Documents & Data · IN-DEPTH PROFILE

eyeball

Document analysis delivered as a Word file with highlighted source screenshots beside factual claims.

Best for

Reviewers who need claim-level visual traceability in document analysis

What you get

Extract the complete source + Anchor every claim

Main limitation

Requires Python packages, Chromium, and sometimes Word automation; setup is substantial.

First risk

Selective screenshots create false confidence. A precise crop can omit qualifications elsewhere in the document. Read the full source, include enough context, disclose missing anchors, and review the generated Word file before relying on it.

EVIDENCE FRESHNESS

Three checks, kept separate

A recent source check is not a runtime test or security audit.

Upstream sourceChecked 2026-08-20

Pinned revision · 318066d2

Open pinned commit
SkillSignal profileEditorial metadata

Updated 2026-08-20

Runtime & securityNot independently verified

Source review does not certify behavior or safety.

30-SECOND BRIEF

What it does—and when it fits

Eyeball is a GitHub Awesome Copilot document-analysis workflow that extracts a source, writes a Word report, and places highlighted source screenshots beside factual assertions so readers can inspect the cited evidence visually.

INSTALL BY AGENT

Choose your Agent

Paths come from official Agent docs or the universal installer behind skills.sh. Compatibility still follows this Skill's record.

Native

This Skill's current record explicitly names this Agent. Still inspect scripts, permissions, and external dependencies first.

Project scope.agents/skills/eyeball/
Personal scope~/.copilot/skills/eyeball/

Use project scope for team sharing and personal scope across repositories. The installer defaults to project scope; add -g for personal scope.

Install command (project scope)npx skills add github/awesome-copilot --skill eyeball --agent github-copilot
Official agent docs

Copilot also accepts .github/skills and .claude/skills at project scope. Preview untrusted Skills before enabling scripts.

View path evidence

TYPICAL WORKFLOW

A practical workflow

01

Extract the complete source

Read the full text and verify actual headings, sections, and page numbers before analysis.

02

Anchor every claim

Select exact, uncommon source phrases and the pages that directly support each point.

03

Build visual evidence

Create a Word document with dynamically cropped and highlighted screenshots.

THE TRADEOFFS

Advantages and tradeoffs

Notable strengths

  1. Makes source verification visible inside the delivered analysis.
  2. Requires exact anchors rather than generic topic labels.

Limitations

  1. Requires Python packages, Chromium, and sometimes Word automation; setup is substantial.
  2. A highlighted passage proves the source text exists, not that the analysis or source itself is correct.

BEST FIT

Who it is for

Reviewers who need claim-level visual traceability in document analysis

Teams checking contracts, reports, or policies against original pages

BEFORE YOU USE IT

Risks to review before use

High

Selective screenshots create false confidence

A precise crop can omit qualifications elsewhere in the document. Read the full source, include enough context, disclose missing anchors, and review the generated Word file before relying on it.

SECURITY

What the permission profile means

  • Approve dependency installation and browser access separately.
  • Protect generated screenshots and reports at the same level as the source.

Not a security certification. External ratings are attributed references. SkillSignal has not independently executed or security-reviewed this Skill.

INSIDE THE PACKAGE

Indexed files

SKILL.mdUpstream package contentSource-linked
tools/eyeball.pyUpstream package contentSource-linked

TAGS

document-analysisscreenshotstraceability

Original SkillSignal editorial profile grounded in GitHub Awesome Copilot commit 318066d2, checked 2026-08-20; not independently executed or security-certified.