Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Scientific Writing

Draft, revise, and audit scientific manuscripts with enforced evidence provenance, reporting-guideline coverage, and authorship/disclosure checks.

Content & WritingAdvanced★ 33,030⑂ 3,248AI score 9/10Last updated: Aug 9, 2026

What it does

Keeps drafting, evidence verification, and submission approval as separate, auditable stages.

  • Hard anti-fabrication rules for citations, DOIs, numbers, methods, ethics statements and disclosures
  • Evidence binding: E IDs for sources, C IDs for claims, N/M/O/R IDs for numeric facts, methods, outcomes and results, anchored inline in the draft
  • Reporting-guideline routing for CONSORT 2025, SPIRIT 2025, PRISMA 2020, STROBE, STARD-AI, TRIPOD+AI, CARE, ARRIVE 2.0, SQUIRE 2.0, CHEERS 2022
  • Authorship, CRediT, AI-use disclosure and open-science statement validation
  • Local linters for method/result mismatches, duplicate reference identifiers, placeholders and draft banners
  • Confidentiality rules that block sending unpublished or peer-review material to external services

All bundled Python scripts are offline, deterministic, dependency-free and need no API keys.

Who it's for

  • Researchers and graduate students preparing journal submissions
  • Clinical trial, systematic review, and diagnostic-accuracy teams bound by checklists
  • Labs and institutions that must comply with ICMJE/journal AI-disclosure policies
  • R&D teams writing traceable technical reports

Examples

  1. Bootstrap a workspace: run scaffold_manuscript.py to generate a CONSORT-2025 randomized-trial draft plus manifests and claim CSV.
  2. Reconcile numbers: run check_consistency.py to catch a sample size in Methods that disagrees with Results, then name the analysis-set difference explicitly.
  3. Pre-submission audit: run audit_claims.py and lint_manuscript.py to confirm no unverified citations or placeholders remain before a human sets submission_ready.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/scientific-writing/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/scientific-writing folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/scientific-writing/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/scientific-agent-skills && mkdir -p ~/.claude/skills && cp -r /tmp/scientific-agent-skills/skills/scientific-writing ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Create the skills directory: mkdir -p ~/.claude/skills
  4. Copy the skill in: cp -r scientific-agent-skills/skills/scientific-writing ~/.claude/skills/
  5. Check Python if you want the CLIs: python3 --version (3.11+ required; no extra packages needed).
  6. Restart Claude Code and try a prompt like "Set up a manuscript workspace for a cohort study using STROBE."
View source on GitHub ↗License: MIT