- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.
01Result
coreyhaines31/marketingskills ↗coreyhaines31/marketingskills AI coding statistics: 69.9%
One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.
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 |
|---|---|---|
| 2026-02 | 88.1% | 42 |
| 2026-03 | 79.2% | 24 |
| 2026-04 | 58.8% | 51 |
| 2026-05 | 83.3% | 30 |
| 2026-06 | 93.3% | 15 |
| 2026-07 | 58.5% | 53 |
| 2026-08 | 86.3% | 51 |
| 2026-09 | 23.3% | 30 |
Peak month: 93.3%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 206 | 69.6% |
| Cursor Agent | Anysphere | 1 | 0.3% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
5b2c0007on GitHubfeat: ai-seo 2.5.0 — ChatGPT 5.6 format-volatility guidance (#579)Claude Code5cd4a7eaon GitHubfix: ploy category → canonical grid name (#578)Claude Code88de9fd1on GitHubfeat: publish Ploy as a live Skill Partner (Website) (#577)Claude Code93782e4bon GitHubfix(attribution): Google/GA4 model availability and accuracy polishCursor Agent
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 | 474 |
| Merge commits removed | −163 |
| CI / dependency bots removed | −15 |
| Considered | 296 |
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 coreyhaines31/marketingskills