agentleFS
Postpartum-genushyacinthus29Postpartum-genushyacinthus29/dotnet-skills/skills/dotnet-mcaf/SKILL.md

dotnet-mcaf

Skill13 starsChanged 8 months agoMITView on GitHub

Adopt MCAF governance in a .NET repository with the right AGENTS.md layout, repo-native docs, skill installation, verification rules, and non-trivial task workflow. Use when bootstrapping or updating MCAF alongside the dotnet-skills catalog.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Start from the canonical bootstrap surface:

    line 20
  2. Distinctive:

    Place root AGENTS.md at the repository or solution root.

    line 24
  3. Distinctive:

    Add project-local AGENTS.md only when the solution has multiple projects with genuinely different local rules.

    line 25
  4. Distinctive:

    Treat verification as part of done: tests, analyzers, formatters, coverage, and any architecture or security gates the repo configured.

    line 52

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

MCAF Adoption

Trigger On

  • bootstrapping MCAF in a new or existing repository that also contains .NET work
  • updating root or project-local AGENTS.md files to follow a durable repo workflow
  • deciding which MCAF governance skills and dotnet-* implementation skills to install together
  • organizing repo-native docs for architecture, features, ADRs, testing, development, and operations

Workflow

  1. Start from the canonical bootstrap surface:
    • tutorial: https://mcaf.managed-code.com/tutorial
    • concepts: https://mcaf.managed-code.com/
    • public MCAF skills: https://mcaf.managed-code.com/skills
  2. Place root AGENTS.md at the repository or solution root.
  3. Add project-local AGENTS.md only when the solution has multiple projects with genuinely different local rules.
  4. Install MCAF governance skills (dotnet-mcaf-*) for process areas and dotnet-* implementation skills for framework work. Check references/skill-map.md for overlap before adding duplicate surfaces.
  5. Route to the narrowest MCAF skill once the governance concern is clear:

    ConcernSkill
    Delivery workflow and feedback loopsdotnet-mcaf-agile-delivery
    Developer onboarding and local inner loopdotnet-mcaf-devex
    Durable docs structure and source-of-truth placementdotnet-mcaf-documentation
    Executable feature behaviour docsdotnet-mcaf-feature-spec
    Human review for large AI-generated dropsdotnet-mcaf-human-review-planning
    ML/AI product delivery processdotnet-mcaf-ml-ai-delivery
    Explicit quality attributes and trade-offsdotnet-mcaf-nfr
    Branch, merge, and release hygienedotnet-mcaf-source-control
    Design-system, accessibility, front-end directiondotnet-mcaf-ui-ux
  6. Scaffold repo-native documentation:
    docs/
    ├── Architecture.md
    ├── Features/
    ├── ADR/
    ├── Testing/
    ├── Development/
    └── Operations/
  7. Encode the non-trivial task flow in AGENTS.md: <slug>.brainstorm.md then <slug>.plan.md then implementation and validation.
  8. Treat verification as part of done: tests, analyzers, formatters, coverage, and any architecture or security gates the repo configured.
flowchart LR
  A["Adopt MCAF"] --> B["Root AGENTS.md"]
  B --> C{"Multi-project?"}
  C -->|Yes| D["Project-local AGENTS.md"]
  C -->|No| E["Root policy only"]
  B --> F["Install mcaf-* governance skills"]
  B --> G["Install dotnet-* implementation skills"]
  D --> H["Document boundaries and commands"]
  E --> H
  F --> I["Repo-native docs scaffolds"]
  G --> J[".NET implementation guidance"]
  H --> K["Run full quality pass"]
  I --> K
  J --> K

Deliver

  • repository-ready MCAF adoption with clear root and local AGENTS.md responsibilities
  • correct split between mcaf-* governance and dotnet-* implementation skills
  • repo-native docs and verification expectations instead of chat-only instructions

Validate

  • root AGENTS.md exists at the repository or solution root
  • project-local AGENTS.md files exist only where genuinely needed
  • repo documents exact build, test, format, analyze, and coverage commands
  • durable docs exist for architecture and behavior, not only inline comments
  • non-trivial work follows the brainstorm-to-plan flow before implementation
  • the full quality pass is part of done, not only a narrow happy-path test run

References

  • references/adoption.md - canonical MCAF entry points, bootstrap rules, and the local-mirror boundary between governance and implementation skills
  • references/skill-map.md - MCAF catalog map with overlap-vs-new split for precise routing

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.