the user submits a non-trivial mathematical claim that needs a rigorous proof or audit.

    476 GitHub starsUsed in 2 repos~3.8k tokens
    Documents & OfficeAuto-check passed
  • Paperjury

    Spark-To-Paper-Skills/paperjury

    Three modes for CS-conference papers (CVPR/ICCV/ECCV vision, ACL/EMNLP/NAACL NLP, ICLR/NeurIPS/ICML/AAAI ML).

    1.2k GitHub stars~5.3k tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed
  • Thesis Defense PPTX Builder

    zouchenzhen/thesis-defense-pptx-skill

    Builds an editable thesis defense PowerPoint from a thesis PDF or LaTeX project while preserving a supplied university or lab template, then runs a visual quality check.

    266 GitHub stars~2.4k tokensUpdated 4 mo ago
    Documents & OfficeAuto-check passed
  • Mathmodel Skill

    handsomeZR-netizen/mathmodel-skill

    CUMCM 国赛、MCM/ICM 美赛与电工杯数学建模竞赛的端到端协作工作流。Use when a user explicitly works on one of these modeling contests or asks to run/review a modeling-competition paper from problem selection through modeling…

    292 GitHub stars~2.5k tokensUpdated 13 days ago
    Documents & OfficeAuto-check passed

More from flonat/flonat-research

All 83 skills in this repo
  • Latex Posters

    flonat/flonat-research

    Create a large-format academic poster in LaTeX using beamerposter, tikzposter, or baposter.

    146 GitHub stars~1.5k tokensUpdated 10 days ago
    Auto-check: notes
  • Skill Creator

    flonat/flonat-research

    Create, revise, and evaluate reusable AI workflow skills, including trigger-quality tests.

    146 GitHub stars~4.4k tokensUpdated 10 days ago
    Auto-check passed
  • DOCX

    flonat/flonat-research

    Create, read, edit, or convert Microsoft Word documents while preserving professional document structure.

    146 GitHub stars~1.2k tokensUpdated 10 days ago
    Auto-check passed
  • PDF

    flonat/flonat-research

    Read, create, combine, split, rotate, OCR, watermark, secure, or extract content from PDF files.

    146 GitHub stars~488 tokensUpdated 10 days ago
    Auto-check passed
  • Init Project Orchestration

    flonat/flonat-research

    Create or migrate project-level agents, repeatable project workflows, and planning state from one client-neutral contract, then render repository-scoped adapters for both Claude Code and Codex.

    146 GitHub stars~1.6k tokensUpdated 10 days ago
    Auto-check passed
  • Pre Commit Audit

    flonat/flonat-research

    Deliver a fast pre-commit safety scan: file size, anonymity (author / affiliation strings in tex/bib), hardcoded secrets, and invisible-Unicode carriers.

    146 GitHub stars~2.8k tokensUpdated 10 days ago
    Auto-check: notes

Works with

Questions about Latex

What does Latex do?

Compile one specified LaTeX document, resolve build errors, audit citations, and report build quality. Latex is an agent skill from flonat/flonat-research. Compile one specified LaTeX document, resolve build errors, audit citations, and report build quality.

When should I use Latex?

Latex fits situations like: A .tex source must be built; A concrete compilation failure repaired.

How do I install Latex in Claude Code?

Run `npx skills add flonat/flonat-research --skill latex -a claude-code`. Or copy the skill folder (skills/latex in flonat/flonat-research) into .claude/skills/latex in your project. Claude Code loads it when a task matches its description.

How do I install Latex in Codex?

Run `npx skills add flonat/flonat-research --skill latex -a codex`. Or copy the skill folder (skills/latex in flonat/flonat-research) into .agents/skills/latex in your project. Codex loads it when a task matches its description.

Can I use Latex in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add flonat/flonat-research --skill latex -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/latex, .gemini/skills/latex, .github/skills/latex and .opencode/skills/latex in your project.

What does Latex need to run?

Going by SKILL.md and its folder, Latex needs the command-line tools its instructions call (uv). Its frontmatter pre-approves these tools: Bash(latexmk*), Bash(xelatex*), Bash(pdflatex*), Bash(biber*), Bash(bibtex*), Bash(mkdir*), Bash(ls*), Bash(wc*), Bash(cp*), Bash(cmp*), Bash(head*), Read, Write, Edit, Grep, Glob.

Does Latex access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Latex safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Latex use?

Latex is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Latex use?

About 4.7k tokens (SKILL.md is roughly 19k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6.8k tokens, read only when the agent opens those files.

What are the alternatives to Latex?

Skills that share tags, products or a category with Latex: Research Writing (alfonso0512/research-writing-skill, 488 stars), Paper Writing (MLNLP-World/Paper-Writing-Tips, 4.7k stars), Evomath Tao (EvoScientist/EvoSkills, 476 stars) and Paperjury (Spark-To-Paper-Skills/paperjury, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Latex?

flonat (a GitHub user) maintains it in flonat/flonat-research, which has 146 GitHub stars. The repository holds 83 skills in this directory. The repository was last updated on September 29, 2026.

Source: flonat/flonat-research on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.