feat: add playwright-visit skill for browser automation

- visit.py CLI with subcommands: screenshot, text, html, pdf - Uses system chromium on NixOS (no browser download) - Fresh profile each run (no cookies/history) - flake.nix provides playwright devShell - Options: --wait, --full-page Useful for JS-heavy sites where WebFetch fails. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-29 00:09:50 -05:00 · 2025-12-29 00:09:50 -05:00 · d24bedcab3
parent efb7cdaffc
commit d24bedcab3
6 changed files with 338 additions and 1 deletions
--- a/.beads/issues.jsonl
+++ b/.beads/issues.jsonl
@ -92,7 +92,7 @@
 {"id":"skills-qeh","title":"Add README.md for web-research skill","description":"web-research skill has SKILL.md and scripts but no README.md. AGENTS.md says README.md is for humans, contains installation instructions, usage examples, prerequisites.","status":"closed","priority":2,"issue_type":"task","created_at":"2025-11-30T11:58:14.475647113-08:00","updated_at":"2025-12-28T22:37:48.339288261-05:00","closed_at":"2025-12-28T22:37:48.339288261-05:00","close_reason":"Added README.md with prerequisites, usage examples, and cross-references","dependencies":[{"issue_id":"skills-qeh","depends_on_id":"skills-vb5","type":"blocks","created_at":"2025-11-30T12:01:30.278784381-08:00","created_by":"daemon","metadata":"{}"}]}
 {"id":"skills-r5c","title":"Extract shared logging library from scripts","description":"Duplicated logging/color functions across multiple scripts:\n- bin/deploy-skill.sh\n- skills/tufte-press/scripts/generate-and-build.sh\n- Other .specify scripts\n\nPattern repeated:\n- info(), warn(), error() functions\n- Color definitions (RED, GREEN, etc.)\n- Same 15-20 lines in each file\n\nFix:\n- Create scripts/common-logging.sh\n- Source from all scripts that need it\n- Estimated reduction: 30+ lines of duplication\n\nSeverity: MEDIUM","status":"open","priority":2,"issue_type":"task","created_at":"2025-12-24T02:50:58.324852578-05:00","updated_at":"2025-12-24T02:50:58.324852578-05:00"}
 {"id":"skills-rex","title":"Test integration on worklog skill","description":"Use worklog skill as first real test case:\n- Create wisp for worklog execution\n- Capture execution trace\n- Test squash → digest\n- Validate trace format captures enough info for replay\n\nMigrated from dotfiles-drs.","status":"open","priority":3,"issue_type":"task","created_at":"2025-12-23T19:21:18.75525644-05:00","updated_at":"2025-12-23T19:21:18.75525644-05:00","dependencies":[{"issue_id":"skills-rex","depends_on_id":"skills-3em","type":"blocks","created_at":"2025-12-23T19:22:00.34922734-05:00","created_by":"dan"}]}
-{"id":"skills-rpf","title":"Implement playwright-visit skill for browser automation","description":"## Overview\nBrowser automation skill using Playwright to visit web pages, take screenshots, and extract content.\n\n## Key Findings (from dotfiles investigation)\n\n### Working Setup\n- Use `python312Packages.playwright` from nixpkgs (handles Node driver binary patching for NixOS)\n- Use `executable_path='/run/current-system/sw/bin/chromium'` to use system chromium\n- No `playwright install` needed - no browser binary downloads\n\n### Profile Behavior\n- Fresh/blank profile every launch by default\n- No cookies, history, or logins from user's browser\n- Can persist state with `storage_state` parameter if needed\n\n### Example Code\n```python\nfrom playwright.sync_api import sync_playwright\n\nwith sync_playwright() as p:\n    browser = p.chromium.launch(\n        executable_path='/run/current-system/sw/bin/chromium',\n        headless=True\n    )\n    page = browser.new_page()\n    page.goto('https://example.com')\n    print(page.title())\n    browser.close()\n```\n\n### Why Not uv/pip?\n- Playwright pip package bundles a Node.js driver binary\n- NixOS can't run dynamically linked executables without patching\n- nixpkgs playwright handles this properly\n\n## Implementation Plan\n1. Create `skills/playwright-visit/` directory\n2. Add flake.nix with devShell providing playwright\n3. Create CLI script with subcommands:\n   - `screenshot \u003curl\u003e \u003coutput.png\u003e` - capture page\n   - `text \u003curl\u003e` - extract text content  \n   - `html \u003curl\u003e` - get rendered HTML\n   - `pdf \u003curl\u003e \u003coutput.pdf\u003e` - save as PDF\n4. Create skill definition for Claude Code integration\n5. Document usage in skill README\n\n## Dependencies\n- nixpkgs python312Packages.playwright\n- System chromium (already in dotfiles)\n\n## Related\n- dotfiles issue dotfiles-m09 (playwright skill request)","status":"open","priority":2,"issue_type":"feature","created_at":"2025-12-16T16:02:28.577381007-08:00","updated_at":"2025-12-16T16:02:28.577381007-08:00"}
+{"id":"skills-rpf","title":"Implement playwright-visit skill for browser automation","description":"## Overview\nBrowser automation skill using Playwright to visit web pages, take screenshots, and extract content.\n\n## Key Findings (from dotfiles investigation)\n\n### Working Setup\n- Use `python312Packages.playwright` from nixpkgs (handles Node driver binary patching for NixOS)\n- Use `executable_path='/run/current-system/sw/bin/chromium'` to use system chromium\n- No `playwright install` needed - no browser binary downloads\n\n### Profile Behavior\n- Fresh/blank profile every launch by default\n- No cookies, history, or logins from user's browser\n- Can persist state with `storage_state` parameter if needed\n\n### Example Code\n```python\nfrom playwright.sync_api import sync_playwright\n\nwith sync_playwright() as p:\n    browser = p.chromium.launch(\n        executable_path='/run/current-system/sw/bin/chromium',\n        headless=True\n    )\n    page = browser.new_page()\n    page.goto('https://example.com')\n    print(page.title())\n    browser.close()\n```\n\n### Why Not uv/pip?\n- Playwright pip package bundles a Node.js driver binary\n- NixOS can't run dynamically linked executables without patching\n- nixpkgs playwright handles this properly\n\n## Implementation Plan\n1. Create `skills/playwright-visit/` directory\n2. Add flake.nix with devShell providing playwright\n3. Create CLI script with subcommands:\n   - `screenshot \u003curl\u003e \u003coutput.png\u003e` - capture page\n   - `text \u003curl\u003e` - extract text content  \n   - `html \u003curl\u003e` - get rendered HTML\n   - `pdf \u003curl\u003e \u003coutput.pdf\u003e` - save as PDF\n4. Create skill definition for Claude Code integration\n5. Document usage in skill README\n\n## Dependencies\n- nixpkgs python312Packages.playwright\n- System chromium (already in dotfiles)\n\n## Related\n- dotfiles issue dotfiles-m09 (playwright skill request)","status":"in_progress","priority":2,"issue_type":"feature","created_at":"2025-12-16T16:02:28.577381007-08:00","updated_at":"2025-12-28T23:36:17.277851709-05:00"}
 {"id":"skills-s92","title":"Add tests for config injection (deploy-skill.sh)","description":"File: bin/deploy-skill.sh (lines 112-137)\n\nCritical logic with NO test coverage:\n- Idempotency (running twice should be safe)\n- Correct brace matching in Nix\n- Syntax validity of injected config\n- Rollback on failure\n\nRisk: MEDIUM-HIGH - can break dotfiles Nix config\n\nFix:\n- Test idempotent injection\n- Validate Nix syntax after injection\n- Test with malformed input\n\nSeverity: MEDIUM","status":"open","priority":3,"issue_type":"task","created_at":"2025-12-24T02:51:01.314513824-05:00","updated_at":"2025-12-24T02:51:01.314513824-05:00"}
 {"id":"skills-ty7","title":"Define trace levels (audit vs debug)","description":"Two trace levels to manage noise vs utility:\n\n1. Audit trace (minimal, safe, always on):\n   - skill id/ref, start/end\n   - high-level checkpoints\n   - artifact hashes/paths\n   - exit status\n\n2. Debug trace (opt-in, verbose):\n   - tool calls with args\n   - stdout/stderr snippets\n   - expanded inputs\n   - timing details\n\nConsider OpenTelemetry span model as reference.\nGPT proposed this; Gemini focused on rotation/caps instead.","status":"in_progress","priority":3,"issue_type":"task","created_at":"2025-12-23T19:49:48.514684945-05:00","updated_at":"2025-12-23T20:05:23.244193346-05:00"}
 {"id":"skills-u3d","title":"Define skill trigger conditions","description":"How does an agent know WHEN to apply a skill/checklist?\n\nOptions:\n- frontmatter triggers: field with patterns\n- File-based detection\n- Agent judgment from description\n- Beads hooks on state transitions\n- LLM-based pattern detection","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-23T17:59:09.69468767-05:00","updated_at":"2025-12-28T22:25:38.579989006-05:00","closed_at":"2025-12-28T22:25:38.579989006-05:00","close_reason":"Resolved: agent judgment from description is the standard. Good descriptions + 'When to Use' sections are sufficient. No new trigger mechanism needed - would add complexity without clear benefit."}
--- a/skills/playwright-visit/README.md
+++ b/skills/playwright-visit/README.md
@ -0,0 +1,62 @@
+# playwright-visit
+
+Browser automation using Playwright for visiting web pages, taking screenshots, and extracting content.
+
+## Overview
+
+Uses headless Chromium to render pages (including JavaScript) and extract content. Useful for:
+- Screenshots of web pages for visual analysis
+- Extracting text from JS-heavy sites (where WebFetch fails)
+- Getting rendered HTML after JavaScript execution
+- Saving pages as PDF
+
+## Prerequisites
+
+- NixOS with system chromium (`/run/current-system/sw/bin/chromium`)
+- Playwright Python package (provided via flake.nix)
+
+## Setup
+
+```bash
+cd ~/.claude/skills/playwright-visit
+nix develop
+```
+
+## Usage
+
+```bash
+# Screenshot
+./scripts/visit.py screenshot "https://example.com" /tmp/shot.png
+./scripts/visit.py screenshot "https://example.com" /tmp/full.png --full-page
+
+# Extract text
+./scripts/visit.py text "https://example.com"
+
+# Get rendered HTML
+./scripts/visit.py html "https://example.com"
+
+# Save as PDF
+./scripts/visit.py pdf "https://example.com" /tmp/page.pdf
+
+# Wait longer for slow pages (default: 1000ms)
+./scripts/visit.py screenshot "https://slow-site.com" /tmp/shot.png --wait 3000
+```
+
+## How It Works
+
+1. Launches headless Chromium using system binary
+2. Creates fresh browser profile (no cookies/logins)
+3. Navigates to URL and waits for network idle
+4. Extracts requested content
+5. Closes browser
+
+## Limitations
+
+- No authentication support (fresh profile each run)
+- Requires NixOS with system chromium
+- Headless only (no visible browser window)
+
+## See Also
+
+- **WebFetch**: For simple HTTP fetches (faster, no browser)
+- **niri-window-capture**: For capturing local application windows
--- a/skills/playwright-visit/SKILL.md
+++ b/skills/playwright-visit/SKILL.md
@ -0,0 +1,63 @@
+---
+name: playwright-visit
+description: Visit web pages using Playwright browser automation. Capture screenshots, extract text, get rendered HTML, or save as PDF.
+---
+
+# Playwright Visit
+
+Browser automation skill using Playwright to visit web pages and extract content. Uses headless Chromium with a fresh profile (no cookies/history from user's browser).
+
+## When to Use
+
+- "Take a screenshot of [url]"
+- "Get the text content from [webpage]"
+- "Capture [url] as a screenshot"
+- "Extract the rendered HTML from [page]"
+- "Save [url] as a PDF"
+- When WebFetch fails on JavaScript-heavy sites
+
+## Process
+
+1. Identify the URL and desired output format from user request
+2. Run the appropriate helper script command
+3. Return the result (file path for screenshot/pdf, content for text/html)
+
+## Helper Scripts
+
+### visit.py
+
+**Screenshot** - Capture page as PNG:
+```bash
+./scripts/visit.py screenshot "https://example.com" /tmp/screenshot.png
+```
+
+**Text** - Extract visible text content:
+```bash
+./scripts/visit.py text "https://example.com"
+```
+
+**HTML** - Get rendered HTML (after JavaScript):
+```bash
+./scripts/visit.py html "https://example.com"
+```
+
+**PDF** - Save page as PDF:
+```bash
+./scripts/visit.py pdf "https://example.com" /tmp/page.pdf
+```
+
+**Options:**
+- `--wait <ms>` - Wait after page load (default: 1000ms)
+- `--full-page` - Capture full scrollable page (screenshot only)
+
+## Requirements
+
+- NixOS with `python312Packages.playwright` in devShell
+- System chromium at `/run/current-system/sw/bin/chromium`
+- Run from skill directory or use `nix develop` first
+
+## Notes
+
+- Uses fresh browser profile each run (no login state)
+- Headless by default
+- For authenticated pages, consider using `storage_state` parameter (not yet implemented)
--- a/skills/playwright-visit/flake.lock
+++ b/skills/playwright-visit/flake.lock
@ -0,0 +1,61 @@
+{
+  "nodes": {
+    "flake-utils": {
+      "inputs": {
+        "systems": "systems"
+      },
+      "locked": {
+        "lastModified": 1731533236,
+        "narHash": "sha256-l0KFg5HjrsfsO/JpG+r7fRrqm12kzFHyUHqHCVpMMbI=",
+        "owner": "numtide",
+        "repo": "flake-utils",
+        "rev": "11707dc2f618dd54ca8739b309ec4fc024de578b",
+        "type": "github"
+      },
+      "original": {
+        "owner": "numtide",
+        "repo": "flake-utils",
+        "type": "github"
+      }
+    },
+    "nixpkgs": {
+      "locked": {
+        "lastModified": 1766902085,
+        "narHash": "sha256-coBu0ONtFzlwwVBzmjacUQwj3G+lybcZ1oeNSQkgC0M=",
+        "owner": "NixOS",
+        "repo": "nixpkgs",
+        "rev": "c0b0e0fddf73fd517c3471e546c0df87a42d53f4",
+        "type": "github"
+      },
+      "original": {
+        "owner": "NixOS",
+        "ref": "nixos-unstable",
+        "repo": "nixpkgs",
+        "type": "github"
+      }
+    },
+    "root": {
+      "inputs": {
+        "flake-utils": "flake-utils",
+        "nixpkgs": "nixpkgs"
+      }
+    },
+    "systems": {
+      "locked": {
+        "lastModified": 1681028828,
+        "narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
+        "owner": "nix-systems",
+        "repo": "default",
+        "rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nix-systems",
+        "repo": "default",
+        "type": "github"
+      }
+    }
+  },
+  "root": "root",
+  "version": 7
+}
--- a/skills/playwright-visit/flake.nix
+++ b/skills/playwright-visit/flake.nix
@ -0,0 +1,30 @@
+{
+  description = "Playwright browser automation skill";
+
+  inputs = {
+    nixpkgs.url = "github:NixOS/nixpkgs/nixos-unstable";
+    flake-utils.url = "github:numtide/flake-utils";
+  };
+
+  outputs = { self, nixpkgs, flake-utils }:
+    flake-utils.lib.eachDefaultSystem (system:
+      let
+        pkgs = nixpkgs.legacyPackages.${system};
+        python = pkgs.python312;
+      in
+      {
+        devShells.default = pkgs.mkShell {
+          buildInputs = [
+            (python.withPackages (ps: [
+              ps.playwright
+            ]))
+          ];
+
+          shellHook = ''
+            echo "Playwright skill environment ready"
+            echo "Run: ./scripts/visit.py --help"
+          '';
+        };
+      }
+    );
+}
--- a/skills/playwright-visit/scripts/visit.py
+++ b/skills/playwright-visit/scripts/visit.py
@ -0,0 +1,121 @@
+#!/usr/bin/env python3
+"""Browser automation CLI using Playwright."""
+
+import argparse
+import sys
+from pathlib import Path
+
+from playwright.sync_api import sync_playwright
+
+CHROMIUM_PATH = "/run/current-system/sw/bin/chromium"
+
+
+def get_browser(playwright):
+    """Launch headless chromium using system binary."""
+    return playwright.chromium.launch(
+        executable_path=CHROMIUM_PATH,
+        headless=True,
+    )
+
+
+def cmd_screenshot(args):
+    """Capture page as PNG screenshot."""
+    with sync_playwright() as p:
+        browser = get_browser(p)
+        page = browser.new_page()
+        page.goto(args.url, wait_until="networkidle")
+        page.wait_for_timeout(args.wait)
+        page.screenshot(path=args.output, full_page=args.full_page)
+        browser.close()
+    print(args.output)
+
+
+def cmd_text(args):
+    """Extract visible text content from page."""
+    with sync_playwright() as p:
+        browser = get_browser(p)
+        page = browser.new_page()
+        page.goto(args.url, wait_until="networkidle")
+        page.wait_for_timeout(args.wait)
+        text = page.inner_text("body")
+        browser.close()
+    print(text)
+
+
+def cmd_html(args):
+    """Get rendered HTML after JavaScript execution."""
+    with sync_playwright() as p:
+        browser = get_browser(p)
+        page = browser.new_page()
+        page.goto(args.url, wait_until="networkidle")
+        page.wait_for_timeout(args.wait)
+        html = page.content()
+        browser.close()
+    print(html)
+
+
+def cmd_pdf(args):
+    """Save page as PDF."""
+    with sync_playwright() as p:
+        browser = get_browser(p)
+        page = browser.new_page()
+        page.goto(args.url, wait_until="networkidle")
+        page.wait_for_timeout(args.wait)
+        page.pdf(path=args.output)
+        browser.close()
+    print(args.output)
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Visit web pages using Playwright browser automation"
+    )
+    subparsers = parser.add_subparsers(dest="command", required=True)
+
+    # Screenshot command
+    p_screenshot = subparsers.add_parser("screenshot", help="Capture page as PNG")
+    p_screenshot.add_argument("url", help="URL to visit")
+    p_screenshot.add_argument("output", help="Output PNG path")
+    p_screenshot.add_argument(
+        "--wait", type=int, default=1000, help="Wait after load (ms)"
+    )
+    p_screenshot.add_argument(
+        "--full-page", action="store_true", help="Capture full scrollable page"
+    )
+    p_screenshot.set_defaults(func=cmd_screenshot)
+
+    # Text command
+    p_text = subparsers.add_parser("text", help="Extract visible text content")
+    p_text.add_argument("url", help="URL to visit")
+    p_text.add_argument("--wait", type=int, default=1000, help="Wait after load (ms)")
+    p_text.set_defaults(func=cmd_text)
+
+    # HTML command
+    p_html = subparsers.add_parser("html", help="Get rendered HTML")
+    p_html.add_argument("url", help="URL to visit")
+    p_html.add_argument("--wait", type=int, default=1000, help="Wait after load (ms)")
+    p_html.set_defaults(func=cmd_html)
+
+    # PDF command
+    p_pdf = subparsers.add_parser("pdf", help="Save page as PDF")
+    p_pdf.add_argument("url", help="URL to visit")
+    p_pdf.add_argument("output", help="Output PDF path")
+    p_pdf.add_argument("--wait", type=int, default=1000, help="Wait after load (ms)")
+    p_pdf.set_defaults(func=cmd_pdf)
+
+    args = parser.parse_args()
+
+    # Check chromium exists
+    if not Path(CHROMIUM_PATH).exists():
+        print(f"Error: Chromium not found at {CHROMIUM_PATH}", file=sys.stderr)
+        sys.exit(1)
+
+    try:
+        args.func(args)
+    except Exception as e:
+        print(f"Error: {e}", file=sys.stderr)
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()