Skills

pdf-proof

by metedata

Trust, but check. A Claude skill that turns AI answers into visual proof — highlighted screenshots and confidence scores, straight from the source PDF.

Visit metedata ↗

Our verdict

Not reviewed yet

We have not reviewed pdf-proof yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About pdf-proof

pdf-proof is a Claude skill that verifies AI answers against source PDFs by generating highlighted screenshots and confidence scores. It operates as a Python-based tool, integrating with Claude to provide visual evidence directly from the document.

Best for

Developers building AI assistants that need to substantiate answers with source documents.

Use cases

Verify AI-generated claims against PDF sources
Produce visual proof for audit or review workflows
Assess answer reliability with confidence scoring

Notes

78 stars on GitHub. Last updated 2026-04-02. Licensed MIT.

Pros

Provides concrete visual evidence, not just text
Integrates directly with Claude for seamless verification
Open-source with a permissive license

Cons

Requires Python environment setup
Limited to PDF sources only
Confidence scores may not reflect all error types

Key facts

What we have checked

Days since the last commit: 219; Checked 7 Nov 2026GitHub
GitHub forks: 3; Checked 7 Nov 2026GitHub
GitHub stars: 78; Checked 7 Nov 2026GitHub
Open issues: 0; Checked 7 Nov 2026GitHub
Releases in the last 90 days: 0; Checked 7 Nov 2026GitHub

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

Stars and usage

How pdf-proof is growing

GitHub stars

77 to 78

stars. 1 Nov 2026 to 7 Nov 2026, 2 readings.

Source: GitHub. Checked 7 Nov 2026.

Health and security

Is pdf-proof looked after, and what do its setup files show

Health score

22 out of 100

Does someone look after this repository? It does not say the code is good or safe. Worked out from GitHub signals checked 7 Nov 2026. How it is worked out

Part	Points	What we saw
Recent activity	13.1 of 30	Last push 219 days ago
Releases	0 of 15	0 releases in 90 days
Issue replies	Not counted	The latest check has no issue response reading (fewer than 3 measured issues, or issues switched off)
Maintainer	0 of 15	Owned by a single user
Official source	Not counted	MCP servers only

Security check static checks

100 out of 100

Reads what is published about the server: package advisories, licence, secrets in the documented setup and tool permissions. Nothing is installed or run, so this is not a security assessment. Checked 24 Oct 2026 by edna-skill-static-v1 main@8ba4cf666459. What it checks

Note 1 of 1 packages are not pinned to one version, so only the malicious packages list was checked for them, not version advisories.

Sources

Where this comes from

GitHubRegistry
Checked 7 Nov 2026 · Days since the last commit, GitHub forks, GitHub stars, Open issues, Releases in the last 90 days

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.

Pairs with

Other entries in the index that connect to this one. Click through to see the chain.

Pairs with3 entries

MMCPCatalogue

research

brontir

Connect BRONTIR to Claude or ChatGPT and it gets real public data from social media, reviews, YouTube, maps, stores and more: structured, with sources, and at a scale your AI can

SSkillslowCatalogue