Build pull request descriptions with templates for summary, changes, testing, and screenshots.
This tool builds a pull request description in the four-section shape reviewers expect: a summary, a bulleted list of changes, how the change was tested, and screenshots. You fill in each field and it returns a ready-to-paste Markdown block with consistent heading levels and formatting. The thing most people get wrong is expecting the tool to write the content for them. It organizes and formats what you enter; it does not read your branch, diff, or commit history, and the description contains only your own words. The value is structure and completeness, not generation.
A concrete input and expected output from the current implementation.
Input
Title: Add dark mode toggle Summary: Adds a theme toggle to the header. The choice persists in localStorage and the saved theme is applied on page load. Changes (one per line): - Add the toggle button to the header - Persist the choice in localStorage - Apply the saved theme on page load Testing: Verified the toggle in Chrome and Safari, reloaded the page to confirm persistence, and tabbed through the header to check focus. Screenshots: header-light.png (Header in light mode), header-dark.png (Header in dark mode)
Expected output
## Summary Adds a theme toggle to the header. The choice persists in localStorage and the saved theme is applied on page load. ## Changes - Add the toggle button to the header - Persist the choice in localStorage - Apply the saved theme on page load ## Testing Verified the toggle in Chrome and Safari, reloaded the page to confirm persistence, and tabbed through the header to check focus. ## Screenshots  
Every line of the output traces to a line of input. The tool wraps the entered content in its template headings, converts each changes line into a hyphen bullet, and turns each screenshot file name and caption into an image link.
The form exposes one field per template section: a summary paragraph, a multiline changes list, a testing note, and screenshot entries with captions. On submit, your entries are merged into a Markdown document with section headings, each changes line becoming a hyphen bullet and each screenshot becoming an image line. Nothing is rewritten or reworded, so what you see in the output is exactly the content you supplied.
The result is a self-contained Markdown block with no surrounding HTML or wrapper, so it pastes directly into the description box of GitHub, GitLab, or Bitbucket and renders with their standard Markdown support. The tool runs entirely in the browser and nothing you enter is uploaded, which matters here because a PR description can carry unreleased code details or screenshots of internal UI.
No. The tool works only from what you type into its fields. It does not fetch your repository, read commits, or inspect a diff, so it cannot summarize code it has never seen. If you want the description to reflect what actually changed, paste your own notes or the relevant commit messages into the summary and changes fields and let the tool structure them.
Yes, for standard Markdown: GitHub renders headings, bullet lists, and image syntax as written, so the block pastes straight into the PR description box. Two details to know: task lists written as - [ ] render as interactive checkboxes, and images referenced by file path display only after those files are pushed to the branch or otherwise reachable at the URL in the link.
The example and behavioral notes were checked against the browser implementation. Standards and primary references below define the relevant format, formula, or platform behavior.
Format, validate, and beautify JSON with syntax highlighting and error detection.
Encode text or files to Base64 and decode Base64 strings back to their original form.
Format and indent SQL queries for better readability across all major dialects.
Convert HTML markup into clean Markdown syntax with support for tables and lists.
Write Markdown and see the rendered HTML output in real time with live preview.
Visualize unified diffs and patch files with color-coded additions and deletions.