# Workflow Chains — Greeting Suggestion Data # Source of truth: .claude/rules/workflow-execution.md # Used by: Native agent greeting (STEP 3, step 5.5) to suggest next command # Story: WIS-16 workflows: # 1. Story Development Cycle (SDC) — PRIMARY - id: sdc name: Story Development Cycle description: Full 4-phase workflow for all development work chain: - step: 1 agent: "@sm" command: "*draft" task: create-next-story.md output: Story file (Draft) condition: Epic context available - step: 2 agent: "@po" command: "*validate-story-draft {story-id}" task: validate-next-story.md output: GO/NO-GO decision condition: Story status is Draft - step: 3 agent: "@dev" command: "*develop {story-id}" task: dev-develop-story.md output: Implementation complete condition: Story status is Approved alternatives: - agent: "@dev" command: "*develop-yolo {story-id}" condition: Simple story, autonomous mode preferred - step: 4 agent: "@qa" command: "*review {story-id}" task: qa-gate.md output: PASS/CONCERNS/FAIL/WAIVED condition: Story status is Ready for Review alternatives: - agent: "@qa" command: "*gate {story-id}" condition: Quick gate decision needed - step: 5 agent: "@devops" command: "*push" task: github-devops-pre-push-quality-gate.md output: Code pushed to remote condition: QA gate PASS # 2. QA Loop — ITERATIVE REVIEW - id: qa-loop name: QA Loop description: Automated review-fix cycle after initial QA gate max_iterations: 5 chain: - step: 1 agent: "@qa" command: "*review {story-id}" task: qa-review-story.md output: APPROVE/REJECT/BLOCKED verdict condition: Story has code changes to review - step: 2 agent: "@dev" command: "*apply-qa-fixes" task: apply-qa-fixes.md output: Fixes applied condition: QA verdict is REJECT alternatives: - agent: "@dev" command: "*fix-qa-issues" condition: Structured fix from QA_FIX_REQUEST.md - step: 3 agent: "@qa" command: "*review {story-id}" task: qa-review-story.md output: Re-review verdict condition: Fixes applied, re-review needed # 3. Spec Pipeline — PRE-IMPLEMENTATION - id: spec-pipeline name: Spec Pipeline description: Transform informal requirements into executable spec chain: - step: 1 agent: "@pm" command: "*gather-requirements" task: spec-gather-requirements.md output: requirements.json condition: New feature or complex change - step: 2 agent: "@architect" command: "*analyze-impact" task: architect-analyze-impact.md output: complexity.json condition: Complexity assessment needed (skip if SIMPLE) - step: 3 agent: "@analyst" command: "*research {topic}" task: create-deep-research-prompt.md output: research.json condition: STANDARD or COMPLEX class (skip if SIMPLE) - step: 4 agent: "@pm" command: "*write-spec" task: spec-write-spec.md output: spec.md condition: Requirements gathered - step: 5 agent: "@qa" command: "*critique-spec {story-id}" task: spec-critique.md output: APPROVED/NEEDS_REVISION/BLOCKED condition: Spec written - step: 6 agent: "@architect" command: "*plan" task: architect-analyze-impact.md output: implementation.yaml condition: Critique verdict is APPROVED # 4. Brownfield Discovery — LEGACY ASSESSMENT - id: brownfield name: Brownfield Discovery description: 10-phase technical debt assessment for existing codebases chain: - step: 1 agent: "@architect" command: "*analyze-brownfield" task: analyze-brownfield.md output: system-architecture.md condition: Existing codebase to assess - step: 2 agent: "@data-engineer" command: "*db-schema-audit" task: db-schema-audit.md output: SCHEMA.md + DB-AUDIT.md condition: Database exists in project - step: 3 agent: "@ux-design-expert" command: "*audit-frontend" task: audit-codebase.md output: frontend-spec.md condition: Frontend exists in project - step: 4 agent: "@qa" command: "*review" task: qa-review-story.md output: APPROVED/NEEDS WORK condition: All specialist reviews complete - step: 5 agent: "@pm" command: "*create-epic" task: brownfield-create-epic.md output: Epic + stories ready for development condition: QA gate APPROVED # --- Cross-Agent Integration Chains (ADR-CROSS-AGENT-INTEGRATION) --- # Design-First Development (greenfield UI projects) - id: design-first-development name: Design-First Development domain: software-dev description: "Greenfield UI workflow starting with design intelligence" chain: - agent: ux-design-expert command: "*research" output: "user research insights" - agent: ux-design-expert command: "*style {domain}" output: "complete style baseline (palette, typography, spacing)" - agent: ux-design-expert command: "*wireframe" output: "visual wireframe in Paper (or markdown if Paper unavailable)" - agent: architect command: "*create-front-end-architecture" output: "frontend architecture doc" - agent: ux-design-expert command: "*setup" output: "design system structure initialized" - agent: dev command: "*develop" output: "implementation" # Design System Review Loop (post-migration quality) - id: design-system-review name: Design System Review Loop domain: software-dev description: "Quality review after design system migration or build" chain: - agent: ux-design-expert command: "*document" output: "pattern library documentation" - agent: ux-design-expert command: "*a11y-check" output: "WCAG compliance report" - agent: qa command: "*review" output: "quality gate verdict" - agent: smith command: "*verify" output: "adversarial review (optional)" optional: true # UX Handoff Suggestions (for SDC integration via handoff mechanism) - id: sdc-ux-handoff name: SDC UX Design Suggestion domain: software-dev description: "When PO validates a frontend story, suggest UX design prep before dev" trigger: from_agent: po last_command: "validate-story" condition: "story.tags includes frontend OR story.tags includes ui OR story.tags includes design" suggestions: - agent: ux-design-expert command: "*style {story.domain}" rationale: "Get design token baseline before implementation" - agent: ux-design-expert command: "*wireframe" rationale: "Create visual wireframe in Paper for story UI requirements" - agent: dev command: "*develop" rationale: "Proceed directly to development (skip UX prep)" # Design System Extraction → Migration (brownfield) - id: design-system-extraction-migration name: Design System Extraction to Migration domain: software-dev description: "Extract existing design system, then plan migration" chain: - agent: ux-design-expert command: "*extract-design-system {source}" output: "MASTER.md + tokens.css + tailwind.config.ts" - agent: ux-design-expert command: "*audit {path}" output: "pattern inventory and redundancies" - agent: ux-design-expert command: "*consolidate" output: "consolidated patterns" - agent: ux-design-expert command: "*tokenize" output: "design tokens extracted" - agent: ux-design-expert command: "*migrate" output: "4-phase migration strategy"