design

name	design
description	[Design] Create or describe a UI design — quick (fast), immersive (good), or recreated/described from a screenshot or video. Dispatch via --mode={fast|good|describe|screenshot|video} (default fast).
disable-model-invocation	false

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 (No Hooks)

Codex uses static project-reference loading instead of runtime-injected project docs. 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)

Missing/stale context route: If docs/project-config.json, the docs index, lessons.md, CLAUDE.md, AGENTS.md, or any task-required reference doc is missing or stale, auto-run $project-init or the narrow setup route ($project-config, $docs-init, $scan-all, $scan --target=<key>, $claude-md-init) before ordinary project-specific work. If Codex mirrors or AGENTS.md are missing/stale, ask the user to run $sync-codex; do not auto-run it.

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 authoring, docs/specs/ pathing, or TC format: feature-spec-reference.md, spec-system-reference.md, spec-principles.md
• Behavior/public-contract changes or spec-test-code sync: workflow-spec-test-code-cycle-reference.md plus the spec docs above
• Derived spec indexes/ERDs/reimplementation guides: spec-system-reference.md and source Feature Specs under docs/specs/
• 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.

Quick Summary

Goal: Create (or describe) a UI design using design-intelligence databases and subagents, dispatched by --mode.

Renamed: folds the former /design-fast, /design-good, /design-describe, /design-screenshot, /design-video skills into --mode={fast|good|describe|screenshot|video} — those names no longer resolve as slash commands; use $design --mode=….

Mode dispatch: --mode={fast|good|describe|screenshot|video} — default fast when omitted.

Mode	Input carrier	Output
fast (default)	text brief	quick prototype implementation
good	text brief	immersive, researched, higher-quality implementation
describe	screenshot / video	super-detailed written description + implementation plan (NO code)
screenshot	screenshot	design recreated from the image as functional code
video	video	design + interactions recreated from the video as functional code

Shared workflow (5-stage spine):

1. Research — Run ui-ux-pro-max searches for design intelligence (ALWAYS FIRST)
2. Ingest — For visual modes (describe/screenshot/video), use visual analysis tooling to analyze the screenshot/video in super-detail
3. Design — Use ui-ux-designer subagent to create the design (or, for describe, an implementation plan)
4. Implement — Build as code with frontend-design (skipped in describe mode)
5. Document — Present to user for approval; update ./docs/design-guidelines.md if needed

Key Rules:

• Always activate ui-ux-pro-max FIRST for design intelligence
• Default to pure HTML/CSS/JS if the user doesn't specify a framework
• Use visual analysis tooling for generating AND reviewing real visual assets
• Use media processing tooling (RMBG) to remove backgrounds from generated assets when needed

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

Arguments & Mode Dispatch

$design --mode={fast|good|describe|screenshot|video} <brief | screenshot | video>

• When --mode is omitted, default to --mode=fast.
• $ARGUMENTS carries the full input after the command. Interpret it per mode: fast/good → a text design brief; describe/screenshot → a screenshot reference (path/URL/attachment); video → a video reference.

Required Skills (Priority Order)

1. ui-ux-pro-max — Design intelligence database (ALWAYS ACTIVATE FIRST)
2. frontend-design — Implementation, screenshot/video analysis, and design replication

Ensure token efficiency while maintaining high quality.

Shared First Step (ALL modes)

FIRST, run ui-ux-pro-max searches to gather design intelligence:

python $HOME/.claude/skills/ui-ux-pro-max/scripts/search.py "<product-type>" --domain product
python $HOME/.claude/skills/ui-ux-pro-max/scripts/search.py "<style-keywords>" --domain style
python $HOME/.claude/skills/ui-ux-pro-max/scripts/search.py "<mood>" --domain typography
python $HOME/.claude/skills/ui-ux-pro-max/scripts/search.py "<industry>" --domain color

Mode Branches

--mode=fast (default) — quick design

1. Run the shared ui-ux-pro-max searches above.
2. Use ui-ux-designer subagent to start the design process.
3. If the user doesn't specify, create the design in pure HTML/CSS/JS.
4. Report back with a brief summary of the changes; ask the user to review and approve.
5. On approval, update ./docs/design-guidelines.md if needed.

--mode=good — immersive, high-quality design

Same spine as fast, raised to a higher quality bar (iterate on details):

1. Run comprehensive ui-ux-pro-max searches across all domains.
2. Use researcher subagent to research design style, trends, fonts, colors, borders, spacing, elements' positions, etc.
3. Use ui-ux-designer subagent to implement the design step by step based on the research.
4. If the user doesn't specify, create the design in pure HTML/CSS/JS.
5. Report back with a summary; ask the user to review and approve.
6. On approval, update ./docs/design-guidelines.md if needed.

• ALWAYS REMEMBER you have the skills of a top-tier UI/UX Designer who won many awards on Dribbble, Behance, Awwwards, Mobbin, TheFWA.
• Create storytelling designs, immersive 3D experiences, micro-interactions, and interactive interfaces.

--mode=describe — describe only (NO implementation)

Treat $ARGUMENTS as the screenshot/video to describe.

1. Use visual analysis tooling to describe super-details of the screenshot/video so a developer can implement it easily.
   • Be specific about design style, every element, elements' positions, every interaction, every animation, every transition, every color, every border, every icon, every font style/size/weight, every spacing/padding/margin, every size/shape/texture/material/light/shadow/reflection/refraction/blur/glow/image, background transparency, etc.
   • IMPORTANT: Predict the font name (Google Fonts) and font size — don't just use Inter or Poppins.
2. Use ui-ux-designer subagent to create a design implementation plan following the progressive-disclosure structure so the result matches the screenshot/video:
   • Create a directory using the naming pattern from the ## Naming section.
   • Save the overview access point at plan.md, keep it generic, under 80 lines, listing each phase with status/progress and links.
   • For each phase, add phase-XX-phase-name.md with sections (Context links, Overview with date/priority/statuses, Key Insights, Requirements, Architecture, Related code files, Implementation Steps, Todo list, Success Criteria, Risk Assessment, Security Considerations, Next steps).
3. Report back with a summary of the plan. Do NOT implement.

--mode=screenshot — recreate from image as code

Treat $ARGUMENTS as the screenshot to recreate exactly.

1. Use visual analysis tooling to describe super-details of the screenshot (design style, trends, fonts, colors, border, spacing, elements' positions, size, shape, texture, material, light, shadow, reflection, refraction, blur, glow, image, background transparency, transition, etc.).
   • IMPORTANT: Predict the font name (Google Fonts) and font size — don't just use Inter or Poppins.
2. Use ui-ux-designer subagent to create a design plan following the progressive-disclosure structure (as in describe) so the final result matches the screenshot. Keep every research markdown report concise (≤150 lines).
3. Implement the plan step by step.
4. If the user doesn't specify, create the design in pure HTML/CSS/JS.
5. Report back with a summary; ask the user to review and approve.
6. On approval, update ./docs/design-guidelines.md if needed.

• ALWAYS REMEMBER you have the skills of a top-tier UI/UX Designer who won many awards on Dribbble, Behance, Awwwards, Mobbin, TheFWA.
• Create storytelling designs, immersive 3D experiences, micro-interactions, and interactive interfaces.

--mode=video — recreate from video as code

Treat $ARGUMENTS as the video to recreate exactly. Same as --mode=screenshot, but ingest a VIDEO and capture BOTH static layout AND interaction/animation/transition patterns.

1. Use visual analysis tooling to describe super-details of the video: every element, every interaction, every animation, every transition, every color, every font, every border, every spacing, every size/shape/texture/material/light/shadow/reflection/refraction/blur/glow/image, background transparency, etc.
   • IMPORTANT: Predict the font name (Google Fonts) and font size — don't just use Inter or Poppins.
2. Use ui-ux-designer subagent to create a design plan following the progressive-disclosure structure so the final result matches the video. Keep every research markdown report concise (≤150 lines).
3. Implement the plan step by step.
4. If the user doesn't specify, create the design in pure HTML/CSS/JS.
5. Report back with a summary; ask the user to review and approve.
6. On approval, update ./docs/design-guidelines.md if needed.

• ALWAYS REMEMBER you have the skills of a top-tier UI/UX Designer who won many awards on Dribbble, Behance, Awwwards, Mobbin, TheFWA.
• Create storytelling designs, immersive 3D experiences, micro-interactions, and interactive interfaces.

Notes (all modes)

• Design system (canonical): When implementing UI — HTML, CSS, or SCSS — read the project canonical design-system doc docs/project-reference/design-system/design-system-canonical.md first for design tokens, component patterns, and BEM conventions. Prefer designSystem.canonicalDoc + tokenFiles (resolved from docs/project-config.json) over per-app docs for new design work.
• Remember you have the capability to generate images, videos, edit images, etc. with visual analysis tooling skills. Use them to create the design and real assets.
• Always review, analyze, and double-check generated assets with visual analysis tooling skills to verify quality.
• Use media processing tooling (RMBG) to remove background from generated assets if needed (good/screenshot/video).
• Maintain and update ./docs/design-guidelines.md docs if needed.

---

[IMPORTANT] Use task tracking to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.

Think hard to plan & start working on these tasks follow the Orchestration Protocol, Core Responsibilities, Subagents Team and Development Rules. Parse --mode from the input (default fast) and route to the matching branch above: $ARGUMENTS

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

Re-read files after context changes. Context compaction, resume, or long-running work can make memory stale; verify current files before acting. Verify generated content against source evidence. AI hallucinates APIs, names, claims, and document facts. Check the relevant source before documenting or referencing. Check downstream references before deleting or renaming. Removing an artifact can stale docs, generated mirrors, configs, and callers; map references first. Trace the full impact chain after edits. Changing a definition can miss derived outputs and consumers. Follow the affected chain before declaring done. Verify ALL affected outputs, not just the first. One green check is not all green checks; validate every output surface the change can affect. Assume existing values are intentional — ask WHY before changing. Before changing a constant, limit, flag, wording, or pattern, read nearby context and history. Surface ambiguity before acting — don't pick silently. Multiple valid interpretations require an explicit question or stated assumption with risk. Keep shared guidance role-relevant. Universal guidance must help every receiving skill or agent; code-specific obligations belong only in code-specific protocols.

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.

MUST ATTENTION apply critical + sequential thinking — every claim needs appropriate traced evidence (file:line for repo/code claims; source URL or artifact section for research, product, content, and docs claims); confidence >80% to act, <60% DO NOT recommend. Anti-hallucination: never present guess as fact, admit uncertainty freely, cross-reference independently, stay skeptical of own confidence.

MUST ATTENTION apply AI mistake prevention — verify generated content against evidence, trace downstream references before deleting or renaming, verify all affected outputs, re-read files after context loss, and surface ambiguity before acting.

Closing Reminders

MUST ATTENTION — Protocols in force (concise digest of the SYNC/shared blocks this skill carries):

• AI Mistake Prevention: verify generated content against evidence, trace downstream references, verify all affected outputs, re-read after context loss, surface ambiguity.

• Critical Thinking: traced file:line proof, confidence >80%; NEVER present a guess as fact.

• MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks using task tracking BEFORE starting

• MANDATORY IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code

• MANDATORY IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act)

• MANDATORY IMPORTANT MUST ATTENTION add a final review todo task to verify work quality

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

Hookless Prompt Protocol Mirror (Auto-Synced)

Source: .claude/.ck.json + .claude/skills/shared/sync-inline-versions.md (:full blocks) + .claude/scripts/lib/hookless-prompt-protocol.cjs

[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. For spec, test-case, behavior-change, public-contract, or docs/specs/ work, route through the local spec docs named by the docs index: feature-spec-reference.md, spec-system-reference.md, spec-principles.md, and workflow-spec-test-code-cycle-reference.md when specs/tests/code must stay synchronized. If either file or a required reference doc is missing or stale, auto-run $project-init (or the narrow lower-level route such as $project-config, $docs-init, $scan-all, or $scan --target=<key>) before ordinary project-specific work. Any supported AI tool may execute when this shared context and local docs are available.

1. DETECT: If the prompt starts with an explicit slash skill/workflow command, execute it directly. Otherwise match the prompt against the workflow catalog and skill list.
2. ANALYZE: Choose the best option: execute directly, invoke a skill, activate a standard workflow, or compose a custom step combination.
3. AUTO-SELECT: Pick the best option yourself. Do not ask the user to choose between direct execution, skill, standard workflow, or custom workflow.
4. ACTIVATE: For a selected workflow, call $start-workflow <workflowId>; for a selected skill, invoke that skill; for a custom workflow, sequence custom steps directly; for direct execution, proceed with the task.
5. CREATE TASKS: task tracking for ALL workflow/skill/custom steps before execution when the selected path has multiple steps.
6. EXECUTE: Advance per the Workflow Step Advancement & Parallel Phases rule in your context instructions — model-driven; a sub-agent completion advances a step identically to an inline call; a parallel-phase group is an all-return barrier (advance only after ALL members return, never serialize it)

Shared AI-SDD Protocol Markers

Source: .claude/skills/shared/sync-inline-versions.md

SYNC:ai-sdd-artifact-contract

AI-SDD Artifact Contract — Shared spec-driven development rules stay portable and source-owned.

1. Keep reusable AI-SDD principles in .claude; put repository-specific paths, commands, owners, products, and formats in project config/reference docs.
2. Preserve cycle: spec -> plan -> tasks -> implement -> verify -> update spec/docs.
3. Trace every requirement or invariant through decision, task, TC/test, source evidence, and docs/spec update.
4. Treat code-to-spec extraction as reference-only until accepted by the canonical spec owner.
5. Any supported AI tool may plan, implement, review, or verify with synced context; using multiple tools is optional.
6. Update .claude source first, then sync generated mirrors; do not manually edit .agents, .codex, or AGENTS.md. — why: mirrors are generated artifacts; hand-edits are overwritten on the next sync
7. If docs/project-config.json, root instruction files, or a required project-reference doc is missing or stale, auto-run $project-init or the narrow lower-level route before ordinary project-specific work.

Active reference: shared/sdd-artifact-contract.md in the active skills root.

---

SYNC:ai-sdd-artifact-contract:reminder

• MANDATORY Apply shared/sdd-artifact-contract.md; keep reusable AI-SDD in .claude and local rules in project docs.
• MANDATORY Code-to-spec extraction is reference-only until canonical acceptance; any supported AI tool may execute with synced context.
• MANDATORY Update .claude source before syncing generated mirrors; do not manually edit .agents, .codex, or AGENTS.md.
• MANDATORY Missing or stale project config, root instruction files, or required reference docs route project-specific work through $project-init or the narrow setup route automatically. [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.

[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/$security-review/$lint catch this?" — Yes → improve review skill instead.
7. BOTH gates pass → ask user to run $learn. [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.

Common AI Mistake Prevention (System Lessons)

• Re-read files after context compaction. Edit requires prior Read in same context; compaction wipes read state. Re-read before editing.
• Grep for old terms after bulk replacements. AI over-trusts find/replace completeness. Grep full repo after bulk edits for missed refs in docs/configs/catalogs.
• Check downstream references before deleting. Deletions cascade doc/code staleness. Map referencing files before removal.
• After memory loss, check existing state before creating new. Compaction wipes prior-work memory. Query current state to resume — never blindly duplicate.
• Verify AI-generated content against actual code. AI hallucinates APIs, class names, method signatures. Grep to confirm existence before documenting/referencing.
• Trace full dependency chain after edits. Changing a definition misses downstream consumers. Trace the full chain.
• When renaming, grep ALL consumer file types. Some file types silently ignore missing refs (no compile error). Search code, templates, configs, generated files.
• Trace ALL code paths when verifying correctness. Code existing ≠ code executing. Trace early exits, error branches, conditional skips — not just happy path.
• Update docs that embed canonical data when source changes. Docs inlining derived data (workflows, schemas, configs) go stale silently. Update all embedding docs alongside source.
• Verify sub-agent results after context recovery. Background agents may finish while parent compacted — grep-verify output, don't trust assumed completion.
• Cross-check full target list against sub-agent assignments. Parallel sub-agents by category miss boundary items. Reconcile union of assignments against target list before proceeding.
• Sub-agents inherit knowledge only from their agent .md definition — use custom agent types, not built-in Explore. Tool adoption = permission + knowledge + enforcement (numbered workflow step).
• Persist sub-agent findings incrementally, not as a final batch. Long sub-agents hit cutoffs before final write — findings lost. Instruct append-per-section to report file.
• When debugging, ask "whose responsibility?" before fixing. Trace caller (wrong data) vs callee (wrong handling). Fix at responsible layer — never patch symptom site.
• Grep ALL removed names after extraction/refactoring. Primary file "done" ≠ secondary files clean. Grep entire scope for every removed symbol before declaring complete.
• Assume existing values are intentional — ask WHY before changing. Pattern-matching as "wrong" skips context. Before changing any constant/limit/flag: read comments, git blame, surrounding code.
• Verify ALL affected outputs, not just the first. One build green ≠ all green. Multi-stack changes (backend/frontend/tests/docs) require verifying EVERY output.
• Evaluate fit before copying a nearby pattern. Closest example ≠ matching preconditions — verify the new context shares the same constraints, base classes, scope, lifetime.
• Holistic-first debugging — resist nearest-attention trap. Don't dive into first plausible cause. List EVERY precondition (config, env vars, paths, DB, endpoints, creds, versions, DI, data). Verify each against evidence (grep/query — not reasoning). Ask "what would falsify this?" — if nothing, it's not a hypothesis. Most expensive failure: going deeper in "obvious" layer while bug sits in layer never questioned.
• Surgical changes — apply the diff test (context-aware). Two modes: (1) Bug fix → every line traces to the bug; no restyling; orphan cleanup only for imports YOUR changes made unused. (2) Review/enhancement → implement improvements AND announce as "Enhancement beyond main request: [what]". Never silently scope-creep. Diff test: "Would this line exist if I wasn't asked to do X?" — if no, delete or announce.
• Surface ambiguity before coding — don't pick silently. Multiple valid interpretations → present each with effort: "[Request] could mean (1) [N h], (2) [N h]. Which matters?" List scope/format/volume/constraints assumptions first. If simpler path exists, say so. Never silently pick.
• [MANDATORY FIRST ACTION] ALWAYS activate a suitable skill or workflow BEFORE responding. Match task against workflow catalog + skill list; invoke via skill invocation or $start-workflow <workflowId>. NEVER answer or write code before checking. Skip = protocol violation.
• Why-Review adversarial mindset — apply when reviewing any plan, decision, or design. Default SKEPTIC not VALIDATOR: steel-man a rejected alternative, invert each stated reason ("what does it sacrifice?"), stress-test top 2-3 assumptions, run pre-mortem ("ships, fails in 3 months — what breaks?"), surface 1-2 alternatives author missed. Section presence ≠ quality; quality = causal reasoning + concrete mitigations + evidence, not "it's better" or "monitor closely".
• Front-load report-write in sub-agent prompts for large reviews. Many-file sub-agents hit budget before final write — findings lost. Design prompts so: (1) report-write is first explicit deliverable, (2) append per-file/section (not batched), (3) scope bounded so reads don't exhaust budget. Truncated mid-sentence with no report file → spawn narrower scope, don't retry same prompt.
• After context compaction, re-verify all prior phase outcomes before continuing. Summaries describe intent, not environment state (git index, filesystem, processes). On resume, FIRST audit: git status, re-read modified files, verify filesystem. Every "completed" claim is an untested hypothesis until evidence confirms.
• OOM/memory: check row count before row size. Triage: (1) Unbounded query — no DB filter for trigger? Push filter to DB; eliminates OOM. (2) Large rows? Projection reduces proportionally. Row reduction > projection in ROI.
• Keep domain concepts out of generic/shared/infrastructure layers. Reusable layer (shared library, framework, infra module) must reference NO consumer-specific domain concept — tenant/customer/product IDs, business entities, feature rules. Leak compiles + runs → passes review silently while coupling the "reusable" layer to one consumer. Keep shared type domain-free; push domain fields/logic down into the consumer via subclass/composition. — why: a layer coupled to one consumer's domain is no longer reusable.