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 read-paper-to-notesgit 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/read-paper-to-notes)<a href="https://agentmods.dev/skills/yujie-jason-zhang/polish_skill/read-paper-to-notes"><img src="https://agentmods.dev/badge/skills/yujie-jason-zhang/polish_skill/read-paper-to-notes/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/read-paper-to-notes"><img src="https://agentmods.dev/badge/skills/yujie-jason-zhang/polish_skill/read-paper-to-notes.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 | $0.00116 | $0.01124 |
| Opus 5 | $0.00058 | $0.00562 |
| Sonnet 5 | $0.00023 | $0.00225 |
| Haiku 4.5 | $0.00012 | $0.00112 |
Grade A, and why
read-paper-to-notes 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read Paper to Notes
Scope
Read one academic paper closely and produce a reusable Markdown note grounded in the supplied source.
For a complete paper note, read references/reading_protocol.md before drafting and use assets/paper-note-template.md as the output structure. Adapt the number of method, equation, and experiment subsections to the paper; keep the core headings and evidence conventions.
Use another skill when the main task is:
- synthesizing several papers into related work or a literature review: use
problem-driven-literature-reviewif available; - diagnosing or rewriting the argument of the user's manuscript: use
paper-argument-reconstructorif available; - polishing manuscript language or preserving TeX: use
paper-polisherif available; - auditing novelty claims or an experiment plan: use the corresponding audit skill if available.
Modes
- Full-note mode: Read the complete paper and fill the bundled Markdown template. Use this by default when the user asks to read a paper or create paper notes.
- Focused mode: Analyze only the requested element, such as one equation, method module, figure, experiment, or limitation. Do not force the complete template.
- Enriched mode: Add verified publisher metadata, project code, datasets, or related-paper context when the user requests them or explicitly permits outside research. Keep outside information separate from paper-derived content.
Default to paper-only mode. Do not silently add web knowledge to a note presented as a summary of the supplied paper.
Workflow
- Establish the source boundary, requested output language, desired depth, and user research context. Infer obvious preferences from the request; ask only when missing information would materially change the note.
- Verify that the PDF or text is readable. Identify missing pages, failed extraction, scans requiring OCR, inaccessible supplements, or unreadable equations before claiming full coverage.
- Read in multiple passes: map the paper structure, reconstruct its problem-to-method chain, inspect technical details, and audit the evidence. Follow
references/reading_protocol.md. - Track important claims in an evidence ledger with the claim type and source location. Use printed page labels when visible; otherwise use
PDF p.N. Add section, equation, table, or figure identifiers when available. - Produce the note with
assets/paper-note-template.md. Replace every placeholder, retain论文未报告,不适用, or无法可靠读取where appropriate, and never fill a section by invention. - Check numerical values, units, metric directions, equation symbols, baseline names, dataset names, and claim boundaries against the source before finalizing.
What ships with it
3 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 · 63 lines · 116 tokens per session scan A 7b32a3f017c6
read-paper-to-notes is a skill published in the GitHub repository yujie-jason-zhang/polish_skill (18 stars, last pushed 1mo ago), licensed MIT. It adds 116 tokens to every session and 1,124 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
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.
latex-rescue
Diagnose and fix LaTeX compilation errors. Handles undefined control sequences, missing brackets, math mode violations, package conflicts, undefined references, and environment mismatches.
pdf2tex
Convert PDF documents back into editable LaTeX source code. Extracts text, math, tables, figures, and structure. Uses pymupdf + AI for intelligent reconstruction.
awesome-ieee-report
Generates IEEE-format LaTeX technical reports from project requirements and codebase evidence, using academic prose, pseudocode-only explanations, BibTeX references, and IEEEtran formatting.
paper-figures
Extract figures from downloaded papers and include them in survey/review reports. Use when the report covers other groups' work and benefits from their architecture diagrams, experimental plots, or system schematics. Your brain prompt supplies the absolute path to the extract-figures script as {{EXTRACTFIGURES}} — use…
compile-latex
Compile a Beamer LaTeX slide deck with XeLaTeX (3 passes + bibtex). Use when user says "compile", "build the slides", "rebuild the PDF", "run latex", "render the tex", or asks why a .tex file isn't producing a PDF. Operates on Slides/.tex.