PrettySeriousResearcher: Skill for Claude Code

.claude/skills/research-writing/SKILL.md

research-writing is a skill for Claude Code from fbabelle/PrettySeriousResearcher. It costs 56 tokens per session (5,491 once invoked), scanned A, original, Apache-2.0.

A workflow for writing and revising research papers after the results are ready. It covers sections, figures, tables, citations, appendices, draft versions, and manuscript files.

In plain words
What is it for?
Turning completed research results into a structured paper, including a full arXiv draft and a shorter version for a specific publication venue.
Why use it?
It keeps evidence, paper drafts, compiled PDFs, and project documentation organised while the manuscript changes.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is fbabelle/PrettySeriousResearcher's own configuration. It tells Claude Code how to work on PrettySeriousResearcher itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything PrettySeriousResearcher configures →

Part of the research-paper-skills plugin — 17 skills shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to fbabelle/PrettySeriousResearcher. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/fbabelle/PrettySeriousResearcher/main/.claude/skills/research-writing/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/fbabelle/PrettySeriousResearcher

Made for: Claude Code.

Or install research-paper-skills, the plugin that ships this one along with the rest of its 17 skills.

Wrote 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.

agentmods badge for research-writing

README.md
[![agentmods](https://agentmods.dev/badge/skills/fbabelle/prettyseriousresearcher/research-writing/github.svg)](https://agentmods.dev/skills/fbabelle/prettyseriousresearcher/research-writing)
Your own site
<a href="https://agentmods.dev/skills/fbabelle/prettyseriousresearcher/research-writing"><img src="https://agentmods.dev/badge/skills/fbabelle/prettyseriousresearcher/research-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.

agentmods 80×15 button for research-writing

Your own site · 80×15
<a href="https://agentmods.dev/skills/fbabelle/prettyseriousresearcher/research-writing"><img src="https://agentmods.dev/badge/skills/fbabelle/prettyseriousresearcher/research-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,491 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.05491
Opus 5 $0.00028 $0.02746
Sonnet 5 $0.00011 $0.01098
Haiku 4.5 $0.00006 $0.00549

Measured 4d ago against content hash fda8d004e4fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

research-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 4d 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.

.claude/skills/research-writing/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase 4 — Writing the paper

Results don't speak for themselves — this phase turns evidence into a manuscript a reviewer will accept. The deliverable is a complete, coherent draft with figures, tables, references, and appendix, in the right voice for the venue.

Drafts & versioning

Write under drafts/ as md + pdf pairs: each drafts/vNN-title.md (the source of truth) has a compiled companion drafts/vNN-title.pdf, recompiled whenever the draft changes meaningfully so the pair stays in sync. Per the user's working agreement, when a chunk of effort exceeds ~5 agent-active hours, start a new versioned draft (drafts/v02-*.md + .pdf) rather than editing the old one in place, so the trajectory is preserved; periodically untrack superseded drafts (move the whole set to drafts/_archive/, which is gitignored) — see research-repo-hygiene. The skeleton from Phase 1 is v01. The main/arXiv draft additionally carries a LaTeX source (vNN-title.tex) alongside the md+pdf — see the next section.

Two versions: the main (arXiv) draft is the priority; the short version is venue-targeted

Prioritize the main (full) draft. It is the complete paper and the one posted to arXiv. A short version is derived from it later, and only once a target venue is chosen.

  • Main / full draftvNN-title.md is the working source of truth (every detail, all ablations, the full method). Maintain it in three forms so it is arXiv-ready: Markdown (vNN-title.md, author and edit here), LaTeX (vNN-title.tex — arXiv's expected submission form), and the compiled PDF (vNN-title.pdf, compiled from the canonical venue/arXiv source — see "Compiling drafts to PDF"). arXiv wants LaTeX source, so the .tex is a first-class deliverable, not an afterthought.
    • The IP/vagueness decision lives with this version, because it's what goes public: mask the recipe, never the evidence. You may abstract exact hyperparameters, proprietary data recipes, engineering tricks, and exact feature formulas (say so plainly) — but the core mechanism (critique-able by an expert), honest complete results, the key ablation, named datasets/eval setup, and leakage/overfitting controls must stay concrete. In finance you may withhold the strategy recipe but never the out-of-sample / multiple-testing / deflated-metric controls. Hiding the evidence (not just the recipe) reads as "marketing, not science" — see references/short-version-guide.md for the safe-vs-concrete table and backfire warnings.
  • Short versionvNN-title-short.md: a distillation built for a specific target conference/journal, conforming to that venue's page/column limit, template, formatting/syntax, required sections, and content/disclosure rules (e.g. double-blind anonymization, ethics/checklist, artifact policy). Don't guess the requirements — research and confirm them first via research-venue-selection (which finds the venue and its exact rules); the short version is not made until a venue is selected.

Read the full file on GitHub · 145 lines

Files

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.

Changes

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.

  1. 4d ago Changed · +10 lines fda8d004e4fa
  2. 9d ago First seen · 135 lines · 56 tokens per session scan A 74098dd6a333

Subscribe to this mod's changes

research-writing is a skill published in the GitHub repository fbabelle/PrettySeriousResearcher (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 56 tokens to every session and 5,491 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

phylogenetics

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

K-Dense-AI/scientific-agent-skills · 68 tokens

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens