Borrowing it
Nothing to install: this file belongs to ThePatriczek/playwright-recast. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ThePatriczek/playwright-recast/main/.claude/playwright-recast/skills/studio-workflow/SKILL.mdgit clone --depth 1 https://github.com/ThePatriczek/playwright-recastWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/thepatriczek/playwright-recast/studio-workflow)<a href="https://agentmods.dev/skills/thepatriczek/playwright-recast/studio-workflow"><img src="https://agentmods.dev/badge/skills/thepatriczek/playwright-recast/studio-workflow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/thepatriczek/playwright-recast/studio-workflow"><img src="https://agentmods.dev/badge/skills/thepatriczek/playwright-recast/studio-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 22 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00076 | $0.01819 |
| Opus 5 | $0.00038 | $0.00910 |
| Sonnet 5 | $0.00015 | $0.00364 |
| Haiku 4.5 | $0.00008 | $0.00182 |
Grade A, and why
studio-workflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Studio Workflow
Generate a demo video from a raw Playwright trace recorded by recast-studio.
When to Use
- User recorded a session with
recast-studioand wants to generate a video - User says "generate video from trace", "process my recording", "make a demo from this trace"
- User points to a directory with
trace.zipand.webmfiles
Input
A directory path containing:
trace.zip— Playwright trace*.webm— screen recording
Produced by: npx recast-studio <url>
Workflow
Execute these steps in order. Each step produces artifacts the next step needs.
Step 1: Parse the trace
Read the trace directory and parse trace.zip to extract all actions. Use the playwright-recast parseTrace function:
const { parseTrace } = await import('<recast-root>/src/parse/trace-parser.js')
const trace = await parseTrace('<input-dir>/trace.zip')
List all actions with their index, method, selector/URL, value, and timestamp. Mask any values from password-like selectors (containing "password", "passwd", "pwd", "secret").
Present the action list to yourself for analysis.
Step 2: Analyze and group actions
Group the actions into logical steps. For each step, decide:
Hidden steps — setup that should not appear in the video:
- Navigation to the starting URL (
goto) - Login flows (fill username + fill password + click submit)
- Cookie consent, onboarding dialogs
- Any action the viewer doesn't need to see
Visible steps — the actual demo content:
- The core user journey being demonstrated
- Each visible step groups 1-3 related actions (e.g., click input + fill value = one step)
Track which action indices belong to each step and whether it's hidden.
Step 3: Write voiceover
For each visible step, write 1-2 sentences of voiceover text. Follow the script-writer skill guidelines:
- Narrative arc — always follow: Hook (problem) → Solution/Walkthrough → Result
- Marketing tone — benefit-focused, professional, concise
- Language — infer from the UI language, user's instructions, or conversation context
- Never describe mechanical clicks — describe what the user ACHIEVES
- Never mention credentials or passwords
- Each sentence should be natural for TTS (ElevenLabs)
- First visible step = hook (name the problem being solved)
- Middle steps = solution/walkthrough (what each action achieves for the user)
- Last visible step = result + soft CTA
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 200 lines · 76 tokens per session scan A c3cfca739a8b
studio-workflow is a skill published in the GitHub repository ThePatriczek/playwright-recast (58 stars, last pushed 9d ago), licensed MIT. It adds 76 tokens to every session and 1,819 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
feature-demo-recording
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…
browser-video-recording
Create polished 60 fps 4:3 4K browser screen-recording style videos from Codex in-app browser captures, with browser-only crop, natural macOS cursor styling, deliberate click choreography, zoom-follow framing, ffprobe/thumbnail verification, and optional native recording compatibility checks. Use when the user asks to…
html-to-video-pipeline
Reliable HTML-to-MP4 rendering via headless browser recording (Playwright/Puppeteer) + ffmpeg — the ordering, gotchas, and verification steps you MUST get right or the output silently rots. Trigger whenever the user is building or debugging any pipeline that turns an HTML/CSS/JS page (single-file, multi-composition…
record-video
Record and upload a short browser interaction video artifact.
playwright-recording
Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.
playwright-recording
Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.