Agent skill · writing content · github
eyeball
Document analysis with inline source screenshots. When you ask Copilot to analyze a document, Eyeball generates a Word doc where every factual claim includes a highlighted screenshot from the source material so you can verify it with your own eyes.
Why this skill is useful
Adds a Python utility that automates document analysis and verification with inline screenshots, significantly enhancing the AI's capability to produce verified content.
What it needs
Requires pillow, playwright, pymupdf, python-docx, python3, pywin32 installed locally. About 4k tokens when loaded. Last updated 2026-08-07. 37,534 stars on the source repository.
What this skill does
Eyeball Analyze documents with visual proof. When activated, Eyeball produces a Word document on the user's Desktop where every factual assertion includes an inline screenshot from the source material with the cited text highlighted in yellow. Activation When the user invokes this skill (e.g., "use eyeball", "run eyeball on this", "eyeball this document"), respond with: Eyeball is active. I'll analyze the document and produce a Word doc with inline source screenshots so you can verify every claim with your own eyes. Then follow the workflow below. Supported Sources Local files: Word documents (.docx, .doc), PDFs (.pdf), RTF files Web URLs: Any publicly accessible web page Tool Location The Eyeball Python utility is located at: To find the actual path, run: If not found there, check the project directory or the user's home directory for the eyeball repo. First-Run Setup Before first use, check that dependencies are installed: If anything is missing, install the required dependencies: On Windows, also install pywin32 for Word automation: Workflow Follow these steps exactly. The order matters. Step 1: Read the source text Before writing any analysis, extract and read the full text of the source document: Read the output carefully. Identify actual section numbers, headings, page numbers, and key language. CRITICAL: Do not skip this step. Do not write analysis based on assumptions about how the document is structured. Read the actual text. Step 2: Write analysis with exact citations For each point in your analysis, you must: 1. Reference the correct section number as it appears in the document (e.g., "Section 9" not "Section 8" because you assumed the numbering). 2. Reference the correct page number where the section appears in the extracted text. 3. Select anchors that are verbatim phrases from the source that directly support your claim. Step 3: Select anchors correctly This is the most important step. Anchors determine what gets highlighted in the screenshots. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills github/eyeball