{
  "id": 19086456,
  "title": "Hide your slop PR descriptions behind <details><summary>",
  "url": "https://urgent.news/2026/11/09/hide-your-slop-pr-descriptions-behind-details-summary",
  "topic": "culture",
  "section": "Culture",
  "published": "2026-11-09T04:25:05.000Z",
  "source": {
    "name": "Simon Willison",
    "slug": "simon-willison",
    "url": "https://simonwillison.net/2026/Nov/9/details-summary/"
  },
  "original_language": "en",
  "account": "Simon Willison's recent article introduces a clever trick for filtering through AI-generated pull request (PR) descriptions on GitHub. The method involves utilizing the HTML `<details>` and `<summary>` elements directly within Markdown comments or PR descriptions. These elements create a collapsible content section, where the summary serves as a concise, high-level introduction, and the detailed description remains hidden until expanded. This approach effectively reduces the cognitive load on readers, allowing them to quickly assess whether a PR merits their attention based on a brief, human-curated summary.\n\nWillison employs this technique for PRs created or edited by AI agents such as Claude Code or Codex. He emphasizes that while AI-generated descriptions are accurate and comprehensive, they often require too much time to read, making them less appealing. By using the `<details>` and `<summary>` tags, he places the most crucial information upfront, ensuring that the essence of the PR is immediately visible. This summary can include screenshots or other visual aids to further illustrate changes or new features.\n\nTo assist with remembering the correct tag order, Willison suggests referring to them as \"details-summary,\" which rolls off the tongue more smoothly than the more intuitive-seeming \"summary-details.\" He encourages readers to practice saying the phrase aloud to reinforce the order. Although GitHub could benefit from a built-in button for this feature in their Markdown editor, Willison believes that implementing it manually is a worthwhile workaround.\n\nOverall, by integrating AI-generated content with human editorial oversight, Willison's method aims to preserve the richness of detailed PR descriptions while making them more accessible and digestible for human readers. This approach not only enhances the readability of PRs but also maintains the integrity of the information presented.",
  "summary": "Most of the changes I make to my projects these days come in the form of PRs opened for me by Claude Code or Codex. The PR is my unit of work - I use them to bundle commits together, iterating on them until a feature is complete, document decisions and then merge the finished result. Today's coding agents are great at writing PR descriptions. They're too good at describing the work The problem is…",
  "key_points": [
    "Use HTML details and summary elements in Markdown for collapsible PR descriptions.",
    "Summaries provide concise, human-curated introductions to PRs.",
    "AI-generated descriptions are accurate but often too lengthy for quick assessment."
  ],
  "editors_take": "Collapsing AI-generated text within pull requests prioritizes human oversight and reduces cognitive fatigue by ensuring that concise, curated summaries are the first thing developers encounter during code reviews.",
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}