Mcaf logo

Mcaf

Organization
managedcode
mcaf

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 documentation, make the smallest durable governance change, then validate the affected repository surfaces.

Overview

Publishermanagedcode
Repositorydotnet-skills
Skill namemcaf
Stars
492
Forks
38
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by managedcode on GitHub. Read the source before you install it.

Installation

Install the Mcaf AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/managedcode/dotnet-skills/tree/main/catalog/Platform/MCAF/skills/mcaf
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/managedcode/dotnet-skills.git /tmp/dotnet-skills
mkdir -p .claude/skills
cp -r /tmp/dotnet-skills/catalog/Platform/MCAF/skills/mcaf .claude/skills/mcaf
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mcaf in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Mcaf on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Mcaf is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

MCAF Governance

Keep MCAF as one opt-in governance layer. Do not create parallel mcaf-* implementation or process skills.

Workflow

  1. Confirm that the request is explicitly about adopting MCAF or changing MCAF governance.
  2. Read the root AGENTS.md and every affected local AGENTS.md completely before editing any of them.
  3. Keep only durable repository rules that future contributors and agents must know.
  4. Put each rule next to the area that owns it. Add a local AGENTS.md only when a subtree genuinely differs.
  5. Record exact build, test, format, analysis, and operational commands when the repository depends on them.
  6. Route implementation work to the normal catalog skill closest to the actual technology or behavior.
  7. Validate the changed policy, documentation links, and repository commands.

MCAF 1.3.68 Policy Contract

When a repository declares that it follows MCAF 1.3, preserve these upstream mandatory policies rather than treating them as optional templates:

  • MCAF-ARCH-001: keep the complete solution in one repository and use one canonical vertical-slice identity across applicable code, tests, infrastructure, and feature documentation.
  • MCAF-GOV-001: merge incoming MCAF guidance into existing root and local AGENTS.md files. Never overwrite, truncate, summarize away, weaken, or silently omit an existing repository rule.
  • MCAF-REQ-001: for non-trivial features, keep stable requirements and acceptance criteria, map them to automated tests or explicit evidence exceptions, and link any required ADR implementation contract.
  • MCAF-AI-001: use a capable planning/integration owner for non-trivial work and keep delegated scopes bounded, independently verified, and joined before completion when the execution environment supports delegation.

Do not inject these policies into a repository that has not chosen MCAF. When updating an existing MCAF repository, preserve any stricter local rule and report a genuine conflict instead of weakening it.

Minimal Rules

  • Keep one root AGENTS.md.
  • In a multi-project MCAF solution, keep a local AGENTS.md in each project or module root with its entry points, boundaries, commands, applicable skills, and local risks.
  • Keep one source of truth for each durable fact.
  • Describe the current repository, not an intended future state.
  • Make acceptance and verification expectations concrete and runnable.
  • Add feature specifications, ADRs, review plans, or quality constraints only when the task actually needs those artifacts.
  • Turn repeated team pain into a small durable rule; do not encode one-off preferences.

Boundaries

  • Do not use MCAF as a router for normal .NET work; use dotnet or the narrow framework skill.
  • Do not impose generic agile ceremonies, branch naming, UI/UX choices, onboarding templates, NFR catalogs, or ML process.
  • Do not duplicate testing, CI, documentation, security, observability, or architecture skills under an MCAF namespace.
  • Do not invent planning artifacts beyond the repository's adopted MCAF version. Current MCAF 1.3 repositories require brainstorm, acceptance, and plan artifacts for non-trivial work, so preserve that contract when it is already adopted.
  • Do not add process artifacts that are larger than the decision or behavior they clarify.

Deliver

  • the smallest repository-native governance change that resolves the explicit MCAF request
  • direct routing to implementation-focused skills for everything outside governance

Validate

  • every new rule is durable, scoped, and owned by a repository surface
  • no rule duplicates a normal implementation skill
  • referenced commands and paths exist
  • an MCAF 1.3 repository preserves MCAF-ARCH-001, MCAF-GOV-001, MCAF-REQ-001, and MCAF-AI-001 or records an explicit versioned migration state
  • scripts/verify-mandatory-policies.sh passes when the consuming repository has adopted the upstream verifier
  • removed or renamed MCAF surfaces leave no dangling catalog, bundle, watch, or documentation references

Reference

Read references/adoption.md only when bootstrapping MCAF in a repository.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Mcaf AI skill do?

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 documentation, make the smallest durable governance change, then validate the affected repository s...

Why use Mcaf on TypingMind?

Because you install it once and use it with any model. Mcaf is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Mcaf in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/managedcode/dotnet-skills/tree/main/catalog/Platform/MCAF/skills/mcaf. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Mcaf?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Mcaf?

As many as you like. As long as a model supports skills, you can use Mcaf with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Mcaf AI skill free?

Yes. It is published on GitHub by managedcode under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇