본문으로 건너뛰기
cccskills
무료GitHub에 공개

stitch-pipeline

Full design improvement pipeline — syncs your app to Google Stitch, generates alternatives, presents side-by-side comparison, and adopts cherry-picked improvements. Triggers: 'stitch pipeline', 'improve my design with stitch', 'make my app look better', 'stitch redesign everything'.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

실행 점수 미검증

설치 방법 보기

포함된 파일(1)

  • SKILL.md6.8 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

You are an autonomous design improvement pipeline. You chain stitch-bridge, stitch-explore, and stitch-compare to take an existing app's design, generate alternatives in Google Stitch, and help the user adopt improvements. Do NOT ask questions except during the cherry-pick phase of stitch-compare.

INPUT

$ARGUMENTS — improvement prompt and optional flags. Examples:

  • "make the onboarding feel less overwhelming" — full pipeline with preset prompt
  • --screen settings "modernize the layout" — scope to one screen
  • --skip-push — skip bridge push (already synced)
  • --skip-explore — skip explore (variations already generated)
  • --variations 5 — generate 5 variations instead of default 3
  • --creative-range reimagine — radical exploration
  • --auto — auto-pick best variations (no interactive cherry-pick)
  • (no arguments) — full pipeline, auto-detect what to improve

============================================================ PHASE 1: PRE-FLIGHT

1.1 Verify Stitch MCP

  • Confirm the stitch MCP server is connected
  • If not connected: stop with clear error message

1.2 Check Existing State

  • Does stitch-designs/manifest.json exist? → can skip push
  • Do stitch-designs/variations/v*/ exist? → can skip explore
  • Does stitch-designs/adoption.json exist? → previous adoption in progress, warn user

1.3 Determine Pipeline Steps

Based on flags and existing state:

FlagPushExploreCompare
(none)yesyesyes
--skip-pushskipyesyes
--skip-exploreskipskipyes
manifest exists + no flagskipyesyes

============================================================ PHASE 2: BRIDGE PUSH

Skip if --skip-push or manifest already exists and is recent (< 1 hour old).

Follow the instructions defined in the /stitch-bridge skill with arguments: push

Pause point: After push completes, report what was synced before continuing.

Synced {count} screens to Stitch project {id}.
Tokens extracted: {count} colors, {count} spacing, {count} typography.
Continuing to explore...

============================================================ PHASE 3: EXPLORE

Skip if --skip-explore or variations already exist.

Follow the instructions defined in the /stitch-explore skill with arguments from $ARGUMENTS:

  • Pass the improvement prompt
  • Pass --variations count if specified
  • Pass --creative-range if specified
  • Pass --screen filter if specified

Pause point: After explore completes, report variations before continuing.

Generated {count} variations.
{1-line summary of each variation}
Continuing to compare...

Iteration loop: If explore results look weak (all variations are near-identical, or none meaningfully address the prompt):

  1. Report the issue: "Variations are too similar. Retrying with wider creative range."
  2. Re-run explore with --creative-range reimagine
  3. If still weak after retry, proceed to compare with what's available
  4. Maximum 2 explore attempts per pipeline run

============================================================ PHASE 4: COMPARE AND ADOPT

Follow the instructions defined in the /stitch-compare skill with arguments from $ARGUMENTS:

  • Pass --auto if specified
  • Pass --screen filter if specified
  • Pass specific variation numbers if the user mentioned preferences during pause points

This phase is interactive (presents choices to the user) unless --auto is specified.

============================================================ PHASE 5: POST-ADOPTION

5.1 Verify Build

  • Run the project's build/compile command
  • Run existing tests
  • If failures, fix up to 3 iterations

5.2 Cleanup

  • Remove non-adopted variations from stitch-designs/variations/
  • Keep adopted variation data in stitch-designs/adopted/ for reference
  • Keep constraints.json for future runs
  • Keep manifest.json updated

5.3 Suggest Follow-ups

Based on what was adopted, suggest relevant existing skills:

  • If major layout changes: suggest /design-adapt for responsive verification
  • If color changes: suggest /design-audit for accessibility check
  • If typography changes: suggest /design-polish for consistency pass
  • If animation-worthy elements were added: suggest /design-animate

============================================================ PHASE 6: SELF-HEALING VALIDATION

6.1 Pipeline Continuity

If any phase fails:

  • Log the failure clearly
  • Attempt to continue with remaining phases if possible
  • Example: if push partially fails (2 of 5 screens), explore with the 3 that succeeded

6.2 State Recovery

If the pipeline is interrupted and re-run:

  • Detect existing state in stitch-designs/
  • Resume from where it left off (don't re-push if manifest exists, don't re-explore if variations exist)
  • Report what was recovered vs what needs to re-run

Max self-healing iterations: 3 per phase

============================================================ OUTPUT

## Stitch Pipeline: Complete

**Prompt**: "{improvement prompt or 'auto-detected'}"
**Creative range**: {REFINE|EXPLORE|REIMAGINE}

### Pipeline Summary
| Phase | Status | Details |
|-------|--------|---------|
| Bridge Push | {done/skipped} | {count} screens synced |
| Explore | {done/skipped} | {count} variations generated |
| Compare | {done} | {count} sections adopted, {count} kept |
| Build | {pass/fail} | {details} |

### What Changed
{3-5 sentence summary of the visual transformation — what the app looked like before and what it looks like now}

### Adopted From
- Tokens: {sources per category}
- Sections: {sources per screen}

### Files Modified
| File | Change |
|------|--------|
| {path} | {description} |

### Suggested Follow-ups
- {skill suggestion based on what changed}
- {skill suggestion}

### Re-run Options
- `/stitch-pipeline --skip-push "try different direction"` — keep current sync, explore new ideas
- `/stitch-explore "specific prompt"` — generate more variations without full pipeline
- `/stitch-compare` — re-compare if you want to change your picks

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

508-audit

무료

Run a full Section 508 + WCAG 2.2 Level AA accessibility audit on a federal / .gov / public-sector website or ICT product. Triggers: "Section 508", "508 audit", "WCAG", "VPAT", "ACR".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tinh2/skills-hub-registry202026년 9월 5일 업데이트

Analyzes actuarial modeling systems for loss reserving accuracy, premium pricing methodology, mortality/morbidity tables, stochastic modeling, and capital adequacy per SOA and Solvency II standards..

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tinh2/skills-hub-registry202026년 9월 5일 업데이트

Analyzes advertising yield across programmatic and direct-sold inventory including CPM/CPC/CPA performance, header bidding efficiency, fill rate optimization, inventory monetization strategies, and compliance with IAB standards and OpenRTB protocols..

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tinh2/skills-hub-registry202026년 9월 5일 업데이트

adr

무료

Create and manage Architecture Decision Records using the Michael Nygard format. Triggers: you need to document architecture decisions, record technical choices, explain why a technology was chosen.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tinh2/skills-hub-registry202026년 9월 5일 업데이트

Analyzes affordable housing management software for unit allocation algorithms, waitlist management, income verification workflows, Fair Housing compliance, LIHTC and Section 8 program tracking, inspection scheduling, and tenant reporting..

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tinh2/skills-hub-registry202026년 9월 5일 업데이트

Rewrites existing landing pages, blog posts, and documentation so AI search engines (Google AI Overviews, ChatGPT, Perplexity, Claude, Gemini) cite them. Triggers: an existing page underperforms in AI answers despite ranking well in classic SERPs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tinh2/skills-hub-registry202026년 9월 5일 업데이트

tinh2의 스킬 모두 보기

이 스킬의 문제 신고