The Agent Skills specification requires only SKILL.md. In the commit-crafter tutorial, everything countable moves into scripts/check_message.py, tested with Python's standard library and no API key.
Reality
- Evidence58
- Adoption
- Insufficient
- Hype gap−6
- Incentives28
- Confidence60
A dev.to walkthrough puts commit signing, commitlint, Gitleaks and OWASP SAST into Husky hooks, then runs commitlint again in GitHub Actions because any developer can skip the local hooks with --no-verify.
Reality
- Evidence50
- Adoption
- Insufficient
- Hype gap+12
- Incentives25
- Confidence55
A commit-crafter tutorial splits judgment from enforcement the right way, but only message formatting makes it inside the deterministic check. The approval gate stays a sentence the model can reinterpret.
Reality
- Evidence58
- Adoption
- Insufficient
- Hype gap+22
- Incentives38
- Confidence52
A zero-budget git-to-Markdown pipeline works because a deterministic fallback runs when the free model tier says no. The interesting part is what the degraded output costs.
Reality
- Evidence58
- Adoption8
- Hype gap+22
- Incentives76
- Confidence55
A developer avoided API-key coupling by shelling out to the Claude CLI. The default output format returns text only, so months of per-commit model calls left no usage record at all.
Reality
- Evidence56
- Adoption12
- Hype gap+18
- Incentives32
- Confidence44