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

Reference Search

by aipoch in aipoch/medical-research-skills

Multi-database literature search and search-strategy design that outputs structured, reproducible result lists; use when you need reference retrieval, systematic searching, review topic selection…

MITAuto-check passedResearch & Science

Install Reference Search

skills CLI
$ npx skills add aipoch/medical-research-skills --skill reference-search -a claude-code

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

GitHub CLI
$ gh skill install aipoch/medical-research-skills reference-search --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/Evidence Insight/reference-search' .claude/skills/reference-search && 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
reference-search
GitHub stars
2k
Token cost
~2k tokens
SKILL.md length
739 words
Files
10 (incl. scripts, references, assets)
Skills in repo
567
Repo updated
First seen
Licence
MIT

At a glance

Multi-database literature search and search-strategy design that outputs structured, reproducible result lists; use when you need reference retrieval, systematic searching, review topic selection…

  • Works in 5 steps: When to Use → Key Features → Dependencies → …
  • You need reference retrieval
  • SKILL.md covers When to Use, Key Features, Dependencies and Example Usage, plus 6 more sections
  • Runs Python scripts from its folder; calls python; reaches eutils.ncbi.nlm.nih.gov; needs API_KEY

What it does

Reference Search is an agent skill from aipoch/medical-research-skills. Multi-database literature search and search-strategy design that outputs structured, reproducible result lists; use when you need reference retrieval, systematic searching, review topic selection, or to construct a traceable search strategy.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including scripts, reference files and assets (for example `inputs/query.json`, `reference-search_audit_result_v1.json` and `references/evaluation-checklist.md`).

It sits in Research & Science, covering Literature review. It works with PubMed. 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

  • You need reference retrieval
  • Systematic searching
  • Review topic selection
  • Construct a traceable search strategy

Example prompts

  • “/reference-search”

Requirements

  • Python 3
  • A credential in API_KEY

Workflow steps

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

  1. When to Use
  2. Key Features
  3. Dependencies
  4. Example Usage
  5. Implementation Details

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

    Hosts in commands or code, which the agent is likely to contact:

    • eutils.ncbi.nlm.nih.gov

    Also links to:

    • ncbi.nlm.nih.gov

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

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • API_KEY

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

Context cost

Reference Search loads about 2k tokens when it runs, and up to ~2.8k if it reads all its reference files. Until then it costs about 65 tokens; SKILL.md has 739 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.8k

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). 739 words, ~1,970 tokens.

Download SKILL.mdSave it as .claude/skills/reference-search/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.
name
reference-search
description
Multi-database literature search and search-strategy design that outputs structured, reproducible result lists; use when you need reference retrieval, systematic searching, review topic selection, or to construct a traceable search strategy.
license
MIT
author
AIPOCH

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

When to Use

  • Use this skill when you need multi-database literature search and search-strategy design that outputs structured, reproducible result lists; use when you need reference retrieval, systematic searching, review topic selection, or to construct a traceable search strategy in a reproducible workflow.
  • Use this skill when a evidence insight task needs a packaged method instead of ad-hoc freeform output.
  • Use this skill when the user expects a concrete deliverable, validation step, or file-based result.
  • Use this skill when scripts/pubmed_search.py is the most direct path to complete the request.
  • Use this skill when you need the reference-search package behavior rather than a generic answer.

Key Features

  • Scope-focused workflow aligned to: Multi-database literature search and search-strategy design that outputs structured, reproducible result lists; use when you need reference retrieval, systematic searching, review topic selection, or to construct a traceable search strategy.
  • Packaged executable path(s): scripts/pubmed_search.py.
  • Reference material available in references/ for task-specific guidance.
  • Reusable packaged asset(s), including assets/search_log_template.csv.
  • Structured execution path designed to keep outputs consistent and reviewable.

Dependencies

  • Python: 3.10+. Repository baseline for current packaged skills.
  • Third-party packages: not explicitly version-pinned in this skill package. Add pinned versions if this skill needs stricter environment control.

Example Usage

bash
cd "20260316/scientific-skills/Evidence Insight/reference-search"
python -m py_compile scripts/pubmed_search.py
python scripts/pubmed_search.py --help

Example run plan:

  1. Confirm the user input, output path, and any required config values.
  2. Edit the in-file CONFIG block or documented parameters if the script uses fixed settings.
  3. Run python scripts/pubmed_search.py with the validated inputs.
  4. Review the generated output and return the final artifact with any assumptions called out.

Implementation Details

  • Execution model: validate the request, choose the packaged workflow, and produce a bounded deliverable.
  • Input controls: confirm the source files, scope limits, output format, and acceptance criteria before running any script.
  • Primary implementation surface: scripts/pubmed_search.py.
  • Reference guidance: references/ contains supporting rules, prompts, or checklists.
  • Packaged assets: reusable files are available under assets/.
  • Parameters to clarify first: input path, output path, scope filters, thresholds, and any domain-specific constraints.
  • Output discipline: keep results reproducible, identify assumptions explicitly, and avoid undocumented side effects.

1. When to Use

Use this skill in the following scenarios:

  1. Systematic or scoping reviews where you must document a reproducible search strategy and export structured results.
  2. Rapid evidence retrieval for a research question, with quick export to CSV/JSON for screening.
  3. Search strategy construction (keywords, synonyms, Boolean logic, field restrictions) before running searches at scale.
  4. Review topic selection by exploring the volume and distribution of literature for candidate topics.
  5. Traceable search logging when you need to record search date, query string, and result counts for auditability.
Show full SKILL.md (312 more words)Show less

2. Key Features

  • Multi-database search framework (currently implemented for PubMed).
  • Automatic keyword extraction and search strategy construction (Boolean logic + field constraints).
  • Structured outputs:
    • Machine-readable JSON
    • Spreadsheet-friendly CSV
  • Reproducible search records (query string, keywords, counts, and record list).
  • Compliance-oriented network access restricted to official PubMed E-utilities endpoints.

3. Dependencies

DependencyVersionNotes
Python3.10+Uses Python standard library only (no third-party packages).

4. Example Usage

Run the PubMed search script
bash
cd skills/reference-search
python scripts/pubmed_search.py
Configure the script

Edit the CONFIG section in scripts/pubmed_search.py:

python
from pathlib import Path

CONFIG = {
    "EMAIL": "your_email@example.com",          # Required (must be provided by the user)
    "API_KEY": "",                               # Optional (can increase rate limits)
    "RETMAX": 20,                                # Max number of records to return
    "OUTPUT_DIR": Path("outputs/pubmed_search"), # Allowed output directory
}
Example output (JSON)
json
{
  "query": "\"Cancer cachexia\"[Title] AND cachexia[Title/Abstract] AND pancreatic[Title/Abstract]",
  "keywords": ["cachexia", "pancreatic", "cancer", "weight", "muscle", "atrophy", "mortality", "treatment"],
  "count": 20,
  "records": [
    {
      "pmid": "36280389",
      "title": "Role of noncoding RNAs in pancreatic ductal adenocarcinoma associated cachexia.",
      "journal": "Journal of Cachexia, Sarcopenia and Muscle",
      "pubdate": "2022",
      "authors": "Wang X, Li Y, Zhang S"
    }
  ]
}

5. Implementation Details

Supported databases and endpoints
  • PubMed (NCBI E-utilities) only.
    • https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi (search)
    • https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi (record summaries)
  1. Define requirements and scope
    • Confirm research question and core concepts.
    • Set inclusion/exclusion criteria (time window, language, publication type).
  2. Design the search strategy
    • Expand keywords with synonyms.
    • Combine with Boolean operators (AND/OR) and apply field restrictions (e.g., Title/Abstract/MeSH).
  3. Execute and export
    • Run the script and export results to JSON/CSV.
    • If combining multiple sources, merge and deduplicate externally while preserving source labels.
  4. Record for reproducibility
    • Save the final query string, search date, and result counts.
Configuration parameters
  • EMAIL (required): Must be provided by the user; must not be hard-coded as a real credential.
  • API_KEY (optional): If provided, can improve throughput under NCBI policies.
  • RETMAX: Limits the number of returned records.
  • OUTPUT_DIR: Must point to an outputs/ subdirectory.
Security, compliance, and access constraints
  • Network access: restricted to the official NCBI host eutils.ncbi.nlm.nih.gov only.
  • Prohibited: any third-party URLs.
  • File read constraints: do not read files outside the skill directory.
  • File write constraints: write outputs only under outputs/ (ensure the directory exists or is created by the script).
  • Timeout: 20 seconds per API request.
  • Rate limiting: 0.35 seconds between requests.
  • Error handling: return semantic, user-facing error messages without exposing sensitive technical details.
Included assets and references (in-repo)
  • Templates:
    • assets/search_log_template.csv
    • assets/search_results_template.csv
  • Additional guidance and checklists:
    • references/guide.md
    • references/evaluation-checklist.md
  • Tests:
    • tests/test_pubmed_search.py
  • External documentation:

© 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 9 other files (scripts, references, assets) in scientific-skills/Evidence Insight/reference-search of aipoch/medical-research-skills.

  • SKILL.md
  • assets/search_log_template.csv
  • assets/search_results_template.csv
  • inputs/query.json
  • reference-search_audit_result_v1.json
  • references/evaluation-checklist.md
  • references/guide.md
  • run_query.py
  • run_search.py
  • scripts/pubmed_search.py

Open the folder on GitHubat commit 686e09d

Compare with similar skills

Reference Search 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.

Reference Search compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Reference Search this skillaipoch/medical-research-skills2k—~2kAutomated safety check: PassMIT
Systematic Review ScreenerImbad0202/academic-research-skills51k—~8.4kAutomated safety check: PassCustom licence
Literature Reviewneflibata-feng/MyArxiv-Agent12621 repos~5.9kAutomated safety check: NotesMIT
PaperSeek Literature SearchMingfengHong/paperseek200—~1.6kAutomated safety check: PassApache-2.0
Academic Search and Citation RouterYuan1z0825/nature-skills46k—~884Automated safety check: PassApache-2.0
Literature ReviewK-Dense-AI/scientific-agent-skills48k1 repos~3.2kAutomated safety check: NotesMIT

Similar skills

  • Systematic Review Screener

    Imbad0202/academic-research-skills

    Screens records for systematic, scoping and rapid reviews against fixed eligibility rules, using two blinded AI reviewers and a third adjudicator, with traceable PRISMA counts.

    51k GitHub stars~8.4k tokensUpdated 4 days ago
    Research & ScienceAuto-check passed

  • Literature Review

    neflibata-feng/MyArxiv-Agent

    Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.).

    126 GitHub starsUsed in 21 repos~5.9k tokens
    Research & ScienceAuto-check: notes

  • PaperSeek Literature Search

    MingfengHong/paperseek

    Routes literature searches through the PaperSeek launcher, picks suitable scholarly sources, parses JSON output and keeps API keys out of the chat.

    200 GitHub stars~1.6k tokensUpdated 2 days ago
    Research & ScienceAuto-check passed

  • Academic Search and Citation Router

    Yuan1z0825/nature-skills

    Finds papers across literature sources, verifies and converts citations, builds MeSH strategies and audits independent citations of a paper.

    46k GitHub stars~884 tokensUpdated yesterday
    Research & ScienceAuto-check passed

  • Literature Review

    K-Dense-AI/scientific-agent-skills

    Runs systematic, scoping or narrative literature reviews across PubMed, arXiv, bioRxiv and Semantic Scholar, with citation checks and Markdown or PDF output.

    48k GitHub starsUsed in 1 repo~3.2k tokens
    Research & ScienceAuto-check: notes

  • PubMed REST API Search

    davila7/claude-code-templates

    Searches PubMed directly through its E-utilities REST API, with guidance on Boolean and MeSH query syntax, batch retrieval and citation data.

    32k GitHub starsUsed in 15 repos~3.9k tokens
    Research & ScienceAuto-check passed

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 20 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 20 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 20 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 20 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 20 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 20 days ago
    Auto-check passed

Works with

Categories

Questions about Reference Search

What does Reference Search do?

Multi-database literature search and search-strategy design that outputs structured, reproducible result lists; use when you need reference retrieval, systematic searching, review topic selection…. Reference Search is an agent skill from aipoch/medical-research-skills. Multi-database literature search and search-strategy design that outputs structured, reproducible result lists; use when you need reference retrieval, systematic searching, review topic selection, or to construct a traceable search strategy.

When should I use Reference Search?

Reference Search fits situations like: you need reference retrieval; systematic searching; review topic selection; construct a traceable search strategy.

How do I install Reference Search in Claude Code?

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

How do I install Reference Search in Codex?

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

Can I use Reference Search 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 reference-search -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/reference-search, .gemini/skills/reference-search, .github/skills/reference-search and .opencode/skills/reference-search in your project.

What does Reference Search need to run?

Going by SKILL.md and its folder, Reference Search needs Python for the scripts in its folder, the command-line tools its instructions call (python) and credentials named API_KEY. Our summary lists: Python 3; A credential in API_KEY.

Does Reference Search access the network?

SKILL.md names 2 domains. In commands or code: eutils.ncbi.nlm.nih.gov; the agent is likely to contact it when it follows the instructions. As links in the text: ncbi.nlm.nih.gov. This is read from the text; nothing was executed.

Is Reference Search 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 Reference Search use?

Reference Search 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 Reference Search use?

About 2k tokens (SKILL.md is roughly 7.9k 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 869 tokens, read only when the agent opens those files.

What are the alternatives to Reference Search?

Skills that share tags, products or a category with Reference Search: Systematic Review Screener (Imbad0202/academic-research-skills, 51k stars), Literature Review (neflibata-feng/MyArxiv-Agent, 126 stars), PaperSeek Literature Search (MingfengHong/paperseek, 200 stars) and Academic Search and Citation Router (Yuan1z0825/nature-skills, 46k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Reference Search?

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.