dotPilot: Skill for Codex

MCAF: Non-Functional Requirements

Trigger On

• a feature or architecture change needs explicit quality attributes
• a team is using vague words like "fast", "reliable", or "secure" without measurable meaning
• docs, ADRs, and tests are out of sync on quality expectations

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

• generic architecture or feature writing with no quality-attribute decision
• loading all NFR references at once

Inputs

• the changed feature, boundary, or rollout path
• the quality attributes that materially affect it
• current docs, ADRs, tests, and ops 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. Decide which quality attributes materially affect the change.
2. Turn vague goals into explicit requirements, constraints, or testable expectations.
3. Link NFRs to feature docs, ADRs, and verification when they affect design or rollout.
4. Use only the specific reference files that match the active quality attribute.

Deliver

• explicit NFRs for the changed area
• docs or ADRs that describe measurable quality attributes
• better alignment between architecture, testing, and operations

Validate

• each chosen NFR is measurable or at least falsifiable
• the selected attributes are the ones that actually drive design trade-offs
• verification and operational expectations are linked where needed

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.