Records reviewable browser videos — a cursor, click ring, and step captions drawn on the page, dead waits cut, H.264 mp4 out, a per-step timings file and contact sheet beside it — for a scripted scene list, a test runner's raw Playwright video, or a Chrome tab driven by another tool (recorded over the DevTools protocol). Triggers on "record this interaction", "screen recording", "make a video of", "/screencast".
94%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
Scripts do the work; this file lists only what differs from a plain Playwright recordVideo + ffmpeg job.
| Script | Use |
|---|---|
scripts/record.mjs <recording.json> | Scripted scenes (caption + click/hover/type/press/scroll/wait steps); schema in the file header. Run from a directory where playwright resolves |
scripts/overlay.js | A test runner's own recording: context.addInitScript({ path }), then window.__rec.step(label) per step |
scripts/finish.mjs <raw.webm>... --out <id>.mp4 | Any raw video(s) + sibling <stem>.timings.json → the outputs below. --crop x,y,w,h, --max-width 768 for video-analyser, --no-trim |
scripts/capture.mjs launch [--port 9222] | disconnect | start --url <part> | step "<label>" | stop --out <id>.mp4 | A Chrome tab another tool drives (claude-in-chrome): streams its frames over the DevTools protocol through a relay that keeps one connection to Chrome, then runs finish.mjs on stop. disconnect closes that connection. launch opens a separate Chrome with a DevTools port, for when remote debugging at chrome://inspect is off. Usage and exit codes in the file header |
node "${CLAUDE_SKILL_DIR}/scripts/finish.mjs" spec-1-1.webm spec-1-2.webm --out .agent/feat-x/.aw-tester/recordings/spec-1.mp4<id>.mp4, <id>.timings.json (steps: [{ label, start, end, result }] in output seconds), and <id>.sheet.png (one frame per step), side by side.
Standalone runs write to .agent/{branch}/recordings/; a caller such as aw-tester keeps its own directory.
<id>.sheet.png before any upload or claim. You cannot watch a video; the sheet is how you check it shows what you say it shows.deviceScaleFactor: a 2x page lands in a corner of the frame. Upscale in ffmpeg if needed.page.screenshot({ style: '#__screencast{display:none!important}' }), so evidence images show only the app.{ label, start, end, result } per step, seconds from newPage(); several launches → pass every segment to finish.mjs in order, and it joins them and offsets their timings.notes line, never a failed check.recordVideo, so record with capture.mjs, never gif_creator: a GIF gets one frame per tool call and is ~20× larger than the mp4.
It needs Chrome's remote debugging on once (chrome://inspect/#remote-debugging), and the user clicks Allow once per Chrome session: the first start prints connecting to Chrome and waits, and later ones reuse the relay's connection. --wait 600 when you start it before asking. Chrome paints only while the page changes and its window is visible, so the video starts at the first frame after start, and stop exits 6 if none came.
Run overlay.js's source with javascript_tool after every navigation and call __rec.step(label) with each capture.mjs step, or the video has no captions.
Exit 6 (no debugging, no matching tab, no frames) → fall back to gif_creator, convert the GIF (ffmpeg -i x.gif -movflags +faststart -vf "scale=1280:-2,format=yuv420p" -c:v libx264 -crf 28 -an x.mp4), and add a notes line.--narrate): each step's say line, spoken with macOS say or SCREENCAST_TTS="<cmd with {text} and {out}>". Never by default — reviewers watch muted.Exit codes: 2 bad arguments, 3 ffmpeg missing, encoding failed, or the mp4 failed its sanity check, 4 playwright does not resolve, 5 --narrate with no voice, 6 capture.mjs found no DevTools endpoint, tab, or frames.
mthines/agent-skills
d444d53
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.