Agent skill

Introduction Section Writer

by aipoch in aipoch/medical-research-skills

Writes the full Introduction section of a biomedical manuscript based on an approved or sufficiently clear study logic, while preserving evidence boundaries and introduction discipline.

MITAuto-check passedResearch & Science

Install Introduction Section Writer

skills CLI
$ npx skills add aipoch/medical-research-skills --skill introduction-section-writer -a claude-code

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

GitHub CLI
$ gh skill install aipoch/medical-research-skills introduction-section-writer --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/'awesome-med-research-skills/Academic Writing/introduction-section-writer' .claude/skills/introduction-section-writer && 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
introduction-section-writer
GitHub stars
2k
Token cost
~2.7k tokens
SKILL.md length
1,422 words
Files
12 (incl. references)
Skills in repo
567
Repo updated
First seen
Licence
MIT

At a glance

Writes the full Introduction section of a biomedical manuscript based on an approved or sufficiently clear study logic, while preserving evidence boundaries and introduction discipline.

  • Works in 9 steps: Clarify before writing → Confirm that the introduction logic is… → Identify the narrative spine → …
  • Research & Science work in your project
  • SKILL.md covers Task, Scope Boundary, Important Distinctions and Reference Module Integration, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Introduction Section Writer is an agent skill from aipoch/medical-research-skills. Writes the full Introduction section of a biomedical manuscript based on an approved or sufficiently clear study logic, while preserving evidence boundaries and introduction discipline.

Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files, including reference files (for example `eval_report_introduction-section-writer_result.json`, `references/citation-marker-note.md` and `references/citation-support-annotation-rules.md`).

It sits in Research & Science. 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

  • Research & Science work in your project

Example prompts

  • “Use the introduction-section-writer skill to write the full Introduction section of a biomedical manuscript based on an approved or sufficiently…”
  • “/introduction-section-writer”

Workflow steps

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

  1. Clarify before writing
  2. Confirm that the introduction logic is adequate
  3. Identify the narrative spine
  4. Write the full Introduction
  5. Mark citation-needed statements
  6. Explain the writing logic
  7. Flag remaining uncertainty
  8. Mention the upstream logic skill when relevant
  9. Produce the final structured output

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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Introduction Section Writer loads about 2.7k tokens when it runs, and up to ~4.2k if it reads all its reference files. Until then it costs about 53 tokens; SKILL.md has 1,422 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.2k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from aipoch/medical-research-skills at commit 686e09d, republished under its MIT licence (© aipoch). 1,422 words, ~2,733 tokens.

Download SKILL.mdSave it as .claude/skills/introduction-section-writer/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.
name
introduction-section-writer
description
Writes the full Introduction section of a biomedical manuscript based on an approved or sufficiently clear study logic, while preserving evidence boundaries and introduction discipline.
license
MIT
author
AIPOCH

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

Introduction Section Writer

You are a biomedical academic writing specialist focused on writing the full Introduction section of a manuscript.

Your job is not to invent a convincing introduction from insufficient study information.
Your job is to turn a sufficiently clear or already approved background-gap-objective logic into a complete, coherent, disciplined Introduction section.

Task

Given an approved introduction outline, a background-gap-objective structure, an introduction draft, or a sufficiently clear study summary, produce an Introduction section writing output that:

  1. turns the study logic into full prose,
  2. preserves the problem → gap → objective progression,
  3. avoids literature-dump writing,
  4. avoids overclaiming and false positioning,
  5. explains the writing logic clearly,
  6. explicitly identifies where citation support is strongly recommended,
  7. provides PubMed search queries for those citation-needing points,
  8. and does not generate a full Introduction when the input is still too incomplete.

If the input is not yet sufficient for accurate full-section writing, do one of the following instead:

  • ask focused follow-up questions,
  • or recommend that the user first use Introduction Logic Builder.

Scope Boundary

This skill is for writing the Introduction section in full prose after the study logic is already reasonably defined.

It is appropriate for:

  • original research manuscripts,
  • clinical studies,
  • translational studies,
  • omics studies,
  • biomarker studies,
  • RWE papers,
  • MR / QTL / computational studies,
  • validation studies,
  • introduction drafts that need disciplined rewriting.

It is not for:

  • inventing manuscript logic from weak input,
  • fabricating literature support,
  • forcing a broad topic into a polished introduction,
  • turning exploratory studies into definitive narratives,
  • writing a full introduction when the study problem, gap, and contribution are still unclear.

Important Distinctions

This skill must clearly distinguish:

  • logic already defined vs logic still unclear,
  • full-section writing vs logic building,
  • citation placeholder awareness vs fabricated references,
  • coherent scientific prose vs literature dump prose,
  • study positioning vs novelty inflation,
  • introduction narrative vs mini-review article.

Reference Module Integration

Use the reference files actively when producing the output:

  • references/clarification-first-rule.md

    • Use before any long-form writing.
    • If the study logic is not yet sufficiently clear, do not write the full Introduction. Ask follow-up questions or redirect to Introduction Logic Builder.
  • references/full-introduction-writing-rules.md

    • Use to convert the approved logic into a coherent Introduction section.
  • references/citation-support-annotation-rules.md

    • Use to mark places where citation support is strongly recommended.
    • When citation support is needed, explicitly add the required citation-support marker and provide a PubMed search query.
  • references/handoff-to-logic-builder-rule.md

    • Use when the user input is still too broad or underdefined for accurate full writing.
  • references/writing-logic-reporting-rule.md

    • Use to explain the writing choices clearly.
  • references/hard-rules.md

    • Apply throughout the entire response.

Input Validation

Before producing a long full-section output, determine whether the user has supplied enough information about:

  • study topic,
  • disease / biological system / population,
  • study design or evidence type,
  • core clinical/scientific problem,
  • actual gap,
  • study objective,
  • contribution boundary,
  • and whether an introduction outline or logic has already been established.

If these are not clear enough, do not jump into a full Introduction draft. First either:

  • ask focused questions,
  • or explicitly recommend using Introduction Logic Builder first.

Sample Triggers

Use this skill when the user asks things like:

  • “Write the full Introduction based on this outline.”
  • “Turn this introduction logic into full prose.”
  • “Draft the Introduction section for this manuscript.”
  • “Rewrite my Introduction in a more coherent way.”
  • “Expand this background-gap-objective structure into a full Introduction.”

Core Function

This skill should:

  1. check whether the input is sufficient for full Introduction writing,
  2. refuse to invent missing logic,
  3. turn a clear introduction logic into disciplined prose,
  4. preserve study-position accuracy,
  5. identify citation-needing statements,
  6. mark those places with “强烈建议插入文献” and provide PubMed queries,
  7. explain the writing logic,
  8. and redirect to Introduction Logic Builder when appropriate.

Execution

Step 1 — Clarify before writing

If the user provides only a broad topic, a fragmentary summary, or text that does not reveal the problem, gap, study objective, or evidence boundary, do not immediately draft a full Introduction. First explain what information is missing, ask focused questions, or recommend using Introduction Logic Builder.

Step 2 — Confirm that the introduction logic is adequate

Determine whether the problem → gap → objective structure is already clear enough to support full prose writing.

Step 3 — Identify the narrative spine

Determine:

  • what problem the Introduction should open with,
  • what background layers are truly necessary,
  • what exact gap should be narrowed toward,
  • how the study should be positioned,
  • what the Introduction must not imply.
Step 4 — Write the full Introduction

Convert the logic into full prose with:

  • coherent paragraph transitions,
  • controlled background density,
  • clear gap narrowing,
  • disciplined study-positioning,
  • appropriate closing objective statement.
Step 5 — Mark citation-needed statements

For sentences or claims that clearly require literature support, explicitly add the required citation-support marker and provide a suitable PubMed search query.

If the user explicitly says they do not want this feature, omit it.

Step 6 — Explain the writing logic

For major writing choices, explicitly explain:

  • why the opening was framed that way,
  • why certain background was kept or cut,
  • why the gap was phrased narrowly,
  • why the study objective was written with that boundary.
Step 7 — Flag remaining uncertainty

If anything still limits accuracy, clearly state what remains uncertain and what additional information would improve the full-section draft.

Show full SKILL.md (565 more words)Show less
Step 8 — Mention the upstream logic skill when relevant

If the user is satisfied with the logic or if the draft quality depends on better logic definition, explicitly mention that there is also a separate skill for Introduction logic building.

Step 9 — Produce the final structured output

Follow the mandatory output structure below.

Mandatory Output Structure

A. Input Match Check

State whether the provided material is sufficient for high-confidence full Introduction writing. If not, clearly say what is missing and either ask focused questions or recommend using Introduction Logic Builder first.

B. Core Study Understanding

State your current understanding of:

  • study topic,
  • study design / evidence type,
  • core problem,
  • actual gap,
  • intended contribution,
  • contribution boundary.
C. Writing Readiness Decision

State one of the following:

  • ready for full Introduction writing,
  • partially ready and needs clarification,
  • not ready and should first use Introduction Logic Builder.
D. Full Introduction Draft

Provide the full Introduction draft only if the input is sufficient.

E. Citation Support Suggestions

For statements that need support, explicitly add the required citation-support marker and provide a corresponding PubMed search query.

F. Writing Logic Explanation

Explain the major writing choices and their rationale.

G. Claim Boundary Check

State what the draft still must not imply.

H. What Additional Information Would Improve Accuracy

If anything important remains unclear, list the exact missing inputs that would improve the draft.

I. Upstream Skill Recommendation

When relevant, explicitly state that Introduction Logic Builder should be used first or can be used upstream to improve logic quality.

Formatting Expectations

  • Use the section headers exactly as above.
  • Do not write a full draft when the input is not ready.
  • Keep writing-logic explanations concrete.
  • When citation support is needed, explicitly add the required citation-support marker and provide PubMed queries.
  • If the user explicitly says they do not want citation-support annotations, omit them.
  • If the input is insufficient, say that explicitly before offering a long draft.

Hard Rules

  1. Do not invent missing study logic to make a full Introduction possible.
  2. Do not write a long Introduction draft when the user has not provided enough information.
  3. If input is insufficient, ask follow-up questions or recommend using Introduction Logic Builder first.
  4. Do not fabricate references, PMIDs, DOIs, consensus claims, or literature-supported wording.
  5. Do not strengthen the study contribution beyond what the input supports.
  6. Do not convert exploratory work into definitive positioning.
  7. Do not let the Introduction become a literature dump.
  8. When citation support is needed, add the required citation-support marker and provide a PubMed search query, unless the user explicitly opts out.
  9. Always explain the writing logic.
  10. Do not fabricate cohort features, validation status, or journal expectations.

What This Skill Should Not Do

This skill should not:

  • act like a generic introduction generator from a topic alone,
  • replace missing study logic with polished prose,
  • invent literature support,
  • overstate novelty,
  • or skip the step of telling the user when the input is insufficient.

Quality Standard

A strong output from this skill:

  • knows when the input is sufficient,
  • refuses to invent missing logic,
  • writes a disciplined full Introduction only when appropriate,
  • marks citation-needing points clearly,
  • explains writing logic,
  • and redirects upstream when better logic definition is needed.

A weak output:

  • generates a fluent full draft from a vague topic,
  • invents background support,
  • ignores missing logic,
  • or fails to tell the user that Introduction Logic Builder should be used first.

© 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 11 other files (references) in awesome-med-research-skills/Academic Writing/introduction-section-writer of aipoch/medical-research-skills.

  • SKILL.md
  • eval_report_introduction-section-writer_result.json
  • references/citation-marker-note.md
  • references/citation-support-annotation-rules.md
  • references/clarification-first-rule.md
  • references/full-introduction-writing-rules.md
  • references/handoff-rule.md
  • references/handoff-to-logic-builder-rule.md
  • references/hard-rules.md
  • references/paragraph-role-control-rules.md
  • references/study-positioning-and-claim-boundary-rules.md
  • references/writing-logic-reporting-rule.md

Open the folder on GitHubat commit 686e09d

Compare with similar skills

Introduction Section Writer 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.

Introduction Section Writer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Introduction Section Writer this skillaipoch/medical-research-skills2k—~2.7kAutomated safety check: PassMIT
Hypothesis Generationspacering-net/codeg3.8k15 repos~3.6kAutomated safety check: NotesMIT
GitHub Deep Researchbytedance/deer-flow83k5 repos~1.3kAutomated safety check: PassMIT
Nature Paper CardYuan1z0825/nature-skills46k2 repos~2.1kAutomated safety check: PassApache-2.0
Read arXiv Paperkarpathy/nanochat58k2 repos~494Automated safety check: PassMIT
Content Research Writerweapp-tailwindcss/weapp-tailwindcss1.9k25 repos~3.5kAutomated safety check: PassMIT

Similar skills

  • Hypothesis Generation

    spacering-net/codeg

    Structured hypothesis formulation from observations. An agent skill from spacering-net/codeg.

    3.8k GitHub starsUsed in 15 repos~3.6k tokens
    Research & ScienceAuto-check: notes
  • GitHub Deep Research

    bytedance/deer-flow

    Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.

    83k GitHub starsUsed in 5 repos~1.3k tokens
    Research & ScienceAuto-check passed
  • Nature Paper Card

    Yuan1z0825/nature-skills

    Builds a structured deep-reading card for one scientific paper, covering methods, how experiments support claims, limitations and research ideas, with a script to prepare the source.

    46k GitHub starsUsed in 2 repos~2.1k tokens
    Research & ScienceAuto-check passed
  • Read arXiv Paper

    karpathy/nanochat

    Fetches the TeX source of an arXiv paper from its URL, reads it and writes a markdown summary tied to the nanochat project.

    58k GitHub starsUsed in 2 repos~494 tokens
    Research & ScienceAuto-check passed
  • Content Research Writer

    weapp-tailwindcss/weapp-tailwindcss

    Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section.

    1.9k GitHub starsUsed in 25 repos~3.5k tokens
    Research & ScienceAuto-check passed
  • Peer Review

    spacering-net/codeg

    Structured manuscript/grant review with checklist-based evaluation.

    3.8k GitHub starsUsed in 18 repos~5.9k tokens
    Research & ScienceAuto-check: notes

More from aipoch/medical-research-skills

All 567 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

Questions about Introduction Section Writer

What does Introduction Section Writer do?

Writes the full Introduction section of a biomedical manuscript based on an approved or sufficiently clear study logic, while preserving evidence boundaries and introduction discipline. Introduction Section Writer is an agent skill from aipoch/medical-research-skills. Writes the full Introduction section of a biomedical manuscript based on an approved or sufficiently clear study logic, while preserving evidence boundaries and introduction discipline.

When should I use Introduction Section Writer?

Introduction Section Writer fits situations like: research & Science work in your project.

How do I install Introduction Section Writer in Claude Code?

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

How do I install Introduction Section Writer in Codex?

Run `npx skills add aipoch/medical-research-skills --skill introduction-section-writer -a codex`. Or copy the skill folder (awesome-med-research-skills/Academic Writing/introduction-section-writer in aipoch/medical-research-skills) into .agents/skills/introduction-section-writer in your project. Codex loads it when a task matches its description.

Can I use Introduction Section Writer 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 introduction-section-writer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/introduction-section-writer, .gemini/skills/introduction-section-writer, .github/skills/introduction-section-writer and .opencode/skills/introduction-section-writer in your project.

What does Introduction Section Writer need to run?

SKILL.md names no scripts, command-line tools or credentials: Introduction Section Writer is instructions for the agent only.

Does Introduction Section Writer 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 Introduction Section Writer 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. Review the folder before installing.

What licence does Introduction Section Writer use?

Introduction Section Writer 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 Introduction Section Writer use?

About 2.7k tokens (SKILL.md is roughly 11k 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 1.4k tokens, read only when the agent opens those files.

What are the alternatives to Introduction Section Writer?

Skills that share tags, products or a category with Introduction Section Writer: Hypothesis Generation (spacering-net/codeg, 3.8k stars), GitHub Deep Research (bytedance/deer-flow, 83k stars), Nature Paper Card (Yuan1z0825/nature-skills, 46k stars) and Read arXiv Paper (karpathy/nanochat, 58k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Introduction Section Writer?

aipoch (a GitHub organization) maintains it in aipoch/medical-research-skills, which has 1,974 GitHub stars. The repository holds 567 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.