Skip to content

kwakseongjae/oh-my-design / skills/omd-lab-02-design-harness

omd-lab-02-design-harness

Flagged

OmD Lab

FileKindSize
SKILL.mdskill md4.8 KB
playbooks/v1.mdmarkdown4.9 KB
playbooks/v2.mdmarkdown2.1 KB
runs/live-2026-04-27-water-app/feedback-log.mdmarkdown22.6 KB
runs/v4-self-test/README.mdmarkdown1.9 KB
runs/v4-self-test/fixtures/founder/README.mdmarkdown182 B
runs/v4-self-test/fixtures/junior-designer/package.jsonmanifest268 B
runs/v4-self-test/fixtures/junior-designer/src/components/Hero.tsxother76 B
runs/v4-self-test/fixtures/junior-designer/src/components/Project.tsxother64 B
runs/v4-self-test/fixtures/senior-dev/package.jsonmanifest522 B
runs/v4-self-test/fixtures/senior-dev/src/components/Accordion.tsxother278 B
runs/v4-self-test/fixtures/senior-dev/src/components/Alert.tsxother262 B
runs/v4-self-test/fixtures/senior-dev/src/components/Avatar.tsxother266 B
runs/v4-self-test/fixtures/senior-dev/src/components/Badge.tsxother262 B
runs/v4-self-test/fixtures/senior-dev/src/components/Breadcrumb.tsxother282 B
runs/v4-self-test/fixtures/senior-dev/src/components/Button.tsxother266 B
runs/v4-self-test/fixtures/senior-dev/src/components/Card.tsxother258 B
runs/v4-self-test/fixtures/senior-dev/src/components/Combobox.tsxother274 B
runs/v4-self-test/fixtures/senior-dev/src/components/DataTable.tsxother278 B
runs/v4-self-test/fixtures/senior-dev/src/components/Dialog.tsxother266 B
runs/v4-self-test/fixtures/senior-dev/src/components/Drawer.tsxother266 B
runs/v4-self-test/fixtures/senior-dev/src/components/Field.tsxother262 B
runs/v4-self-test/fixtures/senior-dev/src/components/Form.tsxother258 B
runs/v4-self-test/fixtures/senior-dev/src/components/Input.tsxother262 B
runs/v4-self-test/fixtures/senior-dev/src/components/Menu.tsxother258 B
runs/v4-self-test/fixtures/senior-dev/src/components/Modal.tsxother262 B
runs/v4-self-test/fixtures/senior-dev/src/components/Pagination.tsxother282 B
runs/v4-self-test/fixtures/senior-dev/src/components/Popover.tsxother270 B
runs/v4-self-test/fixtures/senior-dev/src/components/Select.tsxother266 B
runs/v4-self-test/fixtures/senior-dev/src/components/Sheet.tsxother262 B
runs/v4-self-test/fixtures/senior-dev/src/components/Spinner.tsxother270 B
runs/v4-self-test/fixtures/senior-dev/src/components/Tabs.tsxother258 B
runs/v4-self-test/fixtures/senior-dev/src/components/Toast.tsxother262 B
runs/v4-self-test/fixtures/senior-dev/src/components/Tooltip.tsxother270 B
runs/v4-self-test/fixtures/senior-dev/src/components/VirtualList.tsxother286 B
runs/v4-self-test/fixtures/vibe-coder/package.jsonmanifest375 B
runs/v4-self-test/fixtures/vibe-coder/src/components/Alert.tsxother166 B
runs/v4-self-test/fixtures/vibe-coder/src/components/Avatar.tsxother168 B
runs/v4-self-test/fixtures/vibe-coder/src/components/Badge.tsxother166 B
runs/v4-self-test/fixtures/vibe-coder/src/components/Button.tsxother168 B
runs/v4-self-test/fixtures/vibe-coder/src/components/Card.tsxother164 B
runs/v4-self-test/fixtures/vibe-coder/src/components/Input.tsxother166 B
runs/v4-self-test/fixtures/vibe-coder/src/components/Modal.tsxother166 B
runs/v4-self-test/fixtures/vibe-coder/src/components/Spinner.tsxother170 B
runs/v4-self-test/fixtures/vibe-coder/src/components/Tabs.tsxother164 B
runs/v4-self-test/fixtures/vibe-coder/src/components/Toast.tsxother166 B
runs/v4-self-test/fixtures/vibe-coder/src/styles/globals.cssother401 B
runs/v4-self-test/fixtures/vibe-coder/tailwind.config.tsscript540 B
runs/v4-self-test/iterations/i1-findings.mdmarkdown2.5 KB
runs/v4-self-test/iterations/i2-audit-F.mdmarkdown12.3 KB
runs/v4-self-test/iterations/i2-audit-J.mdmarkdown16.1 KB
runs/v4-self-test/iterations/i2-audit-S.mdmarkdown20.2 KB
runs/v4-self-test/iterations/i2-audit-V.mdmarkdown12.1 KB
runs/v4-self-test/iterations/i2-consolidated.mdmarkdown3.8 KB
runs/v4-self-test/postmortem.mdmarkdown7.4 KB

playbooks/v1.md

View on GitHub
# Lab #02 — Playbook v1 (Baseline)

**Date locked:** 2026-04-27
**Status:** Active baseline
**Hypothesis:** None (this is the reference implementation against which v2+ will measure).

## Configuration snapshot

| Dimension | v1 setting |
|---|---|
| Channels | Claude Code (primary), Codex (mirror — declarative parity) |
| Phases | 10 (1 / 1.5 / 2 / 3 / 4 / 5 / 6 / 6.5 / 7 / 8 + handoff) |
| Sub-agents | 8 (master, ux-researcher, asset-curator, ui-junior, microcopy, a11y-auditor, persona-tester, critic) |
| Iteration cap | 3 |
| User checkpoints | 3 mandatory (Phase 3 / Phase 5 / Phase 8) + 1 informational (Phase 1.5 asset choice) |
| Discovery questions | 5-8 in one batch |
| UX research parallelism | 2-3 ux-researcher agents |
| Persona testing parallelism | 4 persona-testers (1 from §13 user-defined + 3 adversarial) |
| Adversarial persona budget | 3s/step, ABANDON token strict |
| Eval pipeline | deterministic gate → prompt-diversity Claude jury → persona walkthrough |
| External API keys | NOT required — orchestration runs entirely inside Claude Code / Codex session |
| Cross-family jury | Opt-in v2+ feature — v1 uses 3-judge prompt-diversity ensemble on host model |
| Vision-LLM use | Triage only with Set-of-Mark |
| Self-Refine cap | 2 retries gated on oracle signal |
| Korean persona source | Nemotron-Personas-Korea lazy-load opt-in (PIPA-compliant) |
| Asset fallback chain | Pinterest URL listing → Unsplash → Pexels → Lucide → Heroicons → unDraw → Mixkit → Coverr → brand-color SVG |
| Asset Pinterest policy | URL listing only (TOS forbids scraping) |
| Run archive | Permanent, content-addressed screenshots |
| Token budget | None (per user: explicitly out of scope for v1) |

## Agent prompts source

The 8 prompts live at `.claude/agents/omd-*.md` (this repo) and `.codex/agents/omd-*.toml` (Codex mirror). v1 ships them verbatim.

## Eval rubric (jury)

LLM jury rates against 4 dimensions (0-5 each, no compound score):

| Dimension | Rubric criteria |
|---|---|
| Voice fidelity | Forbidden phrases used: 0. Microcopy matches §10 register. |
| State completeness | All 5 states (empty/loading/error/success/skeleton) present per screen. |
| Principle adherence | No §12 Principle violations in wireframes/components. |
| IA discipline | Every screen has entry, exit, error path. |

Pairwise vs previous iteration, both orderings, position bias mitigated.

## Persona pool (default)

For Korean projects:
- 1 from DESIGN.md §13 (user-defined; if missing, swap to nemotron 1×)
- adversarial-impatient (3s budget)
- adversarial-low-literacy
- adversarial-brand-skeptic

For English projects: same skeleton, persona prompts in English.

## Success criteria for v1

A v1 run is "successful" if:
1. Reaches Phase 9 handoff without crash or infinite loop.
2. All 3 mandatory user checkpoints honored (no auto-skip).
3. handoff/v0.zip is non-empty and contains brief + DESIGN.md + wireframes + components/manifest.json + assets/.
4. eval/deterministic.json verdict = "pass".
5. ≥ 2/4 personas reach task_success = true.
6. Total tokens stay under ANY single-day Claude Pro / ChatGPT Plus quota for an active user (informally tracked, not enforced).

## Known v1 limitations (will guide v2-v3 hypotheses)

- Cross-family jury graceful-degrades to single-family if user lacks GPT/Gemini keys → v2 candidate: enforce 2-family minimum or substitute with prompt-diversity ensemble.
- Asset sourcing is API-key-gated (Unsplash / Pexels APIs); without keys, falls back to WebFetch on public pages → v2 candidate: ship with default API keys via package.json env-template, or bundle a public-domain seed pack.
- Persona walkthrough simulation mode (no Playwright) loses motion/click realism → v2 candidate: bundle a static-HTML render layer so simulation has DOM to walk.
- Korean persona pool requires user opt-in (license) → v2 candidate: pre-stage opt-in at first run instead of mid-flow.

## Instrumentation (what v1 measures, mandatory for compare/)

Every v1 run must emit `postmortem.md` with:

```markdown
- iterations: <N>
- total_tokens_estimated: <approx based on agent log>
- persona_abandon_rate: <abandons / total personas>
- deterministic_pass_rate: <passes / total checks>
- jury_score_normalized: <avg rubric score / 5>
- time_to_handoff_min: <ISO end - ISO start, in minutes>
- user_satisfied: yes | partial | no | unknown
- user_reject_phases: [<phases user pushed back on>]
- agent_token_breakdown:
    omd-master: ~Xk
    omd-ux-researcher (×3): ~Xk
    ...
- failure_modes_hit: [<list of named failure modes>]
```

`omd lab compare` reads these to build metrics.json.

## Scope freeze

v1 does NOT include:
- Pixel rendering of components (delegated to v0/Cursor/Subframe)
- A11y violations beyond axe-core + lighthouse (no manual heuristic walk)
- Live A/B testing with real users (synthetic personas only)
- Automatic API key acquisition (user provides)

These are explicit scope decisions — moving them in is a v2+ change, not a v1 bug.
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 323kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall