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 EvoScientist/EvoSkills --skill paper-writinggit clone --depth 1 https://github.com/EvoScientist/EvoSkillsWrote 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/evoscientist/evoskills/paper-writing)<a href="https://agentmods.dev/skills/evoscientist/evoskills/paper-writing"><img src="https://agentmods.dev/badge/skills/evoscientist/evoskills/paper-writing.svg" alt="Measured on agentmods" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00124 | $0.02322 |
| Opus 5 | $0.00062 | $0.01161 |
| Sonnet 5 | $0.00025 | $0.00464 |
| Haiku 4.5 | $0.00012 | $0.00232 |
Grade A, and why
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 8d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- paper-writing — 95% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Writing
A systematic 11-step workflow for writing academic papers, with section-specific templates and battle-tested writing principles.
When to Use This Skill
- User asks to write or draft a paper or paper section
- User needs LaTeX templates for Abstract, Introduction, Method, Experiments, etc.
- User wants to improve academic writing quality
- User mentions "paper writing", "write introduction", "draft method section", etc.
Artifact Sources
If you used upstream EvoSkills, pull these artifacts before writing:
| Source Skill | Artifact | Used In |
|---|---|---|
paper-planning |
Story summary (task → challenge → insight → contribution → advantage) | Steps 1-2 (Introduction writing plan) |
paper-planning |
Module Motivation Mapping table | Step 3 (Method subsections) |
paper-planning |
Experiment plan (comparisons + ablations + demos) | Step 5 (Experiments section) |
paper-planning |
Pipeline figure sketch | Steps 1, 6 (Method overview figure) |
paper-planning |
Claim-to-experiment mapping | Steps 2, 5 (Abstract, Introduction, Experiments) |
paper-planning |
Fallback narrative (if planned) | Steps 7-8 (Introduction / Conclusion pivot) |
experiment-pipeline |
Stage 1-4 results, ablation tables, trajectory logs | Step 5 (write experiments) |
experiment-craft |
Failure analysis, implementation tricks | Step 3 (Method section), Step 9 (limitations) |
The 11-Step Writing Process
Follow these steps in order. Each step builds on the previous one.
- Draw a pipeline figure sketch — Sketch the method's pipeline figure to clarify the overall approach. The figure highlights novelty, not just explanation.
- Design the story and plan experiments — Outline the paper's story (core contribution, module motivations). List comparison experiments and ablation studies. Draft an Introduction writing plan.
- Write Method — Organize the Method writing plan, then draft Method. Run experiments in parallel.
- Revise Introduction and Method — Iterate on both sections while experiments continue.
- Write Experiments — Once experiments are mostly done, organize the Experiments writing plan, then draft.
- Polish figures — Finalize the pipeline figure. Create the teaser figure.
- Write Related Work — List related papers, group into topics, write paragraphs.
- Review the paper — Self-review Introduction, Method, and Experiments. Use the
paper-reviewskill. - Write Abstract — Organize the Abstract writing plan, then draft.
- Choose the title — List important keywords, then compose an informative title.
- Iterate — Repeatedly review and revise the entire paper.
What ships with it
11 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/paper-skeleton.tex 4.9 KB
- assets/table-style.tex 3.0 KB
- references/abstract-templates.md 3.4 KB
- references/counterintuitive-writing.md 2.4 KB
- references/experiments-guide.md 7.9 KB
- references/introduction-templates.md 8.5 KB
- references/method-templates.md 6.6 KB
- references/related-work-guide.md 2.9 KB
- references/supplementary-guide.md 2.9 KB
- references/writing-practice.md 2.4 KB
- references/writing-principles.md 4.3 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.
- 8d ago First seen · 188 lines · 124 tokens per session scan A 63187b8e2bb3
paper-writing is a skill published in the GitHub repository EvoScientist/EvoSkills (436 stars, last pushed 7d ago), licensed Apache-2.0. It adds 124 tokens to every session and 2,322 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
deltasci
Two-perspective co-reasoning for AI4Science hypothesis generation. Runs a structured 4-round dialogue between a domain scientist (parameterized by a domain pack) and an ML engineer, producing a grounded, falsifiable research hypothesis that is honest about the AI's training-distribution edges. Domain-agnostic via…
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
bio-ortholog-inference
Pull pre-computed ortholog calls from public databases (OrthoDB, Ensembl Compara, OMA browser, eggNOG, PANTHER, KEGG Orthology, HomoloGene) via their REST APIs. Use when orthologs are already curated upstream, when the question is "what is the X ortholog of Y" rather than "how to infer orthology de novo", when…
bioprobench
Score an LLM's biological-protocol reasoning on the BioProBench benchmark: protocol QA, step ordering, error detection, protocol generation, and LLM-judged error reasoning; or generate the responses.
arxiv-package
Package a TeX/LaTeX project into a clean tarball or zip for arXiv upload: file selection, build-artifact exclusion, 00README.XXX generation, ancillary file organization, archive validation. Triggers on: "package for arXiv", "create arXiv tarball", "bundle submission", "zip for arXiv", "prepare arXiv upload", "arXiv…
paper2poster
Convert academic papers (PDF) into conference posters (HTML/PNG). You are the conductor: you decide what each section needs — an original paper figure or text — write the outline, hand-author the poster HTML, and iterate on the render using your own visual read and a blind-reader content quiz. Use when the user wants…