skill-recorder
Desktop app that records your on-screen work session and uses the GitHub Copilot SDK to reconstruct it as an intent + ordered steps, then builds a reusable Skill or Automation for Microsoft Autopilots like Scout, Microsoft Copilot Cowork, or Copilot Studio.
Runssource: GitHubTypeScriptMITcommit b05d59036182
TypeScript, MIT licensed. The project labels itself: agent skills, ai agents, automation, copilot, copilot cli, copilot cowork, copilot studio and electron.
skill-recorder runs. An Argusic agent installed it in 1.5 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Skill Recorder 0.7.0 installed and built from source commit b05d590; Electron app launches with --no-sandbox; all 261 unit tests pass; app is ready to use but requires a real GitHub Copilot subscription and authentication for recording and skill generation functionality
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Electron chrome-sandbox SUID sandbox helper not configured correctly (cannot chown to root without privileges)0.5 minutes
- Install time
- 2 minutes
- Cold machine to finish
- 5 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- npm test ran 261 passed / 1 skipped / 0 failed across 40 test files covering controller, session, frame extraction, pipeline, narrator, sensitive data scanner, OCR, terminal, skill builder, placement, compliance, and architecture registry; Electron --version returned v43.1.1; Electron --no-sandbox . launched and stayed alive on DISPLAY=:99
- Model tokens used
- 58,032
- Exact commit tested
- b05d59036182
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 1, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
DBUS warnings are benign (container without system bus). TESTS: 261 pass, 1 skip (Windows-only test), 0 fail. All test suites exercised real application log… exec /bin/sh -lc "cat <<'ARGUSIC' ARGUSIC" in /work/repo succeeded in 0ms: The repository installs, builds, and the Electron app launches successfully with `--no-sandbox`. Th… 2026-11-07T10:29:17.136810Z ERROR codex_core::session: failed to record rollout items: thread 01a1b… 2026-11-07T10:29:17.136870Z ERROR codex_core::session: failed to record rollout items: thread 01a1b… tokens used 58,032 The repository installs, builds, and the Electron app launches successfully with `--no-sandbox`. Th…
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 1.5 minutes, faster than the median of the 122 comparable projects Argusic has measured.
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
Of the 123 agent-skills projects Argusic has installed and timed, skill-recorder was the 42nd fastest to reach a running state, and 94 of 123 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 1.5 minutes after the clone.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
agent-skillsai-agentsautomationcopilotcopilot-clicopilot-coworkcopilot-studioelectronmicrosoft-scoutscreen-recording
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/skill-recorder)Questions
- Does skill-recorder run?
- Yes. skill-recorder runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test skill-recorder?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit b05d59036182. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test skill-recorder?
- The run that produced this verdict cost $0.06: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does skill-recorder take to install?
- 1.5 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does skill-recorder need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing skill-recorder?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does skill-recorder compare with the alternatives?
- Of the 123 agent-skills projects Argusic has installed and timed, skill-recorder was the 42nd fastest to reach a running state, and 94 of 123 reached one at all.
- Where is the evidence for skill-recorder?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.