القائمة
Use when you need to scrape pages, extract structured data or interact with web interfaces via headless browser automation without using screenshots.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Use when running the weekly intelligence review. The AI briefs each engagement from live ecosystem data, the Sovereign speaks freely across 3 this-week and 2 next-week engagements, and the session closes with a Sovereign Command update.
Use when starting a session to initialize the AI interface with continuity checks, a live ecosystem orientation and approval-gated support sweep before any session work begins.
Use when archiving several ecosystem artifacts at once with per-artifact approval gates before any vault move executes.
Use when checking for published updates from the Sovereign Ecosystem GitHub repo and selectively applying only what you explicitly approve.
Use when a long-form manuscript (book chapter, ebook, multi-chapter playbook, long-form digital product) needs an editing pass to identify and remove AI writing tells against the Anti-AI Writing Patterns Codex. Triggered by the Sovereign after draft completion, by a Pending Plan handover map naming this skill at the edit phase, or by any post-draft state where AI-assisted prose needs the anti-pattern sweep before final review.
Use when updating a Pending Plan mid-arc with breadcrumbs, applicability changes, partial implementation notes and reconciliation-ready context.
| name | playwright |
| description | Use when you need to scrape pages, extract structured data or interact with web interfaces via headless browser automation without using screenshots. |
| status | active |
| tier | operational |
Purpose: Browser automation via headless Chromium. Scrape pages, extract structured data, and interact with web interfaces. Returns clean JSON, not screenshots.
Token efficiency: ~200-500 tokens per page vs 20,000-30,000 for screenshot-based approaches.
The run.js script accepts a URL argument and returns JSON. Run it from your vault root using the vault-relative path to this skill's scripts directory.
node "Council Chamber/Skills/Playwright/scripts/run.js" https://example.com
Output format:
{
"url": "https://example.com",
"title": "Page title",
"text": "Cleaned body text...",
"links": [
{ "text": "Link text", "href": "https://..." }
]
}
Playwright must be installed before first use. Run these once with explicit approval from your vault root:
npm install playwright --prefix "Council Chamber/scripts"
npx playwright install chromium
Chromium binary installs to Council Chamber/scripts/node_modules/. Add this path to your AI interface's ignore configuration so it does not appear in context reads.
waitUntil to networkidle and retry.npx playwright install chromium from the scripts directory.playwright-extra and puppeteer-extra-plugin-stealth if a site blocks the script.networkidle for slow pages.finally block. This is already handled in run.js.Tell your AI interface what you need in plain English. Example prompts:
Your AI reads this SKILL.md, runs the script, and returns the data.
Council Chamber/Skills/Playwright/scripts/run.js[!info] Ambassador Doctrine Active This skill operates under the [[Council Chamber/Protocols/Governance/Ambassador Doctrine]]. Primary strategy: Āsana: browser automation is an intelligence retrieval tool; extract, clean, and return before acting. Secondary: Vigraha (assert data quality; surface failed or blocked scrapes rather than returning corrupted output), Saṃśraya (the browser always closes in a finally block; no persistent external state). Playwright does not write to external surfaces. It reads. The read-before-act posture is the doctrine embodied.
(Empty, populated when execution mistakes occur during sessions.)
Also installs standalone from https://www.infinitegameos.io/skills/playwright (dual-distribution: this copy lives in your vault, the public plugin updates independently).