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 yujie-jason-zhang/polish_skill --skill paper-polishergit clone --depth 1 https://github.com/yujie-jason-zhang/polish_skillWrote 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/yujie-jason-zhang/polish_skill/paper-polisher)<a href="https://agentmods.dev/skills/yujie-jason-zhang/polish_skill/paper-polisher"><img src="https://agentmods.dev/badge/skills/yujie-jason-zhang/polish_skill/paper-polisher/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yujie-jason-zhang/polish_skill/paper-polisher"><img src="https://agentmods.dev/badge/skills/yujie-jason-zhang/polish_skill/paper-polisher.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00117 | $0.03843 |
| Opus 5 | $0.00059 | $0.01921 |
| Sonnet 5 | $0.00023 | $0.00769 |
| Haiku 4.5 | $0.00012 | $0.00384 |
Grade A, and why
paper-polisher 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 12d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Polisher
Scope and References
Use this skill for TeX-safe academic English polishing, translation, proofreading, source-to-output verification, terminology or notation review, numerical-consistency review, and explicitly authorized notation normalization.
For full papers, long sections, verification, consistency audits, normalization, or strict style-guide work, read references/tex_safe_polishing.md before acting. Read references/tex_safe_polishing_zh.md instead when Chinese-facing workflow guidance is materially useful; do not load both merely to duplicate context. For a short local polish, use the core rules below and consult a reference only when needed.
Do not use this skill as the main tool for:
- novelty, contribution-defensibility, dangerous-baseline, or reviewer-attack audits; use
idea-novelty-auditorif available; - literature review, gap framing, reference selection, or citation-role assignment; use
problem-driven-literature-reviewif available; - broad storyline, introduction structure, or experiment-to-claim redesign; use
paper-argument-reconstructorif available.
When a request combines those tasks with polishing, complete the upstream reasoning task first and use this skill only for the final faithful language and consistency pass.
Mode Selection and Precedence
Follow the user's explicit requested action before considering who produced the input. Provenance alone never overrides an explicit request to polish, audit, verify, or normalize. If more than one action is requested, keep their artifacts and reports separate unless the user asks for a combined deliverable.
Mode-specific output rules take precedence over output rules based on document length. In particular, a full-manuscript verification or consistency-only audit remains report-only.
If the user requests both notation normalization and prose polishing, perform and approve normalization first, treat the normalized TeX as the new baseline, and then polish against that baseline. Do not try to validate a combined prose-and-symbol change as one normalization comparison.
What ships with it
4 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.
- 12d ago First seen · 217 lines · 117 tokens per session scan A 5a197dc415ab
paper-polisher is a skill published in the GitHub repository yujie-jason-zhang/polish_skill (18 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 3,843 once invoked, about $0.0006 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
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…
systems-paper-writing
Comprehensive guide for writing systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides paragraph-level structural blueprints, writing patterns, venue-specific checklists, reviewer guidelines, LaTeX templates, and conference deadlines. Use this skill for all systems conference paper writing.
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…
academic-paper-writer
Draft economics papers with proper structure and academic style.
ml-paper-writing
Write publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification…
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.