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
SkillScore77Maintained
Automatic
◆AI Engineer pack
Last verified 8/19/2026
What it changes
Passed 16 of 21 test cases with the skill, and 11 of 21 without it.
Without skill50%
With skill77%
Checks it passed that the model alone missed
The response forbids duplicating testing skills under an MCAF namespace.
The response references references/adoption.md for initial bootstrapping.
The response directs using standard dotnet tools or narrow framework skills instead.
and 5 more in the full report
7 fixed10 passed either way4 still failing1 broke
Pass-rate lift
+27 pp
Tokens
-34%
Agent turns
0%
Response time
-60%
Model gemini-3.6-flashMeasured 8/19/2026v117 of 22 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 7
Prompt
A contributor asks to restructure project documentation files without mentioning governance frameworks. What is the first workflow step before applying MCAF changes?
What was checked, without and with the skill
Checked
Without skill
With skill
The response requires confirming the request explicitly concerns MCAF adoption or governance changes.
Missed
Passed
case-19 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md47 lines2 files
MCAF Governance
Keep MCAF as one opt-in governance layer. Do not create parallel mcaf-* implementation or process skills.
Workflow
Confirm that the request is explicitly about adopting MCAF or changing MCAF governance.
Read the root AGENTS.md and the nearest local AGENTS.md, if one exists.
Keep only durable repository rules that future contributors and agents must know.
Put each rule next to the area that owns it. Add a local AGENTS.md only when a subtree genuinely differs.
Record exact build, test, format, analysis, and operational commands when the repository depends on them.
Route implementation work to the normal catalog skill closest to the actual technology or behavior.
Validate the changed policy, documentation links, and repository commands.
Minimal Rules
Keep one root AGENTS.md.
Add local policy only for real local differences; local rules may tighten but not silently weaken root rules.
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 require brainstorm or plan files for every non-trivial task unless the repository explicitly adopts that workflow.
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
Run and debug C# MCP servers locally. Covers IDE configuration, MCP Inspector testing, GitHub Copilot Agent Mode integration, logging setup, and troubleshooting. USE FOR: running MCP servers locally with dotnet run, configuring VS Code or Visual Studio for MCP debugging, testing tools with MCP Inspector, testing with GitHub Copilot Agent Mode, diagnosing tool registration issues, setting up mcp.json configuration, debugging MCP protocol messages, configuring logging for stdio and HTTP servers. D