github-upload-image-to-pr（GitHub upload 图像 TO PR）

Upload Image to PR

Upload local images to a GitHub PR and embed them in the description or comments using browser automation tools.

How It Works

Since the GitHub API does not support direct image uploads, this skill uses the PR comment textarea as a staging area for GitHub's image hosting — uploading files there to obtain persistent user-attachments/assets/ URLs, then updating the PR description or posting a comment via the gh CLI.

Step 0: Resolve PR context

If the user didn't specify a PR number or URL, auto-detect it:

# Get PR number from the current branch
gh pr view --json number,url -q '"\(.number) \(.url)"'

If multiple repos or branches are involved, confirm with the user which PR to target.

Also, normalize the image paths to absolute paths. If a path contains special characters (e.g., Unicode narrow spaces from CleanShot X), copy the file to /tmp/ first:

# e.g., to handle glob-matched paths with special chars
cp /path/to/CleanShot*keyword*.png /tmp/screenshot.png

Tool Detection and Selection

Priority Order

1. Playwright MCP (MCP connection, mcp__playwright__*) — connects to existing browser, login state preserved
2. Chrome DevTools MCP (MCP connection, mcp__chrome-devtools__*) — connects to existing browser, login state preserved
3. agent-browser (CLI via Bash — fallback, login state preserved with --profile)

MCP-based tools connect to an already-running browser instance, so GitHub login state is automatically preserved. agent-browser can persist login state using --profile ~/.agent-browser-github.

Detection

# 1. Search for MCP-based browser tools (preferred)
ToolSearch: "browser navigate upload"

# 2. Fall back to agent-browser only if no MCP tools found
Bash: agent-browser --version

Tool Compatibility Matrix

Steps

Step 1: Navigate to PR page and check login state

Navigate to the PR page and immediately take a snapshot to verify login state.

// Playwright MCP
browser_navigate({ url: "https://github.com/{owner}/{repo}/pull/{number}" })

// Chrome DevTools MCP
navigate_page({ url: "https://github.com/{owner}/{repo}/pull/{number}", type: "url" })

// agent-browser (use --profile to persist login state)
agent-browser --headed --profile ~/.agent-browser-github open "https://github.com/{owner}/{repo}/pull/{number}"

If SSO authentication screen appears: Take a snapshot, locate the "Continue" button, and click it.

If NOT logged in (agent-browser only):

1. Navigate to https://github.com/login
2. Ask the user to log in manually in the headed browser window.
3. Wait for user confirmation, then navigate back to the PR page.

Step 2: Locate the file upload input

Take a snapshot/screenshot and scroll to the bottom to find the comment area.

GitHub renders a file upload input in the comment form. Try these selectors in order (GitHub's UI can change — if one fails, try the next):

// Shared JS for MCP-based tools — tries multiple known selectors
() => {
  const selectors = [
    'input[type="file"][id*="comment"]',
    'input[type="file"][id="fc-new_comment_field"]',
    '#new_comment_field',
    'input[type="file"]'
  ];
  for (const sel of selectors) {
    const el = document.querySelector(sel);
    if (el) return { found: true, id: el.id, selector: sel };
  }
  return { found: false };
}

For Chrome DevTools MCP, you can also take a snapshot to find the uid of the file upload element directly.

Step 3: Upload images one by one

Upload each image file using the detected tool. Wait 2–3 seconds between uploads to allow GitHub to process each file.

For multiple images, upload them all to the same comment textarea before extracting URLs — this is more efficient than navigating between uploads.

// Chrome DevTools MCP: upload_file requires the uid of the input element
// Playwright MCP: browser_file_upload takes the element ref and file path(s) array
// agent-browser: agent-browser upload {ref} {absolute_path}

Important: Always use absolute file paths.

Step 4: Retrieve uploaded image URLs

Wait 3–5 seconds after the last upload, then read the textarea value. GitHub injects markdown image syntax like ![description](https://github.com/user-attachments/assets/...) into the textarea:

// Shared JS — tries both known textarea IDs
() => {
  const ta = document.getElementById('new_comment_field')
          || document.querySelector('textarea[id*="comment"]');
  return ta ? ta.value : 'textarea not found';
}

# agent-browser
agent-browser eval 'document.getElementById("new_comment_field")?.value || document.querySelector("textarea[id*=comment]")?.value || "not found"'

The response contains URLs in the format:

![image](https://github.com/user-attachments/assets/xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx)

Extract all image URLs/markdown from the textarea value before clearing it.

Step 5: Clear the textarea (do not submit the comment)

// MCP-based tools
() => {
  const ta = document.getElementById('new_comment_field')
           || document.querySelector('textarea[id*="comment"]');
  if (ta) { ta.value = ""; return "cleared"; }
  return "textarea not found";
}

# agent-browser
agent-browser eval 'const ta = document.getElementById("new_comment_field") || document.querySelector("textarea[id*=comment]"); if(ta){ta.value=""} "cleared"'

Step 6: Embed images in the PR

Option A — Update PR description (append images to existing body):

EXISTING_BODY=$(gh pr view {PR_NUMBER} --json body -q .body)

gh pr edit {PR_NUMBER} --body "$(printf '%s\n\n## Screenshots\n\n%s' "$EXISTING_BODY" "![screenshot](https://github.com/user-attachments/assets/...)")"

Option B — Post as a new comment:

gh pr comment {PR_NUMBER} --body "## Screenshots

![screenshot](https://github.com/user-attachments/assets/...)"

Use Option A by default unless the user explicitly asks for a comment, or if the PR description is already long and a comment would be cleaner.

Step 7: Verify the result

Reload the page and take a screenshot to confirm the images are displayed correctly.

Tips

• Image sizing: Control display size via HTML <img> tags: <img width="800" alt="description" src="..." />
• Multiple images: Upload all images in one session to the same textarea; extract all URLs before clearing
• Prefer MCP tools: Always prefer Playwright or Chrome DevTools MCP over agent-browser for simpler setup
• agent-browser login persistence: Use --profile ~/.agent-browser-github to persist GitHub login across sessions

Troubleshooting

Notes

• GitHub user-attachments/assets/ URLs are persistent — images remain accessible even without submitting the comment
• Editing the description directly in the browser UI is fragile due to GitHub UI structure changes — updating via gh pr edit is strongly preferred
• Multiple images can be uploaded in a single session before extracting URLs
• MCP-based tools connect to existing browser instances, preserving cookies and login sessions