Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/erafat/skillsnpx agentmods add skills/erafat/skills/scientific-writingWrote 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/erafat/skills/scientific-writing)<a href="https://agentmods.dev/skills/erafat/skills/scientific-writing"><img src="https://agentmods.dev/badge/skills/erafat/skills/scientific-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/erafat/skills/scientific-writing"><img src="https://agentmods.dev/badge/skills/erafat/skills/scientific-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 | $0.00088 | $0.04862 |
| Opus 5 | $0.00044 | $0.02431 |
| Sonnet 5 | $0.00018 | $0.00972 |
| Haiku 4.5 | $0.00009 | $0.00486 |
Grade A, and why
scientific-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 10d 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.
This is a copy
94% identical to scientific-writing — 54 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 484 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scientific Writing
Overview
This is the core skill for the deep research and writing tool—combining AI-driven deep research with well-formatted written outputs. Every document produced is backed by comprehensive literature search and verified citations through the research-lookup skill.
Scientific writing is a process for communicating research with precision and clarity. Write manuscripts using IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, and reporting guidelines (CONSORT/STROBE/PRISMA). Apply this skill for research papers and journal submissions.
Critical Principle: Always write in full paragraphs with flowing prose. Never submit bullet points in the final manuscript. Use a two-stage process: first create section outlines with key points using research-lookup, then convert those outlines into complete paragraphs.
When to Use This Skill
This skill should be used when:
- Writing or revising any section of a scientific manuscript (abstract, introduction, methods, results, discussion)
- Structuring a research paper using IMRAD or other standard formats
- Formatting citations and references in specific styles (APA, AMA, Vancouver, Chicago, IEEE)
- Creating, formatting, or improving figures, tables, and data visualizations
- Applying study-specific reporting guidelines (CONSORT for trials, STROBE for observational studies, PRISMA for reviews)
- Drafting abstracts that meet journal requirements (structured or unstructured)
- Preparing manuscripts for submission to specific journals
- Improving writing clarity, conciseness, and precision
- Ensuring proper use of field-specific terminology and nomenclature
- Addressing reviewer comments and revising manuscripts
Visual Enhancement with Scientific Schematics
⚠️ MANDATORY: Every scientific paper MUST include at least 1-2 AI-generated figures using the scientific-schematics skill.
This is not optional. Scientific papers without visual elements are incomplete. Before finalizing any document:
- Generate at minimum ONE schematic or diagram using scientific-schematics
- Prefer 2-3 figures for comprehensive papers (methods flowchart, results visualization, conceptual diagram)
What ships with it
5 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.
- 10d ago First seen · 484 lines · 88 tokens per session scan A 5a3e0eece589
scientific-writing is a skill published in the GitHub repository erafat/skills (16 stars, last pushed 2mo ago), licensed MIT. It adds 88 tokens to every session and 4,862 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to scientific-writing, differing in 54 lines, and is treated as a copy.
Other skills, from other repositories
dynare-copilot
Write, run, debug, modify, and review Dynare .mod files across the full lifecycle of macro models (DSGE/RBC/NK/HANK/OLG). MUST trigger when: ① writing a new .mod from scratch or translating paper equations into Dynare code; ② replicating a published model ("replicate Smets-Wouters 2007", "code it per GK 2011"); ③…
download-xhs-videos
A process for downloading a Xiaohongshu creator’s videos to a local folder. Xiaohongshu, also called RedNote, is a Chinese social-media platform.
xhs-creator-distill
A research skill for analysing Xiaohongshu, also called RedNote, a Chinese social platform, and turning a creator’s posts or account data into an evidence-based content profile.
pixel2motion
Turn a raster logo (PNG/JPG/WebP/screenshot) into a clean minimal SVG with edge smoothness as the primary hard gate and IoU optimized as high as reasonably possible without a fixed global threshold, then into a choreographed logo animation delivered as standalone JS-rendered HTML, applying Disney's 12 animation…
mandela
Audit any eval, metric, experiment, or benchmark for leakage — does external ground-truth enter independently, or are the model, scorer, and designer just confirming a result no outside truth ever produced? Use before trusting any 'how we'll know it worked' — an A/B, a holdout, a score, a validation — and whenever a…
anti-defensive-writing-en
Stops defensive writing across the entire paper lifecycle — writing, revising, cutting, and organizing experiments. Treats the paper as a press conference, not a project summary, lab log, or self-audit: identify the single most publishable strength of the work and build the most favorable, complete, and persuasive…