Official agent skill

Eyeball

Document analysis with inline source screenshots. An agent skill from github/awesome-copilot.

OfficialMITAuto-check passedDocuments & Office

Install Eyeball

skills CLI

$ npx skills add github/awesome-copilot --skill eyeball -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install github/awesome-copilot eyeball --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/github/awesome-copilot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/eyeball .claude/skills/eyeball && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "eyeball" agent skill from https://github.com/github/awesome-copilot/tree/main/skills/eyeball into .claude/skills/eyeball/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "eyeball", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/github/awesome-copilot/tree/main/skills/eyeball

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add github/awesome-copilot --skill eyeball -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install github/awesome-copilot eyeball --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/github/awesome-copilot.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/eyeball .agents/skills/eyeball && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "eyeball" agent skill from https://github.com/github/awesome-copilot/tree/main/skills/eyeball into .agents/skills/eyeball/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "eyeball", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add github/awesome-copilot --skill eyeball -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install github/awesome-copilot eyeball --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/github/awesome-copilot.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/eyeball .cursor/skills/eyeball && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "eyeball" agent skill from https://github.com/github/awesome-copilot/tree/main/skills/eyeball into .cursor/skills/eyeball/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "eyeball", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/github/awesome-copilot.git --path skills/eyeball

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add github/awesome-copilot --skill eyeball -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install github/awesome-copilot eyeball --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/github/awesome-copilot.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/eyeball .gemini/skills/eyeball && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "eyeball" agent skill from https://github.com/github/awesome-copilot/tree/main/skills/eyeball into .gemini/skills/eyeball/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "eyeball", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install github/awesome-copilot eyeball

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add github/awesome-copilot --skill eyeball -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/github/awesome-copilot.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/eyeball .github/skills/eyeball && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "eyeball" agent skill from https://github.com/github/awesome-copilot/tree/main/skills/eyeball into .github/skills/eyeball/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "eyeball", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add github/awesome-copilot --skill eyeball -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install github/awesome-copilot eyeball --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/github/awesome-copilot.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/eyeball .opencode/skills/eyeball && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "eyeball" agent skill from https://github.com/github/awesome-copilot/tree/main/skills/eyeball into .opencode/skills/eyeball/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "eyeball", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: eyeball
GitHub stars: 40k
Used in: 1 other repo
Token cost: ~1.6k tokens
SKILL.md length: 738 words
Files: 2
Skills in repo: 417
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Document analysis with inline source screenshots. An agent skill from github/awesome-copilot.

Works in 5 steps: Read the source text → Write analysis with exact citations → Select anchors correctly → …
Tasks that involve Word documents
SKILL.md covers Activation, Supported Sources, Tool Location and First-Run Setup, plus 3 more sections
Runs Python scripts from its folder; calls python3, pip3 and pip

What it does

Eyeball is an agent skill from github/awesome-copilot, published by the product's own GitHub organization. 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.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `tools/eyeball.py`).

It sits in Documents & Office, covering Word documents. The repository describes itself as: Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot. The licence is MIT.

When your agent uses it

Tasks that involve Word documents

Example prompts

“/eyeball”

Requirements

Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

Read the source text
Write analysis with exact citations
Select anchors correctly
Build the analysis document
Deliver the output

What it can do on your machine

Read from SKILL.md and the folder at commit 727ff2e. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (Python), which the agent can run.
Shell commands in SKILL.md call:
- python3
- pip3
- pip
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip3 and pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Eyeball loads about 1.6k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 738 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~64
When it runs · the whole SKILL.md, loaded when a task matches: ~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from github/awesome-copilot at commit 727ff2e, republished under its MIT licence (© github). 738 words, ~1,637 tokens.

Download SKILL.mdSave it as .claude/skills/eyeball/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: eyeball
description: 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.

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:

<plugin_dir>/skills/eyeball/tools/eyeball.py

To find the actual path, run:

bash

find ~/.copilot/installed-plugins -name "eyeball.py" -path "*/eyeball/*" 2>/dev/null

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:

bash

python3 <path-to>/eyeball.py setup-check

If anything is missing, install the required dependencies:

bash

pip3 install pymupdf pillow python-docx playwright
python3 -m playwright install chromium

On Windows, also install pywin32 for Word automation:

bash

pip install pywin32

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:

bash

python3 <path-to>/eyeball.py extract-text --source "<path-or-url>"

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:

Reference the correct section number as it appears in the document (e.g., "Section 9" not "Section 8" because you assumed the numbering).
Reference the correct page number where the section appears in the extracted text.
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.

DO:

Use verbatim phrases from the source text that directly support your assertion
Use multiple anchors to span the full range of text the reader should see
Use specific, uncommon phrases that appear only where you intend

DO NOT:

Use generic topic labels (e.g., "Confidentiality") that appear throughout the document
Use section titles alone when they appear as cross-references elsewhere
Use single common words that match in many places

Examples:

WRONG -- uses a generic topic label that matches everywhere:

json

{"anchors": ["User-Generated Content"], "target_page": 8}

RIGHT -- uses the specific language that supports the claim:

json

{"anchors": ["retain ownership", "Ownership of Content, Right to Post"], "target_page": 8}

WRONG -- section title appears as a cross-reference on earlier pages:

json

{"anchors": ["LIMITATION OF LIABILITY"]}

RIGHT -- includes the section number for precision, targets the correct page:

json

{"anchors": ["12. LIMITATION OF LIABILITY", "INDIRECT", "CONSEQUENTIAL"], "target_page": 13}

Show full SKILL.md (315 more words)Show less

Step 4: Build the analysis document

Construct a JSON array of sections and call the build command:

bash

python3 <path-to>/eyeball.py build \
  --source "<path-or-url>" \
  --output ~/Desktop/<title>.docx \
  --title "Analysis Title" \
  --subtitle "Source description" \
  --sections '[
    {
      "heading": "1. Section Title",
      "analysis": "Your analysis text here. Reference Section X on page Y...",
      "anchors": ["verbatim phrase 1", "verbatim phrase 2"],
      "target_page": 5,
      "context_padding": 40
    },
    {
      "heading": "2. Another Section",
      "analysis": "More analysis...",
      "anchors": ["exact quote from source"],
      "target_pages": [10, 11],
      "context_padding": 50
    }
  ]'

Section object fields:

heading (required): Section heading in the output document
analysis (required): Your analysis text
anchors (required): List of verbatim phrases from the source to search for and highlight
target_page (optional): Single page number (1-indexed) to search on
target_pages (optional): List of page numbers to search across (screenshots stitched vertically)
context_padding (optional): Padding in PDF points above/below the anchor region (default: 40). Increase for more context.

Step 5: Deliver the output

Save the output to the user's Desktop. Tell the user the filename and that they can open it to verify each claim against the highlighted source screenshots.

Self-Check Before Delivery

Before saving the final document, mentally verify:

Does each section's analysis text reference the correct section number from the source?
Are the anchors verbatim phrases that appear on the target page?
Does each anchor directly support the claim in the analysis, not just relate to the same topic?
If the screenshot doesn't match the analysis, is the analysis wrong or is the anchor wrong? Fix whichever is incorrect.

Notes

The output document includes highlighted screenshots that are dynamically sized. If you provide multiple anchors, the screenshot expands to cover all of them.
When a search term is not found, the output document will note this. If this happens, the anchor was likely not verbatim enough. Adjust and rebuild.
For web pages, Playwright renders the page to PDF first. The resulting page numbers may differ from what you see in a browser. Use the extracted text output (step 1) to determine correct page numbers.
If the user has already provided the source text or you have already read it in the current conversation, you can skip step 1. But always verify section numbers and page references against the actual text before writing analysis.

Files

SKILL.md and 1 other file in skills/eyeball of github/awesome-copilot.

SKILL.md
tools/eyeball.py

Open the folder on GitHubat commit 727ff2e

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in github/awesome-copilot, which our catalogue first saw on October 7, 2026.

boshi-xixixi/TraeSkill.trae/Skills/.agents/skills/eyeball

Compare with similar skills

Eyeball next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Eyeball compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Eyeball this skillgithub/awesome-copilot	40k	1 repos	~1.6k	Automated safety check: Pass	MIT	today
MarkitdownImCa0/just-laws	781	14 repos	~3.2k	Automated safety check: Notes	MIT	8 days ago
DOCXrvdbreemen/OTGW-firmware	207	33 repos	~4.3k	Automated safety check: Pass	Proprietary	today
Gzh Designisjiamu/gzh-design-skill	3.9k	1 repos	~2.2k	Automated safety check: Pass	AGPL-3.0	4 days ago
Word Document Reader and WriterHKUDS/DeepTutor	41k	—	~2.5k	Automated safety check: Pass	Apache-2.0	3 days ago
GenOffice Document CLIgenspark-ai/genoffice	8.8k	—	~19k	Automated safety check: Pass	Apache-2.0	today

Similar skills

Markitdown
ImCa0/just-laws
Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.
781 GitHub starsUsed in 14 repos~3.2k tokens
Documents & OfficeAuto-check: notes
DOCX
rvdbreemen/OTGW-firmware
A skill your agent uses whenever the user wants to create, read, edit, or manipulate Word documents (.docx files).
207 GitHub starsUsed in 33 repos~4.3k tokens
Documents & OfficeAuto-check passed
Gzh Design
isjiamu/gzh-design-skill
微信公众号文章排版引擎，将 Markdown 转换为可直接粘贴到公众号编辑器的 HTML。主题风格从 references/theme-index.md 注册的自定义主题库中选取，自动章节编号、关键词下划线标记、引言卡片、目录导航、代码块、图片/GIF、作者签名。支持 Markdown / Word(.docx) / PDF / 纯文本输入（非 Markdown…
3.9k GitHub starsUsed in 1 repo~2.2k tokens
Documents & OfficeAuto-check passed
Word Document Reader and Writer
HKUDS/DeepTutor
Reads, creates and edits Word .docx files with python-docx, and drops to raw OOXML for tracked changes, comments and byte-exact edits.
41k GitHub stars~2.5k tokensUpdated 3 days ago
Documents & OfficeAuto-check passed
GenOffice Document CLI
genspark-ai/genoffice
Creates, converts, reads and edits real pptx, xlsx, docx and PDF files locally through the genoffice command line.
8.8k GitHub stars~19k tokensUpdated today
Documents & OfficeAuto-check passed
BiSheng DOCX Builder
dataelement/bisheng
Builds or edits Word .docx documents inside BiSheng's code executor with python-docx, handling Chinese fonts, tables of contents, page numbers and official-document layout.
12k GitHub stars~2.6k tokensUpdated 7 days ago
Documents & OfficeAuto-check passed

Questions about Eyeball

What does Eyeball do?

Document analysis with inline source screenshots. An agent skill from github/awesome-copilot. Eyeball is an agent skill from github/awesome-copilot, published by the product's own GitHub organization. Document analysis with inline source screenshots.

When should I use Eyeball?

Eyeball fits situations like: tasks that involve Word documents.

How do I install Eyeball in Claude Code?

Run `npx skills add github/awesome-copilot --skill eyeball -a claude-code`. Or copy the skill folder (skills/eyeball in github/awesome-copilot) into .claude/skills/eyeball in your project. Claude Code loads it when a task matches its description.

How do I install Eyeball in Codex?

Run `npx skills add github/awesome-copilot --skill eyeball -a codex`. Or copy the skill folder (skills/eyeball in github/awesome-copilot) into .agents/skills/eyeball in your project. Codex loads it when a task matches its description.

Can I use Eyeball in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add github/awesome-copilot --skill eyeball -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/eyeball, .gemini/skills/eyeball, .github/skills/eyeball and .opencode/skills/eyeball in your project.

What does Eyeball need to run?

Going by SKILL.md and its folder, Eyeball needs Python for the scripts in its folder and the command-line tools its instructions call (python3, pip3 and pip). Our summary lists: Python 3.

Does Eyeball access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Eyeball safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Eyeball use?

Eyeball is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Eyeball use?

About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Eyeball?

Skills that share tags, products or a category with Eyeball: Markitdown (ImCa0/just-laws, 781 stars), DOCX (rvdbreemen/OTGW-firmware, 207 stars), Gzh Design (isjiamu/gzh-design-skill, 3.9k stars) and Word Document Reader and Writer (HKUDS/DeepTutor, 41k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Eyeball?

github (a GitHub organization, an official publisher) maintains it in github/awesome-copilot, which has 39,748 GitHub stars. The repository holds 417 skills in this directory. The repository was last updated on October 7, 2026.

Source: github/awesome-copilot on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Eyeball

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Eyeball

Activation

Supported Sources

Tool Location

First-Run Setup

Workflow

Step 1: Read the source text

Step 2: Write analysis with exact citations

Step 3: Select anchors correctly

Step 4: Build the analysis document

Step 5: Deliver the output

Self-Check Before Delivery

Notes

Files

Used in 1 other repository

Compare with similar skills

Similar skills

More from github/awesome-copilot

Related

Questions about Eyeball