Agent skill

Omd Lab 02 Design Harness

by kwakseongjae in kwakseongjae/oh-my-design

“OmD Lab”

— description from SKILL.md by kwakseongjae
MITAuto-check passedFrontend & Design

Install Omd Lab 02 Design Harness

skills CLI
$ npx skills add kwakseongjae/oh-my-design --skill omd-lab-02-design-harness -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install kwakseongjae/oh-my-design omd-lab-02-design-harness --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/kwakseongjae/oh-my-design.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/omd-lab-02-design-harness .claude/skills/omd-lab-02-design-harness && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
omd-lab-02-design-harness
GitHub stars
533
Token cost
~908 tokens
SKILL.md length
265 words
Files
62
Skills in repo
18
Repo updated
First seen
Licence
MIT

At a glance

  • Works in 3 steps: playbooks/v.md 작성. 가설을 한 줄로 → v이 v과 바꾸는 것 정확히 명시. 1개 변수만 바꾸는 게 원칙. → 변경 점이 sub-agent 프롬프트에 있으면…
  • SKILL.md covers 왜, 디렉토리 구조, Lab Run 프로토콜 and 진행 트랙 (이 Lab의 로드맵), plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

About this skill

Omd Lab 02 Design Harness is a skill in kwakseongjae/oh-my-design (533 stars). Its SKILL.md is about 908 tokens, with 61 other files in the folder. Licence: MIT.

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. playbooks/v.md 작성. 가설을 한 줄로
  2. v이 v과 바꾸는 것 정확히 명시. 1개 변수만 바꾸는 게 원칙.
  3. 변경 점이 sub-agent 프롬프트에 있으면 playbooks/v/agents-overrides/*.md로 patch 보관.

What it can do on your machine

Read from SKILL.md and the folder at commit c0ec438. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash and json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Omd Lab 02 Design Harness loads about 908 tokens when it runs. Until then it costs about 8 tokens; SKILL.md has 265 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~8
When it runs · the whole SKILL.md, loaded when a task matches
~908

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from kwakseongjae/oh-my-design at commit c0ec438, republished under its MIT licence (© kwakseongjae). 265 words, ~908 tokens.

Download SKILL.mdSave it as .claude/skills/omd-lab-02-design-harness/SKILL.md (or your agent's skills folder). This skill also uses 61 other files; get the full folder from GitHub.
name
omd-lab-02-design-harness
description
OmD Lab

OmD Lab #02 — Design Harness Refinement

omd:harness의 정교화 작업을 위한 실험실. 동일한 design task를 서로 다른 하네스 설정 (v1, v2, v3, ...)으로 돌려서 품질·비용·실패모드를 비교한다.

왜

Lab #01이 "DESIGN.md 유무"의 영향을 봤다면, Lab #02는 하네스 자체의 설정(prompt 변형, persona pool, eval rubric, asset 정책 등)이 산출물에 미치는 영향을 본다.

디렉토리 구조

skills/omd-lab-02-design-harness/
├── SKILL.md                       (this file)
├── playbooks/
│   ├── v1.md                      (현재 baseline — first full implementation)
│   ├── v2.md                      (다음 실험 가설)
│   └── ...
├── runs/
│   ├── v1-run-<ts>-<slug>/        ← omd:harness가 v1 설정으로 돌린 산출물 전체
│   ├── v2-run-<ts>-<slug>/
│   └── ...
├── compare/
│   ├── README.md                  (어떤 task로 어떤 v를 비교했는가)
│   └── <task-id>/
│       ├── index.html             (v1 vs v2 vs v3 동시 비교 뷰)
│       └── metrics.json           (집계 비교 지표)
└── postmortem-aggregate.md        (전 v 누적 학습)

Lab Run 프로토콜

새 v 정의 (Lab 운영자 — 사용자 또는 Claude)
  1. playbooks/v<N>.md 작성. 가설을 한 줄로:
    ## Hypothesis
    v2 raises persona ABANDON budget from 3s → 5s, expecting fewer false-abandon and more useful friction signal.
  2. v<N>이 v<N-1>과 바꾸는 것 정확히 명시. 1개 변수만 바꾸는 게 원칙.
  3. 변경 점이 sub-agent 프롬프트에 있으면 playbooks/v<N>/agents-overrides/*.md로 patch 보관.
Lab Run 실행
bash
# 운영자가 수동 실행
omd harness "<task>" --lab v2
# 또는 사용자가 자연어:
# "이 task를 lab v2 설정으로도 돌려서 v1과 비교해줘"

--lab v<N>이 들어오면:

  • runs/v<N>-run-<ts>-<slug>/ 디렉토리에 산출물 적재
  • v<N>의 agent overrides가 있으면 그걸 임시로 .claude/agents/에 덮어씌운 채 실행 (run 종료 시 원복)
  • run.log에 lab_version: v<N> 기록
비교 뷰 생성

운영자가 동일 task에 대해 v1, v2, ..., vN의 run을 끝내면:

bash
omd lab compare --task "<task-slug>" --versions v1,v2,v3

이게 compare/<task-slug>/index.html을 만든다. 4-패널 (또는 N-패널) 비교:

  • 각 v의 brief.md / 주요 wireframe / DESIGN.md.patch / persona ABANDON 요약 / 토큰 비용
  • 공통 metrics.json: per-v {iterations, total_tokens, persona_abandon_rate, deterministic_pass_rate, jury_score, time_to_handoff}
비교 metrics 정의
json
{
  "task": "토스 스타일 가족 식단 앱 메인",
  "versions": {
    "v1": {
      "iterations": 2,
      "total_tokens_estimated": 320000,
      "persona_abandon_rate": 0.5,
      "deterministic_pass_rate": 1.0,
      "jury_score_normalized": 0.72,
      "time_to_handoff_min": 18,
      "user_satisfied": "?"
    },
    "v2": { ... }
  },
  "delta_v1_v2": "v2 reduced persona_abandon_rate by 0.25 but raised total_tokens by 12% — net win on signal quality"
}

진행 트랙 (이 Lab의 로드맵)

vhypothesisstatus
v1First full implementation — 8 agents, 10 phases, 3 user checkpointsactive baseline
v2(TBD)pending
v3(TBD)pending

playbooks/v1.md가 baseline 정의. 운영자는 매 회 새 가설로 v<N>.md를 추가한다.

postmortem-aggregate.md 정책

매 lab run 종료 시, run의 postmortem.md에서 cross-version-relevant 신호만 발췌해 postmortem-aggregate.md에 누적:

  • 자주 발생하는 deterministic gate 실패
  • persona ABANDON 트리거 빈도 분포
  • 사용자가 가장 자주 reject하는 phase 출력
  • 토큰이 가장 많이 새는 sub-agent

이게 다음 v의 가설을 만들어낸다.

사용 예 (한 줄 시연)

사용자: "토스 스타일 결제 화면 — Lab #02로 v1, v2 비교"
→ Claude: omd harness "..." --lab v1 실행 → v1-run 적재
→ (사용자 체크포인트 진행, ship 결정)
→ Claude: omd harness "..." --lab v2 실행 (동일 brief 재사용 가능)
→ omd lab compare --task <slug> --versions v1,v2
→ compare/<slug>/index.html 결과 제시

금지

  • v 정의 없이 run 적재 X (반드시 playbooks/v<N>.md 선행)
  • 동일 task의 동일 v 결과를 덮어쓰지 X (timestamp로 보존)
  • runs/ 정리 X (영구 보존)

© kwakseongjae, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 61 other files in skills/omd-lab-02-design-harness of kwakseongjae/oh-my-design.

  • SKILL.md
  • playbooks/v1.md
  • playbooks/v2.md
  • runs/live-2026-04-27-water-app/feedback-log.md
  • runs/v4-self-test/README.md
  • runs/v4-self-test/fixtures/founder/README.md
  • runs/v4-self-test/fixtures/junior-designer/package.json
  • runs/v4-self-test/fixtures/junior-designer/src/components/Hero.tsx
  • runs/v4-self-test/fixtures/junior-designer/src/components/Project.tsx
  • runs/v4-self-test/fixtures/senior-dev/package.json
  • runs/v4-self-test/fixtures/senior-dev/src
  • … and 51 more

Open the folder on GitHubat commit c0ec438

Compare with similar skills

Omd Lab 02 Design Harness next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Omd Lab 02 Design Harness compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Omd Lab 02 Design Harness this skillkwakseongjae/oh-my-design533—~908Automated safety check: PassMIT
Agent Readiness Auditdocker/docs4.7k—~1.8kAutomated safety check: PassApache-2.0
Frontend Build Timing Auditopenops-cloud/openops1.1k—~2.3kAutomated safety check: PassCustom licence
Astrodevantler-tech/ksail1653 repos~1.1kAutomated safety check: PassMIT
Trip Map Builderhiyeshu/trip-map-builder244—~1.7kAutomated safety check: PassNone
Reactopenops-cloud/openops1.1k—~1.7kAutomated safety check: PassCustom licence

Similar skills

  • Official

    Audit a documentation site for agent-friendliness: discovery, markdown delivery, crawlability, semantic structure, machine-readable surfaces, and content legibility.

    4.7k GitHub stars~1.8k tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Frontend Build Timing Audit

    openops-cloud/openops

    Detects and diagnoses chunk-evaluation timing bugs in the Vite/rolldown production build of react-ui (works-in-dev / broken-in-build i18n regressions, missing UI labels, module-scope t()…

    1.1k GitHub stars~2.3k tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Astro

    devantler-tech/ksail

    Skill for building with the Astro web framework. An agent skill from devantler-tech/ksail.

    165 GitHub starsUsed in 3 repos~1.1k tokens
    Frontend & DesignAuto-check passed
  • Trip Map Builder

    hiyeshu/trip-map-builder

    End-to-end trip planning: gather user constraints, build a reference itinerary, research locations and dining signals via 大众点评 + 小红书, then generate an interactive mobile-first map page (Leaflet +…

    244 GitHub stars~1.7k tokensUpdated 3 mo ago
    Frontend & DesignAuto-check passed
  • React

    openops-cloud/openops

    A skill your agent uses when creating or editing frontend React code in react-ui or ui-components packages.

    1.1k GitHub stars~1.7k tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Static Deploy

    nexu-io/nexu

    Deploy static pages to nexu.space. An agent skill from nexu-io/nexu.

    3.3k GitHub stars~989 tokensUpdated 5 mo ago
    Frontend & DesignAuto-check passed

More from kwakseongjae/oh-my-design

All 18 skills in this repo
  • Ego Browser

    kwakseongjae/oh-my-design

    When you need a browser, read this Skill by default. An agent skill from kwakseongjae/oh-my-design.

    533 GitHub starsUsed in 1 repo~4.9k tokens
    Auto-check passed
  • Claude Design

    kwakseongjae/oh-my-design

    현재 코드베이스(또는 폴더)를 분석해 "디자인 컨텍스트 브리프"(스택/디자인 토큰/컴포넌트/ 라우트/실제 UI 카피/큐레이션된 에셋/레포 링크)를 합성하고, 그걸 Claude Design (claude.ai/design)에 자동으로 전달해 디자인을 생성한 뒤 결과 링크를 터미널에 클릭 가능한 형태로 돌려주는 스킬.

    533 GitHub stars~4.8k tokensUpdated 10 days ago
    Auto-check passed
  • Omd Aphrodite

    kwakseongjae/oh-my-design

    Maximum-craft one-page landing — the wow bar. An agent skill from kwakseongjae/oh-my-design.

    533 GitHub stars~2.1k tokensUpdated 10 days ago
    Auto-check passed
  • Omd Autopilot

    kwakseongjae/oh-my-design

    One-prompt autonomous product design and implementation. An agent skill from kwakseongjae/oh-my-design.

    533 GitHub stars~9k tokensUpdated 10 days ago
    Auto-check passed
  • Omd Landing

    kwakseongjae/oh-my-design

    Scroll-native one-page landing that overwhelms — concept, composition, asset placement, and scroll choreography derived from DESIGN.md and the measured landing-craft codex.

    533 GitHub stars~2.3k tokensUpdated 10 days ago
    Auto-check passed
  • Omd Media

    kwakseongjae/oh-my-design

    Brand-consistent asset sets from DESIGN.md — hero, section illustrations, icon sets, OG image — generated through whichever channel the user actually has (grok build imagegen, Codex $imagegen…

    533 GitHub stars~1.1k tokensUpdated 10 days ago
    Auto-check passed

Questions about Omd Lab 02 Design Harness

How do I install Omd Lab 02 Design Harness in Claude Code?

Run `npx skills add kwakseongjae/oh-my-design --skill omd-lab-02-design-harness -a claude-code`. Or copy the skill folder (skills/omd-lab-02-design-harness in kwakseongjae/oh-my-design) into .claude/skills/omd-lab-02-design-harness in your project. Claude Code loads it when a task matches its description.

How do I install Omd Lab 02 Design Harness in Codex?

Run `npx skills add kwakseongjae/oh-my-design --skill omd-lab-02-design-harness -a codex`. Or copy the skill folder (skills/omd-lab-02-design-harness in kwakseongjae/oh-my-design) into .agents/skills/omd-lab-02-design-harness in your project. Codex loads it when a task matches its description.

Can I use Omd Lab 02 Design Harness in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add kwakseongjae/oh-my-design --skill omd-lab-02-design-harness -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/omd-lab-02-design-harness, .gemini/skills/omd-lab-02-design-harness, .github/skills/omd-lab-02-design-harness and .opencode/skills/omd-lab-02-design-harness in your project.

What does Omd Lab 02 Design Harness need to run?

SKILL.md names no scripts, command-line tools or credentials: Omd Lab 02 Design Harness is instructions for the agent only.

Does Omd Lab 02 Design Harness access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Omd Lab 02 Design Harness safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Omd Lab 02 Design Harness use?

Omd Lab 02 Design Harness is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Omd Lab 02 Design Harness use?

About 908 tokens (SKILL.md is roughly 3.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Omd Lab 02 Design Harness?

Skills that share tags, products or a category with Omd Lab 02 Design Harness: Agent Readiness Audit (docker/docs, 4.7k stars), Frontend Build Timing Audit (openops-cloud/openops, 1.1k stars), Astro (devantler-tech/ksail, 165 stars) and Trip Map Builder (hiyeshu/trip-map-builder, 244 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Omd Lab 02 Design Harness?

kwakseongjae (a GitHub user) maintains it in kwakseongjae/oh-my-design, which has 533 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 1, 2026.

Source: kwakseongjae/oh-my-design on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.