🗺️

Literature Map Builder

Research & Analysis · by AIDiveForge · Apr 20, 2026 · Intermediate

Organize supplied papers into an evidence-based topic map.

Get clusters, paper-level evidence and clearly labeled research questions.

Download skill ZIP See the worked example

Free · 2 KB · SKILL.md, instructions and example files. Provide paper texts or abstracts with stable identifiers.

A worked example

A small example to try before using your own data.

Input

{
  "papers": [
    {
      "id": "A",
      "method": "retrieval",
      "finding": "better factuality on short answers"
    },
    {
      "id": "B",
      "method": "retrieval",
      "finding": "no gain on long answers"
    },
    {
      "id": "C",
      "method": "human review",
      "finding": "catches citation errors"
    }
  ]
}

Expected result

Cluster 1: retrieval, A/B; results vary with answer length. Cluster 2: human review, C. Question suggested by this corpus: does combined retrieval and review help long answers? Search beyond these three papers before claiming a literature gap.

What to check: Keep the A/B disagreement and scope every gap claim to the supplied corpus.

Limits: Coverage depends on the papers provided. The output is not a systematic review unless a systematic search was actually performed.

Worked example included. Model-specific performance and vendor compatibility have not been benchmarked.

Installation options and other formats

Install this skill

An agent skill starts with SKILL.md. The ZIP also includes its examples and any helper scripts. Drop the file into your tool of choice — or pick a different format if you use Cursor, Windsurf, Copilot, or something else.

Format Download SKILL.md

Quick install — paste into your terminal

python3 - <<'ADF_SKILL_INSTALL'
import hashlib, io, os, stat, tempfile, urllib.request, zipfile
from pathlib import Path, PurePosixPath
folder = "literature-map-builder"
root = Path(os.environ.get('ADF_SKILL_ROOT', str(Path.home() / '.claude' / 'skills'))).expanduser()
destination = root / folder
if destination.exists() or destination.is_symlink():
    raise SystemExit('An installation already exists. Back it up and merge the ZIP deliberately.')
root.mkdir(parents=True, exist_ok=True)
request = urllib.request.Request("https://aidiveforge.com/skill/literature-map-builder.zip", headers={'User-Agent': 'AIDiveForge-Resource-Installer/1.0 (+https://aidiveforge.com/skills/)'})
with urllib.request.urlopen(request, timeout=30) as response:
    data = response.read(8 * 1024 * 1024 + 1)
if len(data) > 8 * 1024 * 1024 or hashlib.sha256(data).hexdigest() != "2d1db06e3eb4a7d5aeedf33142b57eef4f8b8b091a97c84856cfd541fcbba246":
    raise SystemExit('The download did not match this reviewed bundle. No files were installed.')
with zipfile.ZipFile(io.BytesIO(data)) as archive, tempfile.TemporaryDirectory(prefix='.adf-skill-', dir=root) as temporary:
    members = archive.infolist()
    if len(members) > 100 or sum(m.file_size for m in members) > 16 * 1024 * 1024:
        raise SystemExit('Unexpected archive size')
    for member in members:
        name = PurePosixPath(member.filename)
        if name.is_absolute() or '..' in name.parts or not name.parts or name.parts[0] != folder or '\\' in member.filename or stat.S_ISLNK(member.external_attr >> 16):
            raise SystemExit('Unsafe archive entry; nothing was installed')
        target = Path(temporary).joinpath(*name.parts)
        if member.is_dir():
            target.mkdir(parents=True, exist_ok=True)
        else:
            target.parent.mkdir(parents=True, exist_ok=True)
            with target.open('xb') as stream:
                stream.write(archive.read(member))
    staged = Path(temporary) / folder
    if not (staged / 'SKILL.md').is_file() or destination.exists() or destination.is_symlink():
        raise SystemExit('The skill could not be installed without replacing existing data')
    os.rename(staged, destination)
print('Installed the complete skill folder:', destination)
ADF_SKILL_INSTALL

Claude Code: ~/.claude/skills/literature-map-builder/SKILL.md. Codex: ~/.codex/skills/literature-map-builder/SKILL.md. Keep the complete ZIP folder when helper scripts are included.

🧠 Why it works

Keep the A/B disagreement and scope every gap claim to the supplied corpus.

⚙️ How it works

Record each paper’s question, method, dataset, result and stated limitations.

Cluster by the research question and method rather than title keywords alone.

Keep paper identifiers on every cluster summary and identify contradictory results.

Describe apparent gaps as questions within this supplied corpus, not proof that no research exists.

Return the map, an evidence table and targeted searches that could test the proposed gaps.

Description

Get clusters, paper-level evidence and clearly labeled research questions.

Provide paper texts or abstracts with stable identifiers.

Limits: Coverage depends on the papers provided. The output is not a systematic review unless a systematic search was actually performed.