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-cover-lettergit 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-cover-letter)<a href="https://agentmods.dev/skills/yujie-jason-zhang/polish_skill/paper-cover-letter"><img src="https://agentmods.dev/badge/skills/yujie-jason-zhang/polish_skill/paper-cover-letter/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-cover-letter"><img src="https://agentmods.dev/badge/skills/yujie-jason-zhang/polish_skill/paper-cover-letter.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 | $0.00090 | $0.01158 |
| Opus 5 | $0.00045 | $0.00579 |
| Sonnet 5 | $0.00018 | $0.00232 |
| Haiku 4.5 | $0.00009 | $0.00116 |
Grade A, and why
paper-cover-letter 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Cover Letter
Scope
Use this skill when the manuscript is essentially complete and the user needs the letter that accompanies a journal submission: a new submission, a resubmission, or the cover note for a revised manuscript.
Read references/cover_letter_guide.md for move-by-move templates, length registers, placeholder rules, and the declaration block before drafting a full letter. For a one-line tweak, the core rules below are enough.
Use another skill when the task is primarily:
- a point-by-point response to reviewer comments or a rebuttal: use
paper-response-to-reviewers(if available); that is a separate task, not a cover letter; - manuscript storyline, contribution framing, or section structure: use
paper-argument-reconstructor(if available) to settle the contributions first; - TeX-safe or final-language polishing of the letter text: use
paper-polisher(if available) for the closing pass; - novelty-risk auditing of the underlying idea: use
idea-novelty-auditor(if available).
A cover letter reuses contributions that the manuscript already supports. It does not establish new ones.
Verification Mode
This skill has two modes. By default it drafts the letter as described above. When the input is a cover letter another tool or skill has already drafted, switch to verification mode instead of regenerating:
- do not overwrite the other tool's wording;
- check it against this skill's rules: no overclaiming, novelty kept hedged, ethics statements treated as facts to confirm rather than assumed, and placeholders for every unconfirmed specific;
- report only the deviations; fix one in place only if it breaks a hard rule.
The suite's value is faithful, bounded output, not a competing rewrite. Verify rather than replace what a stronger generator already produced.
Non-Negotiable Rules
- Do not invent contributions, results, novelty, or journal-scope claims that the manuscript or the user does not support.
- Treat every originality and ethics statement as a factual claim: no prior publication, no concurrent submission, all-author approval, conflict-of-interest status, funding, and data availability. Do not assert these on the user's behalf. Insert them only when the user confirms them; otherwise leave an explicit
[...]placeholder and flag it. - Do not overclaim. Keep novelty hedged (for example, "to the best of our knowledge") and tie any superiority to the evaluated conditions, mirroring the manuscript's own claim boundaries.
- Leave every unconfirmed specific as a
[...]placeholder: editor name, journal name, manuscript ID, article type, author names, emails, and dates. Do not fabricate them. - Preserve the manuscript's terminology and claim strength. The letter must not promise more than the paper delivers.
What ships with it
1 file 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 · 83 lines · 90 tokens per session scan A 6f2260577924
paper-cover-letter is a skill published in the GitHub repository yujie-jason-zhang/polish_skill (18 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 1,158 once invoked, about $0.0005 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
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.
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.
overleaf
Sync and manage Overleaf LaTeX projects from the command line. Pull projects locally, push changes back, compile PDFs, and download compile outputs like .bbl files for arXiv submissions. Use when working with LaTeX, Overleaf, academic papers, or arXiv.
paperjury
A tool for reviewing and editing computer-science conference papers in LaTeX or Markdown, the document formats commonly used for research papers. It supports direct edits, structured pre-submission review, and an optional unattended mode for selected fixes.
parallel-subagents
When a task decomposes into independent slices — separate files, OR separate sections of ONE file — fan it out: write job files to the subagent queue and the host runs real parallel Codex workers for you. For a single file, extract per-section slice files into the queue's work/ zone, let workers polish them in…