dotnet-mcaf-feature-spec

MCAF: Feature Spec

Trigger On

• add or change non-trivial behaviour
• behaviour is under-specified and engineers are guessing
• tests need a stable behavioural source of truth

Value

• produce a concrete project delta: code, docs, config, tests, CI, or review artifact
• reduce ambiguity through explicit planning, verification, and final validation skills
• leave reusable project context so future tasks are faster and safer

Do Not Use For

• architecture decisions that need alternatives and trade-offs
• tiny typo or cosmetic-only changes with no behavioural impact

Inputs

• docs/Architecture.md
• the nearest AGENTS.md
• current user flows, business rules, and acceptance expectations

Quick Start

1. Read the nearest AGENTS.md and confirm scope and constraints.
2. Run this skill's Workflow through the Ralph Loop until outcomes are acceptable.
3. Return the Required Result Format with concrete artifacts and verification evidence.

Workflow

1. Define scope first: in scope, out of scope, boundaries touched.
2. If the feature doc is missing, scaffold from references/feature-template.md.
3. Keep the spec executable:
   • numbered rules
   • main flow
   • edge and failure flows
   • system behaviour
   • verification steps
   • Definition of Done
4. Make the spec concrete enough that tests can be written without guessing.
5. If the feature creates a new dependency, boundary, or major policy shift, update an ADR too.

Deliver

• docs/Features/feature-name.md
• a feature spec that engineers and agents can implement directly

Validate

• rules are testable, not aspirational
• edge cases are captured where they matter
• verification steps match the intended behaviour
• the doc can drive implementation without hidden tribal knowledge

Ralph Loop

Use the Ralph Loop for every task, including docs, architecture, testing, and tooling work.

1. Brainstorm first (mandatory):
   • analyze current state
   • define the problem, target outcome, constraints, and risks
   • generate options and think through trade-offs before committing
   • capture the recommended direction and open questions
2. Plan second (mandatory):
   • write a detailed execution plan from the chosen direction
   • list final validation skills to run at the end, with order and reason
3. Execute one planned step and produce a concrete delta.
4. Review the result and capture findings with actionable next fixes.
5. Apply fixes in small batches and rerun the relevant checks or review steps.
6. Update the plan after each iteration.
7. Repeat until outcomes are acceptable or only explicit exceptions remain.
8. If a dependency is missing, bootstrap it or return status: not_applicable with explicit reason and fallback path.