🧮

Statistical Claim Checker

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

Check quantitative claims against their cited data and definitions.

Get recalculated figures, source locations and severity-ranked corrections.

Download skill ZIP See the worked example

Free · 2 KB · SKILL.md, instructions and example files. Provide the claim, original data or source, units and relevant dates.

A worked example

A small example to try before using your own data.

Input

{
  "before": {
    "successes": 20,
    "total": 100
  },
  "after": {
    "successes": 30,
    "total": 100
  },
  "claim": "Success improved by 10 percent."
}

Expected result

Rate rose from 20% to 30%: +10 percentage points, or +50% relative. The supplied counts do not establish that the intervention caused the change.

What to check: Show both denominators and both change definitions; do not infer significance or causation from these totals.

Limits: Missing source data stays unresolved. This recipe does not replace domain-specific statistical review.

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 = "statistical-claim-checker"
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/statistical-claim-checker.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() != "f3a68f8bc90ccc8a654e01a8f6a38e3081b385089813be483771ab0a8ca31ee2":
    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/statistical-claim-checker/SKILL.md. Codex: ~/.codex/skills/statistical-claim-checker/SKILL.md. Keep the complete ZIP folder when helper scripts are included.

🧠 Why it works

Show both denominators and both change definitions; do not infer significance or causation from these totals.

⚙️ How it works

Extract the quantity, denominator, comparison window, unit and claimed uncertainty.

Locate the source rows and confirm the same population and definitions are used.

Recalculate with explicit arithmetic, preserving missing data and units.

Distinguish percentage-point changes, percentage changes and causal claims.

Report the supported statement and any unresolved assumptions rather than giving a single opaque credibility score.

Description

Get recalculated figures, source locations and severity-ranked corrections.

Provide the claim, original data or source, units and relevant dates.

Limits: Missing source data stays unresolved. This recipe does not replace domain-specific statistical review.