Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Apply minimal MCAF repository governance when the user explicitly asks to adopt MCAF or change MCAF-specific rules. USE FOR: creating or tightening root and local AGENTS.md policy; placing durable engineering context; defining the repository's own verification contract. DO NOT USE FOR: ordinary .NET implementation, documentation edits, UI/UX, testing, CI, Git, NFR, developer-experience, or ML work unless the request is specifically about MCAF governance. INVOKES: inspect repository policy and do
.claude/skills/managedcode-mcaf/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | -47% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -42% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -48% | 0% |
| case-17 | ✗→✓ | ▲ Improved | -54% | 0% |
| case-18 | ✗→✓ | ▲ Improved | -21% | 0% |
Keep MCAF as one opt-in governance layer. Do not create parallel mcaf-* implementation or process skills.
AGENTS.md and the nearest local AGENTS.md, if one exists.AGENTS.md only when a subtree genuinely differs.AGENTS.md.dotnet or the narrow framework skill.Read references/adoption.md only when bootstrapping MCAF in a repository.
Other measured skills in the registry, with their headline benchmark lift.