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 chgagne/claude-skills-research --skill proofreading-paper-writinggit clone --depth 1 https://github.com/chgagne/claude-skills-researchWrote 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/chgagne/claude-skills-research/proofreading-paper-writing)<a href="https://agentmods.dev/skills/chgagne/claude-skills-research/proofreading-paper-writing"><img src="https://agentmods.dev/badge/skills/chgagne/claude-skills-research/proofreading-paper-writing/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/chgagne/claude-skills-research/proofreading-paper-writing"><img src="https://agentmods.dev/badge/skills/chgagne/claude-skills-research/proofreading-paper-writing.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 | $0.00108 | $0.03006 |
| Opus 5.5 | $0.00043 | $0.01202 |
| Sonnet 5.5 | $0.00022 | $0.00601 |
| Haiku 4.5 | $0.00011 | $0.00301 |
Grade A, and why
proofreading-paper-writing 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 7d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proofreading Paper Writing
Overview
A critical reader for the prose of an ML paper. It judges each sentence, paragraph and
framing choice against a field profile (what well-written papers at the venue do) and
phrases fixes in the author profile (how these authors write when they write well).
Field decides what is a defect; author decides the wording of the fix. Proposals become a
second changes.sty author, LG, in dark green, next to the blue science author CL
that reviewing-paper-sources uses, so a reader sees at a glance which marks are about
the science and which about the writing.
Four levels, tiered in the PDF: mechanics as bare track changes, style as track
changes with a W<n> margin tag, flow and framing as margin comments only. Every
W<n> is an entry in writing-report.md.
Inputs and outputs
Input: a paper directory with a compiling main.tex (or the pdfshim pseudo-source),
optionally an existing main-annotated.tex from the reviewer. Outputs, all in the paper
directory, none committed:
| File | Content |
|---|---|
main-annotated.tex / .pdf |
existing CL markup plus LG markup |
writing-report.md / .pdf |
header, counts, one entry per W<n>, cut appendix |
writing-ledger.jsonl |
every proposal with its final status |
glossary.md |
the paper's terms, first definitions, variants found |
Private state (never in this repo): $STYLE_PROFILES_DIR (default ~/Claude/style-profiles)
with profiles, sources, preferences.md, preferences-pending.md. See
reference/building-style-profiles.md.
Workflow
0. Mode and profiles. Mode A (internal, authors will see the copy) runs everything.
Mode B (external referee) runs only step 1 and writes its top ten findings as prose into
the review's §8; no annotated copy, no calibration, no author profile. Then: does a field
profile exist for this subfield, and an author profile for these authors? If not, propose
corpora and build them (reference/building-style-profiles.md); if the user declines or
the fetch fails, run on reference/style-defaults.md alone and say so in the report
header. In Mode A, if /Applications/Antidote exists, ask in the same round whether to add
the Antidote pass (step 3b). Read preferences.md now; every rule in it binds every agent below.
What ships with it
37 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.
- assets/antidote-rows.py 3.1 KB runs code
- assets/changes-author-LG.tex 212 B
- assets/fetch-corpus.py 1.7 KB runs code
- assets/profile-stats.py 1.3 KB runs code
- assets/proofread/__init__.py 0 B runs code
- assets/proofread/anchors.py 5.5 KB runs code
- assets/proofread/antidote.py 9.0 KB runs code
- assets/proofread/apply.py 4.3 KB runs code
- assets/proofread/build.py 3.2 KB runs code
- assets/proofread/corpus.py 3.0 KB runs code
- assets/proofread/ledger.py 3.7 KB runs code
- assets/proofread/markup.py 1.9 KB runs code
- assets/proofread/preamble.py 2.8 KB runs code
- assets/proofread/report.py 3.6 KB runs code
- assets/proofread/stats.py 5.1 KB runs code
- assets/render-ledger.py 4.2 KB runs code
- assets/tests/__init__.py 0 B runs code
- assets/tests/fixtures/antidote-corrected.tex 761 B
- assets/tests/fixtures/antidote-orig.tex 725 B
- assets/tests/fixtures/tiny.tex 750 B
- assets/tests/test_anchors.py 4.2 KB runs code
- assets/tests/test_antidote.py 6.1 KB runs code
- assets/tests/test_apply.py 5.7 KB runs code
- assets/tests/test_build.py 2.9 KB runs code
- assets/tests/test_cli.py 3.0 KB runs code
- assets/tests/test_corpus.py 3.1 KB runs code
- assets/tests/test_ledger.py 3.3 KB runs code
- assets/tests/test_markup.py 3.3 KB runs code
- assets/tests/test_preamble.py 2.8 KB runs code
- assets/tests/test_report.py 2.8 KB runs code
- assets/tests/test_stats.py 2.4 KB runs code
- reference/antidote-pass.md 3.3 KB
- reference/building-style-profiles.md 3.0 KB
- reference/critique-rubric.md 3.3 KB
- reference/ledger-schema.md 2.6 KB
- reference/style-defaults.md 2.6 KB
- reference/writing-report-template.md 1.2 KB
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.
- 7d ago Changed · +9 lines ed1136433f2d
- 20d ago First seen · 176 lines · 108 tokens per session scan A cc02f8d09438
proofreading-paper-writing is a skill published in the GitHub repository chgagne/claude-skills-research (5 stars, last pushed 2d ago), licensed MIT. It adds 108 tokens to every session and 3,006 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-26.
Other skills, from other repositories
paper-writer
Medical/scientific paper writing workflow skill. Manages the full pipeline from literature search to submission-ready manuscript. Creates and manages a project directory with IMRAD-format section files, literature matrix, reference management, and quality checklists. Supports both English and Japanese papers.…
food-research
Run a comprehensive, multi-source literature and evidence-synthesis workflow for food & nutrition science. Use when the user wants to research a food/nutrition topic in depth, do a literature review, build an evidence brief, screen and synthesize many sources, verify citations, or scope a systematic review.…
food-paper
Multi-subagent manuscript system for food & nutrition science covering the whole research process: understand the field, frame research questions, curate and analyze data, run statistics, build figures and tables, construct the discussion, draft, polish, and self-review — journal-aware throughout. Includes a…
food-pipeline
Master orchestrator for the whole food & nutrition research-to-publication workflow. Coordinates the specialist skills — each with its own subagent set — into one governed path: journal selection, research (food-research / food-deep-research), writing & analysis (food-paper), figures (food-figure), peer review…
food-review
Multi-reviewer peer-review system for food & nutrition manuscripts. Simulates an editorial panel — a coordinating editor, three domain reviewers (methodology/statistics, domain/novelty, integrity/ethics), and a devil's advocate — plus a formatting-compliance check against the target journal (APA 7.0 by default, or a…
food-deep-research
General-purpose deep research that produces a fully written, source-validated literature review on any question: scope it, design the method, discover and screen sources by journal ranking, validate every source, extract and verify evidence, synthesize, stress-test, then write and format the review (APA 7.0 by…