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 understudylabs/understudy-agent-tools --skill latex-paper-polishgit clone --depth 1 https://github.com/understudylabs/understudy-agent-toolsWrote 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/understudylabs/understudy-agent-tools/latex-paper-polish)<a href="https://agentmods.dev/skills/understudylabs/understudy-agent-tools/latex-paper-polish"><img src="https://agentmods.dev/badge/skills/understudylabs/understudy-agent-tools/latex-paper-polish.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00088 | $0.01289 |
| Opus 5 | $0.00044 | $0.00645 |
| Sonnet 5 | $0.00018 | $0.00258 |
| Haiku 4.5 | $0.00009 | $0.00129 |
Grade A, and why
latex-paper-polish 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LaTeX Paper Polish
Use this skill for research notes, white papers, case studies, and technical PDFs where the goal is not only "compile the TeX" but "make the artifact credible and readable."
This skill combines four passes:
- Evidence and claim proofreading.
- Deslop-style prose cleanup.
- TeX/PDF build and warning triage.
- Typesetting polish for page flow, tables, URLs, and dangling text.
Trigger
Use this skill when the user asks for any of the following:
- polish a LaTeX paper or PDF
- compile or rebuild a paper
- proofread a paper draft
- deslop a paper
- fix trailing paragraphs, widows, or orphans
- make a PDF shareable
- inspect LaTeX warnings
- improve tables, appendix layout, claim sections, or evidence sections
If the task explicitly mentions "deslop", also use the installed deslop skill.
Safety Gates
Treat compilation as a local file operation. Do not install a TeX distribution, fetch remote assets, overwrite a canonical PDF, or publish a paper without the user's authorization. Preserve claims, citations, and uncertainty during prose and layout edits; a cleaner page must not imply stronger evidence.
Workflow
1. Locate the Source and PDF
Find the canonical .tex source before editing. If there are multiple related paper files, identify:
- active source file
- build output directory
- current PDF path
- web/public copy path, if any
- data artifacts cited by the paper
Do not assume the displayed PDF is generated from the nearest .tex file. Check filenames, timestamps, and build output.
2. Preserve the Evidence Boundary
Before changing prose, audit claims against local artifacts where feasible.
Check whether the paper distinguishes:
- measured result vs hypothesis
- live provider run vs dry run
- invoice/billing evidence vs response-usage estimate
- row-matched vs payload-identical comparison
- task-success ground truth vs teacher-imitation evidence
- completion logprobs vs prompt logprobs
- route health vs model quality
- current snapshot vs durable provider conclusion
What ships with it
2 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.
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 · 180 lines · 88 tokens per session scan A d19b8feeb5b0
latex-paper-polish is a skill published in the GitHub repository understudylabs/understudy-agent-tools (16 stars, last pushed 6d ago), licensed MIT. It adds 88 tokens to every session and 1,289 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…