Agent skill

Academic Highlight Generator

by aipoch in aipoch/medical-research-skills

Generates submission-ready Elsevier/SCI Highlights from manuscript text or extracted PDF/DOCX/TXT content.

MITAuto-check passedDocuments & Office

Install Academic Highlight Generator

skills CLI
$ npx skills add aipoch/medical-research-skills --skill academic-highlight-generator -a claude-code

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

GitHub CLI
$ gh skill install aipoch/medical-research-skills academic-highlight-generator --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/Academic Writing/academic-highlight-generator' .claude/skills/academic-highlight-generator && 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
academic-highlight-generator
GitHub stars
2k
Token cost
~1.5k tokens
SKILL.md length
687 words
Files
4 (incl. scripts, references)
Skills in repo
578
Repo updated
First seen
Licence
MIT

At a glance

Generates submission-ready Elsevier/SCI Highlights from manuscript text or extracted PDF/DOCX/TXT content.

  • Works in 5 steps: Validate source sufficiency → Extract text if needed → Detect article type → …
  • A user needs 3-5 concise
  • SKILL.md covers When to Use, When Not to Use, Required Inputs and Output Contract, plus 5 more sections
  • Runs Python scripts from its folder; calls python

What it does

Academic Highlight Generator is an agent skill from aipoch/medical-research-skills. Generates submission-ready Elsevier/SCI Highlights from manuscript text or extracted PDF/DOCX/TXT content. Use when a user needs 3-5 concise, evidence-grounded highlight bullets for a research paper, review, meta-analysis, case report, or bioinformatics manuscript.

Its SKILL.md is about 1.5k 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 `academic-highlight-generator_audit_result_v1.json`, `references/prompts.md` and `scripts/extract_text.py`).

It sits in Documents & Office, covering Word documents, Bioinformatics and Scientific writing. It works with Microsoft Word. 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

  • A user needs 3-5 concise
  • Evidence-grounded highlight bullets for a research paper
  • Bioinformatics manuscript

Example prompts

  • “Use the academic-highlight-generator skill to generate submission-ready Elsevier/SCI Highlights from manuscript text or extracted PDF/DOCX/TXT content”
  • “/academic-highlight-generator”

Requirements

  • Python 3

Workflow steps

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

  1. Validate source sufficiency
  2. Extract text if needed
  3. Detect article type
  4. Generate draft highlights
  5. Self-critique and refine

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

Academic Highlight Generator loads about 1.5k tokens when it runs, and up to ~2.5k if it reads all its reference files. Until then it costs about 74 tokens; SKILL.md has 687 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~74
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.5k

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). 687 words, ~1,505 tokens.

Download SKILL.mdSave it as .claude/skills/academic-highlight-generator/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
academic-highlight-generator
description
Generates submission-ready Elsevier/SCI Highlights from manuscript text or extracted PDF/DOCX/TXT content. Use when a user needs 3-5 concise, evidence-grounded highlight bullets for a research paper, review, meta-analysis, case report, or bioinformatics manuscript.
license
MIT
author
AIPOCH

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

Academic Highlight Generator

Generate journal-ready Highlights that can be pasted directly into a submission system. This skill is for academic writing output, not for inventing missing results.

When to Use

  • The user wants a Highlights section for a manuscript submission.
  • The source is an English manuscript, abstract, results summary, or extracted full text.
  • The paper falls into one of these types: Original Research, Meta-analysis, Review, Case Report, Bioinformatics, Bibliometrics, or Technical Note.
  • The user needs a deterministic, concise output with strict bullet-count and length limits.

When Not to Use

  • The user asks you to fabricate results, novelty claims, study counts, effect sizes, or conclusions that are not in the source.
  • The source text is too short to identify study type or key findings reliably.
  • The document is a perspective, commentary, editorial, or otherwise unsuitable for formal submission highlights.
  • The user provides a binary .doc file. This package supports .txt, .pdf, and .docx; convert .doc before continuing.

Required Inputs

Provide one of the following:

  • Plain manuscript text, abstract, or structured study summary.
  • A supported source file path for scripts/extract_text.py: .txt, .pdf, or .docx.

Recommended metadata if available:

  • Manuscript type or target journal.
  • Core method, main findings, and significance sentence.
  • Any wording constraints such as British/American spelling.

Output Contract

Always return:

text
Highlights
- <bullet 1>
- <bullet 2>
- <bullet 3>
[- <bullet 4>]
[- <bullet 5>]

Hard requirements:

  • Exactly 3-5 bullets.
  • English bullets only unless the user explicitly requests Chinese.
  • Maximum 85 characters per English bullet.
  • Objective third-person tone.
  • No first person (we, our).
  • No undefined abbreviations, citation markers, or figure/table references.
  • Every bullet must be grounded in source material.

Supported Execution Paths

Path A: Source text already provided

Use the provided text directly. This is the preferred path for speed and determinism.

Path B: Source file needs extraction

Use:

bash
python scripts/extract_text.py <file_path>

Supported formats:

  • .txt
  • .pdf
  • .docx

Unsupported format:

  • .doc -> ask the user to convert to .docx or .pdf first.

Workflow

1. Validate source sufficiency

Before writing anything, confirm the source contains enough signal to identify:

  • study type
  • method or evidence base
  • main finding or conclusion

If not, stop and use the refusal template in ## Fallback and Refusal Contract.

2. Extract text if needed

If the user provided a file instead of text, run:

bash
python scripts/extract_text.py <file_path>

If extraction fails:

  • report the exact failure,
  • preserve the original file path in the message,
  • do not invent content from the missing file.
3. Detect article type

Use references/prompts.md to classify the manuscript into one of:

  • Original Research
  • Meta-analysis
  • Review
  • Case Report / Case Series
  • Bioinformatics Study
  • Perspective / Commentary
  • Education / Policy Research
  • Bibliometric Analysis
  • Short Communication / Technical Note
  • Other / Unclear
Show full SKILL.md (271 more words)Show less
4. Generate draft highlights

Select the matching generation prompt from references/prompts.md.

Coverage priorities by type:

  • Original Research: method, main result, mechanism/utility, significance
  • Meta-analysis / Review: evidence base, synthesis method, conclusion, gap/future direction
  • Case Report: case feature, diagnostic or treatment learning point, follow-up significance
  • Bioinformatics: data source, analytic method, marker/pathway/model, biological relevance
  • Bibliometrics: database, time span, tools, hotspots/trends, collaboration pattern
  • Technical Note: method/device/process optimization, efficiency or usability gain
5. Self-critique and refine

Use the critique and refinement prompts in references/prompts.md.

The final output must satisfy all of these checks:

  • 3-5 bullets
  • no bullet exceeds the limit
  • the bullets are not copied verbatim from the abstract
  • the set covers method + finding + value at least once
  • no fabricated numbers or study claims

Fallback and Refusal Contract

If the source is unsuitable or insufficient, respond with this structure:

text
Cannot generate submission-ready Highlights yet.
Reason: <insufficient source / unsupported article type / unsupported file format>
Detected type: <type or Unknown>
Minimum additional input needed:
- <item 1>
- <item 2>

Use this refusal contract when:

  • the article type is Other / Unclear,
  • the text is too short to ground claims,
  • the user asks for invention rather than extraction,
  • the file format is unsupported.

Deterministic Rules

  • Keep the same output header every time: Highlights.
  • Do not switch between sentence fragments and full sentences in one output.
  • Prefer one factual claim per bullet.
  • If a key value is unavailable, omit that value instead of guessing it.
  • If the source supports only three safe bullets, output three rather than padding to five.

Quality Checklist

Before returning the final answer, verify:

  • Study type and bullet focus are aligned.
  • No unsupported causal overstatement appears.
  • No clinical recommendation is implied unless the source itself states one cautiously.
  • Each bullet is independently readable.
  • The final output can be pasted into a journal submission form without reformatting.

© 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/Academic Writing/academic-highlight-generator of aipoch/medical-research-skills.

  • SKILL.md
  • academic-highlight-generator_audit_result_v1.json
  • references/prompts.md
  • scripts/extract_text.py

Open the folder on GitHubat commit 686e09d

Compare with similar skills

Academic Highlight Generator 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.

Academic Highlight Generator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Academic Highlight Generator this skillaipoch/medical-research-skills2k—~1.5kAutomated safety check: PassMIT
Academic Paperbrycewang-stanford/Auto-Empirical-Research-Skills4.5k—~7.3kAutomated safety check: PassCustom licence
Biomedical PaperLeoYeAI/openclaw-master-skills2.2k—~3.3kAutomated safety check: PassMIT
Academic Integrity Rewritelin1111-1/academic-integrity-rewrite102—~1.1kAutomated safety check: PassMIT
PRISMA Systematic Review Writerkeemanxp/slr-prisma1011 repos~7.1kAutomated safety check: PassMIT
Formal Modeling Paper Writeryushui2022/MathModel-Skill453—~1.6kAutomated safety check: PassMIT

Similar skills

  • Academic Paper

    brycewang-stanford/Auto-Empirical-Research-Skills

    Academic paper writing skill with 12-agent pipeline. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills.

    4.5k GitHub stars~7.3k tokensUpdated 4 days ago
    Documents & OfficeAuto-check passed
  • Biomedical Paper

    LeoYeAI/openclaw-master-skills

    AI-powered biomedical manuscript generation with docx output.

    2.2k GitHub stars~3.3k tokensUpdated 2 mo ago
    Documents & OfficeAuto-check passed
  • Academic Integrity Rewrite

    lin1111-1/academic-integrity-rewrite

    Revise Chinese or English academic writing for lower unnecessary textual overlap while preserving meaning, evidence, numbers, equations, terminology, and citations.

    102 GitHub stars~1.1k tokensUpdated 28 days ago
    Research & ScienceAuto-check passed
  • Guides you through writing a systematic literature review to the PRISMA 2020 checklist, producing a journal-format Word manuscript, a flow diagram and APA 7th references.

    101 GitHub starsUsed in 1 repo~7.1k tokens
    Research & ScienceAuto-check passed
  • Formal Modeling Paper Writer

    yushui2022/MathModel-Skill

    Plans, drafts, audits, formats and verifies a formal mathematical-modeling paper from an evidence chain, delivering audited Markdown and a Word file with native equations.

    453 GitHub stars~1.6k tokensUpdated 2 days ago
    Research & ScienceAuto-check passed
  • Document Converter

    wentorai/Research-Claw

    Convert Office documents (PPTX, DOCX, XLSX, PDF, HTML, CSV, JSON, XML, images) to Markdown using Microsoft MarkItDown.

    858 GitHub stars~1.3k tokensUpdated 1 mo ago
    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…

    2k GitHub stars~2.2k tokensUpdated 22 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.

    2k GitHub stars~1.4k tokensUpdated 22 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.

    2k GitHub stars~3.7k tokensUpdated 22 days ago
    Auto-check passed
  • Iso Certification

    aipoch/medical-research-skills

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

    2k GitHub stars~1.8k tokensUpdated 22 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…

    2k GitHub stars~1.7k tokensUpdated 22 days ago
    Auto-check passed
  • Latex Posters

    aipoch/medical-research-skills

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

    2k GitHub stars~1.3k tokensUpdated 22 days ago
    Auto-check passed

Works with

Questions about Academic Highlight Generator

What does Academic Highlight Generator do?

Generates submission-ready Elsevier/SCI Highlights from manuscript text or extracted PDF/DOCX/TXT content. Academic Highlight Generator is an agent skill from aipoch/medical-research-skills. Generates submission-ready Elsevier/SCI Highlights from manuscript text or extracted PDF/DOCX/TXT content.

When should I use Academic Highlight Generator?

Academic Highlight Generator fits situations like: A user needs 3-5 concise; evidence-grounded highlight bullets for a research paper; bioinformatics manuscript.

How do I install Academic Highlight Generator in Claude Code?

Run `npx skills add aipoch/medical-research-skills --skill academic-highlight-generator -a claude-code`. Or copy the skill folder (scientific-skills/Academic Writing/academic-highlight-generator in aipoch/medical-research-skills) into .claude/skills/academic-highlight-generator in your project. Claude Code loads it when a task matches its description.

How do I install Academic Highlight Generator in Codex?

Run `npx skills add aipoch/medical-research-skills --skill academic-highlight-generator -a codex`. Or copy the skill folder (scientific-skills/Academic Writing/academic-highlight-generator in aipoch/medical-research-skills) into .agents/skills/academic-highlight-generator in your project. Codex loads it when a task matches its description.

Can I use Academic Highlight Generator 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 academic-highlight-generator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/academic-highlight-generator, .gemini/skills/academic-highlight-generator, .github/skills/academic-highlight-generator and .opencode/skills/academic-highlight-generator in your project.

What does Academic Highlight Generator need to run?

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

Does Academic Highlight Generator 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 Academic Highlight Generator 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 Academic Highlight Generator use?

Academic Highlight Generator 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 Academic Highlight Generator use?

About 1.5k tokens (SKILL.md is roughly 6k 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 969 tokens, read only when the agent opens those files.

What are the alternatives to Academic Highlight Generator?

Skills that share tags, products or a category with Academic Highlight Generator: Academic Paper (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars), Biomedical Paper (LeoYeAI/openclaw-master-skills, 2.2k stars), Academic Integrity Rewrite (lin1111-1/academic-integrity-rewrite, 102 stars) and PRISMA Systematic Review Writer (keemanxp/slr-prisma, 101 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Academic Highlight Generator?

aipoch (a GitHub organization) maintains it in aipoch/medical-research-skills, which has 1,978 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.