Workflow Map

The MaxwellAI OS Froid (Froid) organizes software delivery into four phases. Each phase adds only the context the work needs, from optional discovery through planning, solutioning, and implementation.

Use Choose a Planning Path to decide how much of this map your change needs. Invoke the listed skills directly. If you are unsure what to do next in an installed project, run froid-help.

Open diagram in new tab ↗

Phase 1: Analysis (Optional)

Explore the problem space and validate ideas before committing to planning. See Explore and Validate an Idea for which tool fits your situation and Define Requirements and a Specification for brief versus PRFAQ.

Workflow	Purpose	Produces
froid-brainstorming	Brainstorm Project Ideas with guided facilitation of a brainstorming coach	brainstorm.html keepsake plus an optional brainstorm-intent.md
froid-forge-idea	Pressure-test an idea until it hardens, proves out, or dies cheaply	forge-report.html every run; forged-idea.md when an idea hardens
froid-deep-recon	Research any subject for a decision — draft a prompt for your deep-research tool, process its report, or run the research here; six typed packs, verified and cited	Research report or summary + optional HTML briefing
froid-product-brief	Capture strategic vision — best when your concept is clear	brief.md + addendum.md, plus any desired HTML or presentation output
froid-prfaq	Working Backwards — stress-test your product concept customer-first	prfaq-{project}.md

For Deep Recon’s three modes and how to choose between them, see Research a Decision.

Phase 2: Planning

Define what to build and for whom. See Define Requirements and a Specification and Design UX and Architecture.

Workflow	Purpose	Produces
froid-prd	Create, update, or validate a PRD — facilitated discovery, three intents in one skill	Create/Update: prd.md, addendum.md, .memlog.md; Validate: validation-report.html + .md
froid-ux	Design user experience (when UX matters) — DESIGN.md (visual) + EXPERIENCE.md (behavioral) spine pair	DESIGN.md, EXPERIENCE.md, .memlog.md
froid-spec	Distill any intent input (brief, PRD, transcript, brain dump, design folder) into a succinct SPEC.md contract + companions — locks the WHAT before the HOW	SPEC.md + companions under {output_folder}/specs/spec-{slug}/; optional stories.yaml

Three intents in one skill

froid-prd handles the full PRD lifecycle. State your intent when invoking or the skill will ask:

• Create — new PRD from scratch via coached discovery; produces prd.md, addendum.md, and .memlog.md
• Update — reconcile an existing PRD with a change signal, surfacing conflicts before applying changes
• Validate — critique a PRD against a configurable checklist and produce a structured HTML findings report

froid-spec

froid-spec produces the canonical machine contract: a five-field kernel (Why, Capabilities, Constraints, Non-goals, Success signal) plus companion files, validated so every load-bearing source claim is preserved. It is the only writer of SPEC.md; other skills invoke it headless when they need to express or update intent. On request, Story Breakdown also creates the ordered stories.yaml used to implement an epic across several sessions. See Define Requirements and a Specification and Choose a Planning Path.

Upstream: froid-product-brief

froid-product-brief (Phase 1) produces a product-brief.md that froid-prd can source-extract during Discovery, reducing re-explanation and keeping the two documents aligned. Neither skill requires the other — start with froid-prd directly if you already know what you’re building.

Phase 3: Solutioning

Decide how to build it and break work into stories.

Workflow	Purpose	Produces
froid-architecture	Make technical decisions explicit	ARCHITECTURE-SPINE.md is the spine by default but can hydrate to your desired output or presentation needs also
froid-create-epics-and-stories	Break requirements into implementable work	Epic files with stories
froid-sprint-planning	Readiness gate before implementation, then story tracking and status view	PASS/CONCERNS/FAIL + sprint-status.yaml

For how the readiness gate, deterministic tracking, and status view work together, see Break Work into Stories and Track It. For closing an epic, see Finish an Epic.

Phase 4: Implementation

Implementation happens in session-sized units. froid-build handles a unit attentively; froid-build-auto handles one unit unattended. Larger planning paths create and preserve the context those units need. See Build a Change for the attended path, Review a Change for a standalone review, Walk Through a Change to walk a finished change, and Test Completed Work to choose a testing path.

Workflow	Purpose	Produces
froid-build	Implement and review one direct intent or planned story with human checkpoints	Implementation record + code
froid-build-auto	Implement and review one unit unattended for a caller or orchestrator	Implementation record + code + terminal status
froid-code-review	Ad hoc review of any code change. See Review a Change	Findings + applied patches
froid-correct-course	Handle significant mid-sprint changes	Updated plan or re-routing
froid-retrospective	Evidence-based review of a completed epic against its acceptance criteria	Retro document, action items, acceptance verdict

Direct and Planned Entry

Clear one-session work can enter froid-build directly. A spec-backed epic uses Story Breakdown to create several units under one SPEC.md. A multi-epic project may add a PRD, UX, architecture, epics, readiness results, and sprint tracking before selecting each unit.

Build Auto does not orchestrate those units. An AI coding session or another orchestrator, such as froid-loop, selects and dispatches one worker per unit. See Autonomous Development Loops for the worker and orchestration contracts.

Context Management

Each document becomes context for later decisions. The PRD records the product requirements. The architecture records the patterns and boundaries that each implementation unit must follow. Specs and story records preserve intent, decisions, and completion state as work is divided and recombined.

Project Context

Recommended

Set up your repo so AI agents follow your project’s rules across all workflows: a small verified block in AGENTS.md, maintained by froid-project-context. Seed it from your architecture at the end of planning, or discover it from an existing codebase at any time.

How to create it:

• Run froid-project-context — greenfield (seeded from your spec or architecture) or brownfield (discovered from the codebase, verified, then confirmed with you). The earlier froid-generate-project-context is deprecated and forwards there; an existing project-context.md is offered up for absorption.

Learn more about project context