- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
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.
01Result
microsoft/skill-recorder ↗microsoft/skill-recorder AI coding statistics: 82.9%
A small group is using agents. Adoption has spread beyond one person but is not project-wide.
02Drivers
What shapes this result
Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.
Assisted or autonomous
Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached.
Agent share by month
| Month | Agent share | Considered commits |
|---|---|---|
| 2026-07 | 85.1% | 87 |
| 2026-08 | 76.2% | 21 |
| 2026-09 | 66.7% | 3 |
Peak month: 85.1%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| GitHub Copilot | GitHub | 92 | 82.9% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
6578f750on GitHubRelease Skill Recorder 0.6.0GitHub Copilot744c70e4on GitHubImprove Copilot sign-in routing and resume interrupted analysisGitHub Copilot68ced22eon GitHubfeat: add screen selection for recordingsGitHub Copilot
04Method
What entered the denominator
The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.
Exclusion ledger
| Commits in window | 147 |
| Merge commits removed | −34 |
| CI / dependency bots removed | −2 |
| Considered | 111 |
Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.
Continue exploring
Related coding-agent evidence
Run the same detector locally.
Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.
npx qmmit-cli microsoft/skill-recorder