skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
lintendo/axhub-skills65 installs

extract-annotation-source

Use when an Axhub prototype URL needs its PRD, directory, or annotation context read from window.__AXHUB_ANNOTATION_SOURCE__, especially for prototype-as-PRD review, agent context gathering, or annotation extraction with Playwright, Browser, Chrome, or an equivalent page evaluator.

How do I install this agent skill?

npx skills add https://github.com/lintendo/axhub-skills --skill extract-annotation-source
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    The skill extracts metadata and annotations from Axhub prototypes using browser automation. It is vulnerable to indirect prompt injection because it processes content from external websites, including fields specifically designed to hold AI instructions, without implementing sanitization or boundary markers.

  • Socketpass

    No alerts

  • Snykfail

    Risk: HIGH · 2 issues

What does this agent skill do?

Extract Annotation Source

Read Axhub prototype context from the runtime snapshot. Treat the page as read-only.

Workflow

  1. Open the requested prototype URL with Playwright, Browser, Chrome, or an equivalent tool that can evaluate page JavaScript.
  2. Wait until the app renders, then poll briefly for window.__AXHUB_ANNOTATION_SOURCE__.
  3. Evaluate and return that value. Do not modify the object or write anything back to window.
  4. If the value is missing, report the URL, page title, relevant console errors, and that the annotation runtime snapshot was not published.
  5. If the user asks to submit a review report back to Axhub Make, read references/review-report-submission.md.

Minimal page evaluation:

await page.waitForFunction(() => window.__AXHUB_ANNOTATION_SOURCE__, { timeout: 10000 });
const source = await page.evaluate(() => window.__AXHUB_ANNOTATION_SOURCE__);

What To Report

  • Directory / PRD outline from source.directory.
  • Markdown or PRD entries from directory nodes with type: "markdown".
  • Annotation count and the important node fields: id, title, pageId, locator, annotationText, aiPrompt, color, and controls.
  • Source handoff from source.source when present. Report root and manifest; when source is needed, read the manifest and relevant files via root.
  • Mention whether images are attached by checking images.length; do not download images unless the user asks.

Data Shape

type AnnotationSourceRuntimeSnapshot = {
  directory: AnnotationDirectory | null;
  nodes: AnnotationNode[];
  source?: {
    root?: string;
    manifest?: string;
  };
};
  • directory.nodes is the prototype tree. Node types are folder, route, link, and markdown.
  • nodes is the full annotation list, independent of current page, selected state, and color filter.
  • Each annotation node includes id, index, optional title, optional pageId, locator, aiPrompt, annotationText, hasMarkdown, color, images, optional controls, createdAt, and updatedAt.
  • source is only a source-code discovery reference. In HTML published with source included, manifest points to source/manifest.json; resolve its paths relative to source.root.

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/lintendo/axhub-skills/extract-annotation-source">View extract-annotation-source on skillZs</a>