Wireframe To Spec

Codex compatibility note:

>

- Invoke repository skills with $skill-name in Codex; this mirrored copy rewrites legacy Claude /skill-name references.

- Task tracker mandate: BEFORE executing any workflow or skill step, create/update task tracking for all steps and keep it synchronized as progress changes.

- User-question prompts mean to ask the user directly in Codex.

- Ignore Claude-specific mode-switch instructions when they appear.

- Strict execution contract: when a user explicitly invokes a skill, execute that skill protocol as written.

- Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required spawn_agent subagent(s) for that task.

- Do not skip, reorder, or merge protocol steps unless the user explicitly approves the deviation first.

- For workflow skills, execute each listed child-skill step explicitly and report step-by-step evidence.

- If a required step/tool cannot run in this environment, stop and ask the user before adapting.

<!-- CODEX:PROJECT-REFERENCE-LOADING:START -->

Codex Project-Reference Loading (No Hooks)

Codex does not receive Claude hook-based doc injection. When coding, planning, debugging, testing, or reviewing, open project docs explicitly using this routing.

Always read:

• docs/project-config.json (project-specific paths, commands, modules, and workflow/test settings)
• docs/project-reference/docs-index-reference.md (routes to the full docs/project-reference/* catalog)
• docs/project-reference/lessons.md (always-on guardrails and anti-patterns)

Situation-based docs:

• Backend/CQRS/API/domain/entity changes: backend-patterns-reference.md, domain-entities-reference.md, project-structure-reference.md
• Frontend/UI/styling/design-system: frontend-patterns-reference.md, scss-styling-guide.md, design-system/README.md
• Spec/test-case planning or TC mapping: feature-docs-reference.md
• Integration test implementation/review: integration-test-reference.md
• E2E test implementation/review: e2e-test-reference.md
• Code review/audit work: code-review-rules.md plus domain docs above based on changed files

Do not read all docs blindly. Start from docs-index-reference.md, then open only relevant files for the task.

<!-- CODEX:PROJECT-REFERENCE-LOADING:END -->

Quick Summary

Goal: Bridge image inputs (wireframes, sketches) to structured UI specifications.

Workflow:

1. Detect Input Type — Hand-drawn, digital wireframe, or screenshot 2. Analyze Image — Use ai-multimodal with wireframe-specific prompts 3. Generate Spec — ASCII wireframe + components + states + responsive per ui-wireframe-protocol.md 4. Output — PBI-compatible ## UI Layout section or standalone spec file

Key Rules:

Frontend/UI Context (if applicable)

When this task involves frontend or UI changes,

• Component patterns: docs/project-reference/frontend-patterns-reference.md (read directly when relevant; do not rely on hook-injected conversation text)
• Styling/BEM guide: docs/project-reference/scss-styling-guide.md
• Design system tokens: docs/project-reference/design-system/README.md

• Always require human review — wireframe analysis is 70-80% accurate
• Route to other skills when appropriate (Figma URL → figma-design, app screenshot → design-screenshot)
• [BLOCKING] Tech-agnostic output: spec prose/headings follow docs/project-reference/spec-principles.md §3 — describe components by UX role, not framework/library names; source paths and class names appear ONLY in evidence fields (**Evidence**, [Source:]), frontmatter, and Mermaid.

Input Routing

Wireframe Analysis

Use ai-multimodal with these prompts:

Prompt 1: Layout Extraction

"Analyze this wireframe image. Identify: (1) page layout regions (header, sidebar, main, footer), (2) all UI elements with approximate position and type (button, input, table, card, dropdown, modal, tabs), (3) content hierarchy (what is primary vs secondary), (4) interactive elements, (5) any text labels or annotations, (6) navigation patterns."

Prompt 2: Component Identification

"From the wireframe, list every distinct UI component. For each: name it descriptively, classify its complexity (primitive=single element, composite=grouped elements, section=page region), note its purpose."

Output Generation

After image analysis, generate output per ui-wireframe-protocol.md:

1. ASCII Wireframe — Recreate layout using box-drawing characters 2. Component Inventory — List with tier classification (Common/Domain-Shared/Page) 3. States Table — Default, Loading, Empty, Error per view 4. Component Decomposition Tree — If detail level warrants (refine/story) 5. Responsive Suggestions — Based on layout complexity

M1-M5 Compliance in UI Conversion

See .claude/skills/shared/sdd-artifact-contract.md → "AI-SDD Mandates (M1-M6)" for BLOCKING criteria. When converting a wireframe to a spec:

• M1-M2 — Business-level descriptions. Describe every component and state in business/UX terms (Primary Button, Modal Dialog, Data Table, Filter Bar) and observable markers — NEVER framework component class names, library imports, CSS classes, or component-state props in prose. Source identifiers belong only in **Evidence**/[Source:] carriers, frontmatter, and Mermaid.
• M3 — Map to feature logic by logical ID. Map each interactive component and interaction to the feature-spec operation or rule it drives, citing the logical ID (OP-/BR-/FR-). The logical ID is the primary spine; any [Source: namespace/service/id] abstract anchor stays in the Evidence carrier only — never a physical file:line/src/ path.
• M4 — Observable state transitions. Define every state transition by what visibly changes (color, icon, position, visible text) and its trigger — NEVER by code-level state management. Each transition must have exactly one valid interpretation.
• M5 — Rebuild-from-spec test. Before finalizing, confirm a reader with zero codebase knowledge could rebuild this screen on ANY framework from the spec alone. If any marker requires reading source to interpret, restate it as a visual/textual observable.

Mapped Business Operations

Emit this table linking each interactive component to the feature operations/rules it drives (logical ID is the primary spine; mark [UNVERIFIED — needs feature-spec mapping] when the wireframe alone cannot determine it):

Output Formats

Format A: PBI Section (default)

Output as ## UI Layout section compatible with PBI/story templates.

Format B: Standalone Spec

Output as team-artifacts/design-specs/{YYMMDD}-wireframe-spec-{slug}.md

Confidence & Review

• Always display confidence level for wireframe interpretation
• Always recommend human review before proceeding to implementation
• If confidence <70%: ask user clarifying questions about ambiguous elements via a direct user question

---

[IMPORTANT] Use task tracking to break ALL work into small tasks BEFORE starting.

<!-- SYNC:ui-system-context -->

UI System Context — For ANY task touching .ts, .html, .scss, or .css files:

>

MUST ATTENTION READ before implementing:

>

1. docs/project-reference/frontend-patterns-reference.md — component base classes, stores, forms

2. docs/project-reference/scss-styling-guide.md — BEM methodology, SCSS variables, mixins, responsive

3. docs/project-reference/design-system/README.md — design tokens, component inventory, icons

>

Reference docs/project-config.json for project-specific paths.

<!-- /SYNC:ui-system-context -->

<!-- SYNC:ui-wireframe-protocol -->

UI Wireframe Protocol — Wireframe-to-implementation flow: (1) Process design input (Figma/screenshot/sketch via ai-multimodal). (2) Create ASCII wireframe with box-drawing chars. (3) Build component inventory with tier classification (Common/Domain-Shared/Page). (4) Document states (Default/Loading/Empty/Error). (5) Map to design tokens. (6) Define responsive breakpoints. Search existing component libraries before creating new. Progressive detail by skill level (idea=sketch, story=full tree+specs).

<!-- /SYNC:ui-wireframe-protocol -->

<!-- SYNC:critical-thinking-mindset -->

Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act.

Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

<!-- /SYNC:critical-thinking-mindset -->

<!-- SYNC:ai-mistake-prevention -->

AI Mistake Prevention — Failure modes to avoid on every task:

>

Check downstream references before deleting. Deleting components causes documentation and code staleness cascades. Map all referencing files before removal.

Verify AI-generated content against actual code. AI hallucinates APIs, class names, and method signatures. Always grep to confirm existence before documenting or referencing.

Trace full dependency chain after edits. Changing a definition misses downstream variables and consumers derived from it. Always trace the full chain.

Trace ALL code paths when verifying correctness. Confirming code exists is not confirming it executes. Always trace early exits, error branches, and conditional skips — not just happy path.

When debugging, ask "whose responsibility?" before fixing. Trace whether bug is in caller (wrong data) or callee (wrong handling). Fix at responsible layer — never patch symptom site.

Assume existing values are intentional — ask WHY before changing. Before changing any constant, limit, flag, or pattern: read comments, check git blame, examine surrounding code.

Verify ALL affected outputs, not just the first. Changes touching multiple stacks require verifying EVERY output. One green check is not all green checks.

Holistic-first debugging — resist nearest-attention trap. When investigating any failure, list EVERY precondition first (config, env vars, DB names, endpoints, DI registrations, data preconditions), then verify each against evidence before forming any code-layer hypothesis.

Surgical changes — apply the diff test. Bug fix: every changed line must trace directly to the bug. Don't restyle or improve adjacent code. Enhancement task: implement improvements AND announce them explicitly.

Surface ambiguity before coding — don't pick silently. If request has multiple interpretations, present each with effort estimate and ask. Never assume all-records, file-based, or more complex path.

<!-- /SYNC:ai-mistake-prevention -->

<!-- SYNC:ui-system-context:reminder -->

IMPORTANT MUST ATTENTION read frontend pattern docs, SCSS guide, and design system tokens BEFORE any UI implementation.

<!-- /SYNC:ui-system-context:reminder -->

<!-- SYNC:ui-wireframe-protocol:reminder -->

IMPORTANT MUST ATTENTION follow wireframe protocol: ASCII wireframe, component inventory with tiers, states table, design tokens, responsive breakpoints.

<!-- /SYNC:ui-wireframe-protocol:reminder -->

<!-- SYNC:critical-thinking-mindset:reminder -->

MUST ATTENTION apply critical thinking — every claim needs traced proof, confidence >80% to act. Anti-hallucination: never present guess as fact.

<!-- /SYNC:critical-thinking-mindset:reminder -->

<!-- SYNC:ai-mistake-prevention:reminder -->

MUST ATTENTION apply AI mistake prevention — holistic-first debugging, fix at responsible layer, surface ambiguity before coding, re-read files after compaction.

<!-- /SYNC:ai-mistake-prevention:reminder -->

Closing Reminders

IMPORTANT MUST ATTENTION break work into small todo tasks using task tracking BEFORE starting IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act) IMPORTANT MUST ATTENTION add a final review todo task to verify work quality MANDATORY IMPORTANT MUST ATTENTION READ the following files before starting:

IMPORTANT MUST ATTENTION READ CLAUDE.md before starting

[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using task tracking.

<!-- CODEX:SYNC-PROMPT-PROTOCOLS:START -->

Hookless Prompt Protocol Mirror (Auto-Synced)

Source: .claude/hooks/lib/prompt-injections.cjs + .claude/.ck.json

[WORKFLOW-EXECUTION-PROTOCOL] [BLOCKING] Workflow Execution Protocol — MANDATORY IMPORTANT MUST CRITICAL. Do not skip for any reason.

Generic portability boundary: Reusable skills and protocol text stay project-neutral; project-specific conventions are discovered from docs/project-config.json and docs/project-reference/. Apply shared AI-SDD from shared/sdd-artifact-contract.md. Read docs/project-config.json and docs/project-reference/docs-index-reference.md, then open the project reference docs named there. Any supported AI tool may execute when this shared context and local docs are available.

1. DETECT: Match prompt against workflow catalog 2. ANALYZE: Find best-match workflow AND evaluate if a custom step combination would fit better 3. ASK (REQUIRED FORMAT): Use a direct user question with this structure unless the user explicitly invoked a workflow/skill and the local protocol treats explicit invocation as confirmation:

• Question: "Which workflow do you want to activate?"
• Option 1: "Activate [BestMatch Workflow] (Recommended)"
• Option 2: "Activate custom workflow: [step1 → step2 → ...]" (include one-line rationale)

4. ACTIVATE (if confirmed): Call $workflow-start <workflowId> for standard; sequence custom steps manually 5. CREATE TASKS: task tracking for ALL workflow steps 6. EXECUTE: Follow each step in sequence [CRITICAL-THINKING-MINDSET] Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination principle: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination. AI Attention principle (Primacy-Recency): Put the 3 most critical rules at both top and bottom of long prompts/protocols so instruction adherence survives long context windows. Goal-driven execution: Define success criteria first, loop until verified, and stop only when observable checks pass. Tests verify intent: Tests must protect business rules/invariants and fail when the protected intent breaks, not only mirror current behavior.

[LESSON-LEARNED-REMINDER] [BLOCKING] Task Planning & Continuous Improvement — MANDATORY. Do not skip.

Break work into small tasks (task tracking) before starting. Add final task: "Analyze AI mistakes & lessons learned".

Extract lessons — ROOT CAUSE ONLY, not symptom fixes:

1. Name the FAILURE MODE (reasoning/assumption failure), not symptom — "assumed API existed without reading source" not "used wrong enum value". 2. Generality test: does this failure mode apply to ≥3 contexts/codebases? If not, abstract one level up. 3. Write as a universal rule — strip project-specific names/paths/classes. Useful on any codebase. 4. Consolidate: multiple mistakes sharing one failure mode → ONE lesson. 5. Recurrence gate: "Would this recur in future session WITHOUT this reminder?" — No → skip $learn. 6. Auto-fix gate: "Could $code-review/$code-simplifier/$security/$lint catch this?" — Yes → improve review skill instead. 7. BOTH gates pass → ask user to run $learn. [TASK-PLANNING] [MANDATORY] BEFORE executing any workflow or skill step, create/update task tracking for all planned steps, then keep it synchronized as each step starts/completes.

<!-- CODEX:SYNC-PROMPT-PROTOCOLS:END -->