Add explicit guidance to use playwriter first for JS-rendered websites and blocking overlays, based on repeated failures where webfetch/curl returned empty shells and screenshots were used too early.
Key updates:\n- Add a hard 'when to use playwriter vs webfetch/curl' rule in the main skill docs\n- Add a 'snapshot before screenshot' rule to prevent slow image-first debugging loops\n- Add a concrete anti-pattern for JS-rendered sites in common mistakes\n- Add obstacle-handling flow for cookie/login/age-gate overlays\n- Add media extraction/download pattern using evaluate + Node fetch/fs\n- Update skill frontmatter description (and well-known discovery copies) so context-loaded summaries also include the JS-heavy-site rule
Clarify in the skill frontmatter that playwriter should be used over
other Playwright MCPs since it connects to the user's existing Chrome
instead of launching a new browser instance.
- Move skills/playwriter/SKILL.md to playwriter/src/skill.md (source of truth)
- Add 'playwriter skill' CLI command to output full docs
- Make skills/playwriter/SKILL.md a lightweight stub pointing to CLI
- Generate prompt.md to dist/ instead of src/
- Strip CLI-only content from MCP prompt
- Replace cac with @xmorse/cac for space-separated commands
- Add 'playwriter session new' to get new session ID
- Add 'playwriter session list' to show sessions and state keys
- Add 'playwriter session reset <id>' to reset a session
- Update SKILL.md with new CLI docs and multiline examples
- Put -s flag before -e in all examples
Tommy D. Rossi