Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add arnabdeypolimi/claude_code_setup --skill latex-paper-engit clone --depth 1 https://github.com/arnabdeypolimi/claude_code_setupWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/arnabdeypolimi/claude_code_setup/latex-paper-en)<a href="https://agentmods.dev/skills/arnabdeypolimi/claude_code_setup/latex-paper-en"><img src="https://agentmods.dev/badge/skills/arnabdeypolimi/claude_code_setup/latex-paper-en.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00184 | $0.01831 |
| Opus 5 | $0.00092 | $0.00915 |
| Sonnet 5 | $0.00037 | $0.00366 |
| Haiku 4.5 | $0.00018 | $0.00183 |
Grade A, and why
latex-paper-en scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LaTeX Academic Paper Assistant (English)
Use this skill for targeted work on an existing English LaTeX paper project. Keep the workflow low-friction: identify the right module, run the smallest useful check, and return actionable comments in LaTeX-friendly review format.
Capability Summary
- Compile and diagnose LaTeX build failures.
- Audit formatting, bibliography, grammar, sentence length, argument logic, and figure quality.
- Review IEEE-style pseudocode blocks, figure-wrapped algorithms, captions, labels, comments, and algorithm package choices.
- Improve expression, translate academic prose, optimize titles, and reduce AI-writing traces.
- Review experiment sections without rewriting citations, labels, or math.
Triggering
Use this skill when the user has an existing English .tex paper project and wants help with:
- compiling or fixing build errors
- format or venue compliance
- bibliography and citation validation
- grammar, sentence, logic, or expression review
- translation of academic prose
- title optimization
- figure or caption quality checks
- pseudocode and algorithm-block review
- de-AI editing of visible prose
- experiment-section analysis
Do Not Use
Do not use this skill for:
- planning or drafting a paper from scratch
- deep literature research or fact-finding without a paper project
- Chinese thesis-specific structure/template work
- Typst-first paper workflows
- DOCX/PDF conversion tasks that do not involve the LaTeX source
- multi-perspective review, scoring, or submission gate decisions (use
paper-audit) - standalone algorithm design from scratch without a paper project
Module Router
| Module | Use when | Primary command | Read next |
|---|---|---|---|
compile |
Build fails or the user wants a fresh compile | uv run python -B $SKILL_DIR/scripts/compile.py main.tex |
references/modules/COMPILE.md |
format |
User asks for LaTeX or venue formatting review | uv run python -B $SKILL_DIR/scripts/check_format.py main.tex |
references/modules/FORMAT.md |
bibliography |
Missing citations, unused entries, BibTeX validation | uv run python -B $SKILL_DIR/scripts/verify_bib.py references.bib --tex main.tex |
references/modules/BIBLIOGRAPHY.md |
grammar |
Grammar and surface-level language fixes | uv run python -B $SKILL_DIR/scripts/analyze_grammar.py main.tex --section introduction |
references/modules/GRAMMAR.md |
sentences |
Long, dense, or hard-to-read sentences | uv run python -B $SKILL_DIR/scripts/analyze_sentences.py main.tex --section introduction |
references/modules/SENTENCES.md |
logic |
Weak argument flow, unclear transitions, introduction funnel problems, or abstract/conclusion misalignment | uv run python -B $SKILL_DIR/scripts/analyze_logic.py main.tex --section methods |
references/modules/LOGIC.md |
expression |
Academic tone polish without changing claims | uv run python -B $SKILL_DIR/scripts/improve_expression.py main.tex --section related |
references/modules/EXPRESSION.md |
translation |
Chinese-to-English academic translation or bilingual polishing | uv run python -B $SKILL_DIR/scripts/translate_academic.py input.txt --domain deep-learning |
references/modules/TRANSLATION.md |
title |
Generate, compare, or optimize paper titles | uv run python -B $SKILL_DIR/scripts/optimize_title.py main.tex --check |
references/modules/TITLE.md |
figures |
Figure existence, extension, DPI, or caption review | uv run python -B $SKILL_DIR/scripts/check_figures.py main.tex |
references/REVIEWER_PERSPECTIVE.md |
pseudocode |
IEEE-safe pseudocode review, algorithm2e cleanup, caption/label/reference checks, and comment-length review |
uv run python -B $SKILL_DIR/scripts/check_pseudocode.py main.tex --venue ieee |
references/modules/PSEUDOCODE.md |
deai |
Reduce AI-writing traces while preserving LaTeX syntax | uv run python -B $SKILL_DIR/scripts/deai_check.py main.tex --section introduction |
references/modules/DEAI.md |
experiment |
Inspect experiment design/write-up quality, discussion depth, discussion layering, and conclusion completeness | uv run python -B $SKILL_DIR/scripts/analyze_experiment.py main.tex --section experiments |
references/modules/EXPERIMENT.md |
What ships with it
52 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 390 B
- evals/evals.json 7.8 KB
- examples/compile-and-bibliography.md 551 B
- examples/experiment-review.md 527 B
- examples/figures-and-title.md 513 B
- examples/grammar-and-logic.md 687 B
- examples/translation-and-deai.md 630 B
- references/BEST_PRACTICES.md 456 B
- references/CITATION_VERIFICATION.md 4.1 KB
- references/COMMON_ERRORS.md 2.8 KB
- references/COMPILATION.md 2.0 KB
- references/DEAI_GUIDE.md 17 KB
- references/FORBIDDEN_TERMS.md 1.6 KB
- references/modules/BIBLIOGRAPHY.md 748 B
- references/modules/CAPTION.md 2.0 KB
- references/modules/COMPILE.md 2.8 KB
- references/modules/DEAI.md 1.0 KB
- references/modules/EXPERIMENT.md 3.8 KB
- references/modules/EXPRESSION.md 789 B
- references/modules/FORMAT.md 440 B
- references/modules/GRAMMAR.md 980 B
- references/modules/LOGIC.md 7.6 KB
- references/modules/PSEUDOCODE.md 1.7 KB
- references/modules/SENTENCES.md 575 B
- references/modules/TITLE.md 7.7 KB
- references/modules/TRANSLATION.md 1.1 KB
- references/modules/WORKFLOW.md 910 B
- references/REVIEWER_PERSPECTIVE.md 4.9 KB
- references/STYLE_GUIDE.md 6.5 KB
- references/TERMINOLOGY.md 9.9 KB
- references/TRANSLATION_GUIDE.md 11 KB
- references/VENUES.md 6.4 KB
- references/WRITING_PHILOSOPHY.md 6.7 KB
- scripts/__pycache__/parsers.cpython-312.pyc 18 KB
- scripts/analyze_experiment.py 18 KB runs code
- scripts/analyze_grammar.py 3.6 KB runs code
- scripts/analyze_logic.py 18 KB runs code
- scripts/analyze_sentences.py 3.6 KB runs code
- scripts/check_figures.py 6.4 KB runs code
- scripts/check_format.py 6.4 KB runs code
- scripts/check_pseudocode.py 11 KB runs code
- scripts/check_references.py 14 KB runs code
- scripts/compile.py 17 KB runs code
- scripts/deai_batch.py 9.9 KB runs code
- scripts/deai_check.py 16 KB runs code
- scripts/extract_prose.py 2.7 KB runs code
- scripts/improve_expression.py 3.2 KB runs code
- scripts/online_bib_verify.py 12 KB runs code
- scripts/optimize_title.py 15 KB runs code
- scripts/parsers.py 15 KB runs code
- scripts/translate_academic.py 5.1 KB runs code
- scripts/verify_bib.py 15 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 118 lines · 184 tokens per session scan A f66086051e97
latex-paper-en is a skill published in the GitHub repository arnabdeypolimi/claude_code_setup (4 stars, last pushed 3d ago), licensed MIT. It adds 184 tokens to every session and 1,831 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
bitcoin-secp256k1
The elliptic curve Bitcoin uses for all signatures (ECDSA + Schnorr). Defined by SECG (SEC 2: Recommended Elliptic Curve Domain Parameters).
scientific-method
Use this skill whenever someone doubts a number, demands rigorous proof of a cause, or wants something invented and proven — any time a benchmark, metric, ceiling, or root-cause story must be verified rather than trusted, or a limit must be broken with a built, measured mechanism. Typical situations: a measurement…
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…