Index of every page on this site: llms.txt
All skills
segmently-ai avatar

/playwright-bowser-core

@f3f9f19
Run it yourself

Portable browser automation core for public playwright-cli setup, sessions, screenshots, custom code, storage, traces, and videos.

  • 5 files
  • 5.2 KB
  • Updated 5 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/segmently-ai/segmently-support-plugins/playwright-bowser-core

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈39 tokens for metadata: the name and description. ≈507 when used: this file. ≈779 more on demand in 4 files.

Description uses 1.9% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈155 characters, or 1.9%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Playwright Bowser Core

Use this skill as the shared browser automation base for Segmently support plugins. It documents public playwright-cli behavior only. It does not contain Segmently maintainer runbooks, repository routes, local stack assumptions, or private selectors.

Preflight

Check Node/npm/npx before browser setup; Playwright CLI and its fallback browser installer depend on them:

node --version
npm --version
npx --version

Use Node.js 20 LTS or newer. If any command is missing, ask the customer to install Node.js and reopen the terminal before continuing.

Check the browser tool before any live browser work:

playwright-cli --help

If it is missing and the environment allows installs:

npm install -g @playwright/cli@latest
playwright-cli install-browser

If the browser install command is unavailable, use:

npx playwright install chromium

If Chromium still cannot launch on Linux, use:

npx playwright install --with-deps chromium

Session Pattern

Use a named persistent session for user-facing walkthroughs:

PLAYWRIGHT_MCP_VIEWPORT_SIZE=1440x900 playwright-cli -s=segmently-show open https://app.segmently.ai --persistent
playwright-cli -s=segmently-show snapshot
playwright-cli -s=segmently-show screenshot --filename=segmently-show.png

Use run-code for known scripted actions and snapshot for discovery. Capture a screenshot when visual evidence helps the user.

Safety

  • Do not print credentials, cookies, browser storage secrets, or auth files.
  • Do not run mutation scripts unless the owning skill supplies an explicit action contract and the user confirms the target.
  • Report setup or auth blockers as setup blockers, not product failures.
  • Close short-lived sessions when the task is complete.

References

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at f3f9f19. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated 5 months ago

README badge

README badge for segmently-ai/segmently-support-plugins/playwright-bowser-core