AutoResearchClaw: Skill for Claude Code

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

scientific-writing is a skill for Claude Code from aiming-lab/AutoResearchClaw. It costs 28 tokens per session (626 once invoked), scanned A, original, MIT.

Guidance for writing academic papers using the IMRAD structure: introduction, methods, results, and discussion. It also covers citations, paragraph structure, reporting, and clear academic style.

In plain words
What is it for?
It is for drafting or revising manuscripts, writing abstracts and sections, applying citation styles, and reporting methods, results, limitations, and implications.
Why use it?
It helps organize research findings into a paper that readers can follow and other researchers can reproduce.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is aiming-lab/AutoResearchClaw's own configuration. It tells Claude Code how to work on AutoResearchClaw 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 AutoResearchClaw configures →

About the project

AutoResearchClaw is a system that turns a research idea into a scientific paper through autonomous and collaborative AI research workflows. It is for researchers who want agents to investigate questions, run experiments, and produce papers, with optional human guidance. Catalogue skills and agents provide parts of its research workflow.

aiming-lab/AutoResearchClaw · 14,389 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to aiming-lab/AutoResearchClaw. 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/aiming-lab/AutoResearchClaw/main/.claude/skills/scientific-writing/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/aiming-lab/AutoResearchClaw

Made for: Claude Code.

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 scientific-writing

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

agentmods 80×15 button for scientific-writing

Your own site · 80×15
<a href="https://agentmods.dev/skills/aiming-lab/autoresearchclaw/scientific-writing"><img src="https://agentmods.dev/badge/skills/aiming-lab/autoresearchclaw/scientific-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 626 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00028 $0.00626
Opus 5 $0.00014 $0.00313
Sonnet 5 $0.00006 $0.00125
Haiku 4.5 $0.00003 $0.00063

Measured 11d ago against content hash d744442c5165, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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 11d 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/scientific-writing/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scientific Writing Best Practice

IMRAD Structure

  1. Abstract: State objective, methods, key results, and conclusion in 150-300 words
  2. Introduction: Move from broad context to specific gap to your contribution (funnel structure)
  3. Methods: Sufficient detail for replication; use past tense, passive voice
  4. Results: Present findings without interpretation; pair text with figures/tables
  5. Discussion: Interpret results, compare with literature, acknowledge limitations, state implications

Paragraph-Level Guidance

  1. Each paragraph should convey ONE main idea
  2. Open with a topic sentence; close with a transition to the next paragraph
  3. Write in full flowing prose — never submit bullet points as final manuscript text
  4. Use active voice for clarity: "We measured..." not "Measurements were taken..."
  5. Vary sentence length; aim for average 15-25 words per sentence

Citation Best Practices

  1. Cite primary sources over reviews when making specific claims
  2. Use citation styles consistently (APA, Vancouver, IEEE) per target journal
  3. Every factual claim needs a citation unless it is common knowledge in the field
  4. Avoid citation strings of 5+ references — select the most relevant 2-3
  5. Self-citations should be limited to genuinely relevant prior work

Common Writing Pitfalls

  1. Avoid hedge-stacking: "It might possibly suggest..." — choose one hedge
  2. Do not start sentences with "It is well known that" — cite or remove
  3. Distinguish "significant" (statistical) from "substantial" (practical)
  4. Ensure figures/tables are referenced in text BEFORE they appear
  5. Keep abbreviations to a minimum; define each on first use

Reporting Guidelines

  1. Randomized trials: follow CONSORT checklist
  2. Observational studies: follow STROBE checklist
  3. Systematic reviews: follow PRISMA checklist
  4. Diagnostic accuracy: follow STARD checklist
  5. Always check target journal's author guidelines for specific requirements

Revision Checklist

  1. Verify all figures/tables are cited in text and numbered sequentially
  2. Confirm reference list matches in-text citations exactly
  3. Check that abstract accurately reflects the final manuscript content
  4. Ensure methods section enables independent replication
  5. Read aloud to catch awkward phrasing and run-on sentences

Read the full file on GitHub · 57 lines

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. 11d ago First seen · 57 lines · 28 tokens per session scan A d744442c5165

Subscribe to this mod's changes

scientific-writing is a skill published in the GitHub repository aiming-lab/AutoResearchClaw (14,389 stars, last pushed 22d ago), licensed MIT. It adds 28 tokens to every session and 626 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

aclawdemy

The academic research platform for AI agents. Submit papers, review research, build consensus, and push toward AGI — together.

LeoYeAI/openclaw-master-skills · 30 tokens

adme-property-predictor

Predict ADME (Absorption, Distribution, Metabolism, Excretion) properties for drug candidates using cheminformatics models and molecular descriptors. Evaluates drug-likeness, bioavailability, and pharmacokinetic profile to guide lead optimization and candidate selection in drug discovery.

LeoYeAI/openclaw-master-skills · 61 tokens

baseline-comparison-audit

Audit whether a paper's baseline comparisons are COMPLETE, FAIR, and SIGNIFICANT: a required recent SOTA baseline is missing while 'best/SOTA' is claimed (HP-MISSING-BASELINE); a baseline is undertuned / given less compute-tuning-data, run at a mismatched config, or the equal-budget ablation-as-baseline is absent…

wanshuiyin/Anti-Autoresearch · 310 tokens

eval-design-forensics

Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan…

wanshuiyin/Anti-Autoresearch · 458 tokens

proof-derivation-forensics

Family-G proof & derivation integrity forensics: does a THIRD PARTY's written proof/derivation actually establish its theorem, or does it skip an obligation, assume its own conclusion, take an invalid step, drift a symbol's meaning, or smuggle an unstated assumption? Decides from the WRITTEN proof/derivation …

wanshuiyin/Anti-Autoresearch · 222 tokens

arxiv-summarizer-orchestrator

End-to-end orchestration skill for periodic arXiv collection and reporting using three sub-skills: arxiv-search-collector, arxiv-paper-processor, and arxiv-batch-reporter. Supports manual language control across all markdown outputs and Stage-B processing strategy (subagentparallel default max 5, or serial).

InternLM/WildClawBench · 75 tokens