New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Sci Paper Reviewer

by aipoch in aipoch/medical-research-skills

Simulates a strict SCI peer-review workflow; trigger when a user uploads or pastes a manuscript (PDF/DOC/DOCX/TXT) and requests an innovation score (1–12) plus experimental-logic vulnerability…

MITAuto-check passedDocuments & Office

Install Sci Paper Reviewer

skills CLI
$ npx skills add aipoch/medical-research-skills --skill sci-paper-reviewer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install aipoch/medical-research-skills sci-paper-reviewer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/aipoch/medical-research-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/scientific-skills/Other/sci-paper-reviewer .claude/skills/sci-paper-reviewer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
sci-paper-reviewer
GitHub stars
1.9k
Token cost
~1.8k tokens
SKILL.md length
673 words
Files
4 (incl. scripts, references)
Skills in repo
578
Repo updated
First seen
Licence
MIT

At a glance

Simulates a strict SCI peer-review workflow; trigger when a user uploads or pastes a manuscript (PDF/DOC/DOCX/TXT) and requests an innovation score (1–12) plus experimental-logic vulnerability…

  • Works in 8 steps: Parse a file and review the extracted text → Direct text input (no file) → Document Processing Rules → …
  • Pastes a manuscript (PDF/DOC/DOCX/TXT) and requests an innovation score (1–1
  • SKILL.md covers When to Use, Key Features, Dependencies and Example Usage, plus 1 more section
  • Runs Python scripts from its folder; calls python

What it does

Sci Paper Reviewer is an agent skill from aipoch/medical-research-skills. Simulates a strict SCI peer-review workflow; trigger when a user uploads or pastes a manuscript (PDF/DOC/DOCX/TXT) and requests an innovation score (1–12) plus experimental-logic vulnerability checks and revision suggestions.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts and reference files (for example `references/document_parser_requirements.md`, `sci-paper-reviewer_audit_result_v1.json` and `scripts/enhanced_document_parser.py`).

It sits in Documents & Office, covering Word documents, PDF and Peer review. It works with Microsoft Word and pypdf. The repository describes itself as: Hundreds of agent skills for medical research, including protocol design, data analysis, evidence insights, and academic writing. The licence is MIT.

When your agent uses it

  • Pastes a manuscript (PDF/DOC/DOCX/TXT) and requests an innovation score (1–1
  • Plus experimental-logic vulnerability checks and revision suggestions

Example prompts

  • “Use the sci-paper-reviewer skill to simulate a strict SCI peer-review workflow; trigger when a user uploads or pastes a manuscript…”
  • “/sci-paper-reviewer”

Requirements

  • Python 3

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Parse a file and review the extracted text
  2. Direct text input (no file)
  3. Document Processing Rules
  4. Section Extraction (for analysis)
  5. Research Type Classification
  6. Innovation Evaluation (Score 1–12)
  7. Logic Vulnerability Screening (Results-Focused)
  8. Required Output Structure (Final Review Report)

What it can do on your machine

Read from SKILL.md and the folder at commit 686e09d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sci Paper Reviewer loads about 1.8k tokens when it runs, and up to ~2.1k if it reads all its reference files. Until then it costs about 61 tokens; SKILL.md has 673 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~61
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from aipoch/medical-research-skills at commit 686e09d, republished under its MIT licence (© aipoch). 673 words, ~1,773 tokens.

Download SKILL.mdSave it as .claude/skills/sci-paper-reviewer/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
sci-paper-reviewer
description
Simulates a strict SCI peer-review workflow; trigger when a user uploads or pastes a manuscript (PDF/DOC/DOCX/TXT) and requests an innovation score (1–12) plus experimental-logic vulnerability checks and revision suggestions.
license
MIT
author
AIPOCH

Source: https://github.com/aipoch/medical-research-skills

When to Use

  • When a user uploads a manuscript (PDF/DOC/DOCX/TXT) and asks for an SCI-style peer review.
  • When a user wants an innovation/novelty score (1–12) with explicit criteria and justification.
  • When a user needs a logic audit of the Results section (false positives, missing controls, broken mechanism chains).
  • When a user requests actionable experimental revisions (what to add/verify, which controls are missing).
  • When a user provides copy-pasted manuscript text and wants the same structured review output.

Key Features

  • Automatic manuscript parsing for PDF, Word, and TXT, plus direct text input.
  • Section-oriented analysis: focuses on Abstract, Results, Introduction, and Discussion.
  • Research type classification: Materials, Basic Medical, Clinical, or Review.
  • Innovation evaluation with a strict 1–12 scoring rubric (originality, theory extension, translational path).
  • Logic vulnerability screening in Results:
    • false-positive risk (lack of orthogonal validation)
    • mechanism breaks (unverified upstream/downstream links)
    • control failures (missing double-negative controls)
  • Structured review report with numbered, concrete modification suggestions (no generic filler).

Dependencies

  • Python >=3.9
  • Document parsing libraries (optional but supported):
    • pypdf (version varies)
    • pdfplumber (version varies)
    • PyMuPDF (version varies)
    • PyPDF2 (version varies)
    • python-docx (version varies)

The parser should fall back to basic extraction if some advanced libraries are unavailable.

Example Usage

1) Parse a file and review the extracted text
bash
# Parse an uploaded manuscript into a text file (recommended to avoid console buffer limits)
python scripts/enhanced_document_parser.py /path/to/manuscript.pdf extracted_content.txt

Then provide extracted_content.txt to the skill (or paste its content) and request a review, for example:

text
Please review this manuscript as a strict SCI reviewer.
Requirements:
1) Classify research type.
2) Evaluate innovation (score 1–12) using your rubric.
3) Screen Results for logic vulnerabilities (false positives, mechanism breaks, control failures).
4) Output a structured report with numbered experimental modification suggestions.
[PASTE CONTENT OF extracted_content.txt HERE]
2) Direct text input (no file)
text
I will paste the manuscript text below. Please perform an SCI-style review:
- Extract Abstract/Results/Introduction/Discussion (as available)
- Classify research type
- Innovation score (1–12) and rationale
- Logic vulnerability screening
- Provide numbered modification suggestions only (no generic “other suggestions”)
[PASTE MANUSCRIPT TEXT]

Implementation Details

1) Document Processing Rules
  • Input detection:
    • If a file is provided, detect type: PDF, DOCX, DOC, or TXT.
    • If text is pasted, process it directly.
  • Parsing script:
    • Use: scripts/enhanced_document_parser.py
    • Recommended invocation (write to file):
      • python scripts/enhanced_document_parser.py <file_path> extracted_content.txt
    • Then read extracted_content.txt as the canonical extracted content.
  • Failure handling:
    • If the parser outputs Warning: No text extracted, treat the file as likely scanned/image-based and inform the user that OCR may be required before review.
2) Section Extraction (for analysis)

From the parsed content, extract (as available):

  • Abstract (work summary)
  • Results (core experimental findings and data claims)
  • Introduction & Discussion (background, positioning, interpretation)

If headings are missing, infer sections by typical academic structure and transitions.

3) Research Type Classification

Classify into one of:

  • Materials Research
  • Basic Medical Research
  • Clinical Research
  • Review

Use cues such as study subjects (cells/animals/patients), endpoints, materials synthesis/characterization, and whether the manuscript is primarily summarizing prior work.

Show full SKILL.md (298 more words)Show less
4) Innovation Evaluation (Score 1–12)

Evaluate primarily from Introduction and Discussion (and claims in Abstract), using the following rubric:

  • Major Original (9–12): Proposes a fundamentally new mechanism or a disruptive hypothesis.
  • Clear Translation Path (8–11): Identifies targetable markers and provides inhibitor screening/validation data.
  • Theory Extension (5–8): Extends the boundary or applicability of an existing theory/framework.
  • Potential Application Value (4–7): Reveals regulatory mechanisms but lacks actionable intervention/translation.
  • Validation Study (1–4): Primarily replicates/validates known theories or fills incremental details.
  • Heuristic note: “miRNA-based novelty” is generally treated as average unless supported by strong mechanistic and translational evidence.
5) Logic Vulnerability Screening (Results-Focused)

Screen the Results for the following vulnerabilities:

  1. False Positive Risk

    • Claims rely on a single assay/marker without orthogonal validation (e.g., only qPCR without protein-level confirmation; only one antibody without specificity checks).

  2. Mechanism Break

    • Upstream/downstream relationships are asserted but not experimentally verified (e.g., correlation presented as causation; missing rescue/epistasis tests).

  3. Control Failure

    • Key experiments lack appropriate controls, especially double-negative controls where required (e.g., vehicle + non-targeting controls; isotype controls; sham operations; matched baseline).

  4. Basic Medicine Rule (method sufficiency)

    • For cell-level knockdown, siRNA/shRNA is sufficient; CRISPR is not mandatory unless the claim requires stable knockout or allele-specific inference.
6) Required Output Structure (Final Review Report)

The generated review must follow this structure:

  1. Document Information

    • File type and processing status
    • Extracted sections overview (what was found/used)
    • Parser used (enhanced parser vs. fallback)

  2. Innovation Evaluation

    • Provide the innovation level and rationale (score may be stated explicitly or implied, but must map to the rubric).
    • Use academic, precise language.

  3. Experimental Modification Suggestions

    • Provide only concrete, logic-driven revisions derived from the vulnerability screening.
    • Number items as 2.1, 2.2, 2.3, ...
    • Avoid generic “Other suggestions”; each item must specify what experiment/control/verification to add and what claim it would support or falsify.

© aipoch, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts, references) in scientific-skills/Other/sci-paper-reviewer of aipoch/medical-research-skills.

  • SKILL.md
  • references/document_parser_requirements.md
  • sci-paper-reviewer_audit_result_v1.json
  • scripts/enhanced_document_parser.py

Open the folder on GitHubat commit 686e09d

Compare with similar skills

Sci Paper Reviewer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Sci Paper Reviewer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sci Paper Reviewer this skillaipoch/medical-research-skills1.9k—~1.8kAutomated safety check: PassMIT
PDFzai-org/ZCode7.7k—~18kAutomated safety check: NotesProprietary
AI Review SkillNeuroDong/Ai-Review628—~2.5kAutomated safety check: PassMIT
File Converteraiskillstore/marketplace4331 repos~895Automated safety check: PassNone
Document Processingericrisco/rsc-harness180—~2.4kAutomated safety check: PassMIT
Paper CovertGRIND-Lab-Core/night_owl_research_agent106—~2.1kAutomated safety check: NotesNone

Similar skills

  • PDF

    zai-org/ZCode

    Professional PDF toolkit covering four production workflows: reports, creative visuals, academic LaTeX, and existing PDF processing.

    7.7k GitHub stars~18k tokensUpdated today
    Documents & OfficeAuto-check: notes

  • AI Review Skill

    NeuroDong/Ai-Review

    Generates structured AI paper reviews (SoT style) for LaTeX, PDF, and Word manuscripts.

    628 GitHub stars~2.5k tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed

  • File Converter

    aiskillstore/marketplace

    This skill handles file format conversions across documents (PDF, DOCX, Markdown, HTML, TXT), data files (JSON, CSV, YAML, XML, TOML), and images (PNG, JPG, WebP, SVG, GIF).

    433 GitHub starsUsed in 1 repo~895 tokens
    Documents & OfficeAuto-check passed

  • Document Processing

    ericrisco/rsc-harness

    A skill your agent uses when the deliverable is a document's bytes or its literal content — text/tables out of PDFs, AcroForm fill and flatten, page merge/split, PDF/DOCX from templates, OCR of…

    180 GitHub stars~2.4k tokensUpdated yesterday
    Documents & OfficeAuto-check passed

  • Paper Covert

    GRIND-Lab-Core/night_owl_research_agent

    Converts the final Markdown manuscript from paper-draft / paper-review-loop into a submission package for the target venue — modular LaTeX (one file per section), compiled PDF, and Word .docx.

    106 GitHub stars~2.1k tokensUpdated 5 mo ago
    Documents & OfficeAuto-check: notes

  • Office Artifacts

    Prismer-AI/PrismerCloud

    Generate real DOCX, PPTX, XLSX, PDF, CSV files using python-docx / python-pptx / openpyxl / reportlab by writing them into the dispatch artifacts dir, then explicitly deliver each one with cloud…

    1.6k GitHub stars~2.6k tokensUpdated today
    Documents & OfficeAuto-check passed

More from aipoch/medical-research-skills

All 578 skills in this repo

  • Academic Poster Generator

    aipoch/medical-research-skills

    Complete workflow for generating academic research posters from PDF literature; use when you need to extract paper content from PDFs and produce a LaTeX-based poster…

    1.9k GitHub stars~2.2k tokensUpdated 24 days ago
    Auto-check passed

  • Diagnostic Study Quality Assessment Quadas

    aipoch/medical-research-skills

    Analyzes clinical diagnostic accuracy studies for bias using the QUADAS-2 tool.

    1.9k GitHub stars~1.4k tokensUpdated 24 days ago
    Auto-check passed

  • Exploratory Data Analysis

    aipoch/medical-research-skills

    Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats.

    1.9k GitHub stars~3.7k tokensUpdated 24 days ago
    Auto-check passed

  • Iso Certification

    aipoch/medical-research-skills

    A toolkit for preparing ISO 13485:2016 certification documentation for medical device QMS.

    1.9k GitHub stars~1.8k tokensUpdated 24 days ago
    Auto-check passed

  • Journal Skills

    aipoch/medical-research-skills

    Recommends target journals for manuscript submission by analyzing the paper topic/abstract and the journal distribution of similar PubMed literature; use when users ask for journal…

    1.9k GitHub stars~1.7k tokensUpdated 24 days ago
    Auto-check passed

  • Latex Posters

    aipoch/medical-research-skills

    Creates academic-poster writing packages for LaTeX using beamerposter, tikzposter, or baposter.

    1.9k GitHub stars~1.3k tokensUpdated 24 days ago
    Auto-check passed

Works with

Categories

Questions about Sci Paper Reviewer

What does Sci Paper Reviewer do?

Simulates a strict SCI peer-review workflow; trigger when a user uploads or pastes a manuscript (PDF/DOC/DOCX/TXT) and requests an innovation score (1–12) plus experimental-logic vulnerability…. Sci Paper Reviewer is an agent skill from aipoch/medical-research-skills. Simulates a strict SCI peer-review workflow; trigger when a user uploads or pastes a manuscript (PDF/DOC/DOCX/TXT) and requests an innovation score (1–12) plus experimental-logic vulnerability checks and revision suggestions.

When should I use Sci Paper Reviewer?

Sci Paper Reviewer fits situations like: pastes a manuscript (PDF/DOC/DOCX/TXT) and requests an innovation score (1–1; plus experimental-logic vulnerability checks and revision suggestions.

How do I install Sci Paper Reviewer in Claude Code?

Run `npx skills add aipoch/medical-research-skills --skill sci-paper-reviewer -a claude-code`. Or copy the skill folder (scientific-skills/Other/sci-paper-reviewer in aipoch/medical-research-skills) into .claude/skills/sci-paper-reviewer in your project. Claude Code loads it when a task matches its description.

How do I install Sci Paper Reviewer in Codex?

Run `npx skills add aipoch/medical-research-skills --skill sci-paper-reviewer -a codex`. Or copy the skill folder (scientific-skills/Other/sci-paper-reviewer in aipoch/medical-research-skills) into .agents/skills/sci-paper-reviewer in your project. Codex loads it when a task matches its description.

Can I use Sci Paper Reviewer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aipoch/medical-research-skills --skill sci-paper-reviewer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sci-paper-reviewer, .gemini/skills/sci-paper-reviewer, .github/skills/sci-paper-reviewer and .opencode/skills/sci-paper-reviewer in your project.

What does Sci Paper Reviewer need to run?

Going by SKILL.md and its folder, Sci Paper Reviewer needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Sci Paper Reviewer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Sci Paper Reviewer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Sci Paper Reviewer use?

Sci Paper Reviewer is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Sci Paper Reviewer use?

About 1.8k tokens (SKILL.md is roughly 7.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 306 tokens, read only when the agent opens those files.

What are the alternatives to Sci Paper Reviewer?

Skills that share tags, products or a category with Sci Paper Reviewer: PDF (zai-org/ZCode, 7.7k stars), AI Review Skill (NeuroDong/Ai-Review, 628 stars), File Converter (aiskillstore/marketplace, 433 stars) and Document Processing (ericrisco/rsc-harness, 180 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sci Paper Reviewer?

aipoch (a GitHub organization) maintains it in aipoch/medical-research-skills, which has 1,937 GitHub stars. The repository holds 578 skills in this directory. The repository was last updated on September 17, 2026.

Source: aipoch/medical-research-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.