Playwright interactive: persistent js_repl browser sessions for UI debugging
Debug local web or Electron apps with a persistent Playwright js_repl session — short pointer
- What
- Debug local web or Electron apps with a persistent Playwright js_repl session — short pointer
- Cost
- Free
- Needs
- the Codex agent runtime with js_repl enabled (~/.codex/config.toml) and sandboxing disabled (--sandbox danger-full-access) — understand that trade-off before starting; a local web or Electron project to debug; no license declared in the source repo — read it yourself before reusing its content
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — ⚠️ Security warning — this skill requires Codex with sandboxing DISABLED (`--sandbox danger-full-access`) and the `js_repl` feature enabled; only use it in a workspace you fully trust, and understand the trade-off before you start. A short pointer to @openai's playwright-interactive workflow: keep one persistent Playwright session alive across iterations to debug local web or Electron apps — write a QA inventory from the requirements and implemented behaviors first, run the bootstrap cell once, keep reusing the same handles for renderer reloads and app relaunches, run functional QA with normal user input plus a separate visual QA pass, capture screenshot evidence for every signed-off claim, and reset the kernel only as a recovery tool. Honest caveats: no license declared in the repository — license unknown, so this is a short fiche linking to the source, without reusing its content; built for the Codex agent runtime (`js_repl` in `~/.codex/config.toml`), not generic agents. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Playwright interactive is a free Muse skill and short pointer for debugging local web or Electron apps with one persistent Playwright js_repl session kept alive across iterations. Security warning: it requires Codex with sandboxing disabled and the js_repl feature enabled, so use it only in a workspace you fully trust, understanding the trade-off before you start.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 49f948fStep 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: the Codex agent runtime with js_repl enabled (~/.codex/config.toml) and sandboxing disabled (--sandbox danger-full-access) — understand that trade-off before starting; a local web or Electron project to debug; no license declared in the source repo — read it yourself before reusing its content Install "Playwright interactive: persistent js_repl browser sessions for UI debugging" for me. Fetch the SKILL.md from the source repository into a temporary folder, review it for anything suspicious, and report in two or three sentences what the playwright-interactive workflow covers (persistent js_repl Playwright session, QA inventory, bootstrap cell, functional plus visual QA, screenshot evidence) so I can follow it in my own Codex workspace. Do not copy the workflow's content into my project — this is a reference lookup only. Repository: https://raw.githubusercontent.com/openai/skills/49f948faa9258a0c61caceaf225e179651397431/skills/.curated/playwright-interactive/SKILL.md Pinned version: install the code at commit 49f948faa9258a0c61caceaf225e179651397431 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Rules: don't touch anything outside the temp folder. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
- It can create or modify files.
What the scan found — excerpts from the install prompt
- writes files — Prerequisites: the Codex agent runtime with js_repl enabled (~/.codex/config.toml) and sandboxing disabled (-- · Prérequis : le runtime d'agent Codex avec js_repl activé (~/.codex/config.toml) et sandboxing désactivé (--san
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 49f948f · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : writes files
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.