本文へ移動
cccskills
無料GitHub で公開

stitch-design

Route Google Stitch tasks to the correct imported Stitch skill, with verified MCP tool boundaries, upload safety, and cross-client fallback guidance.

インストール方法を見る

含まれるファイル(3)

  • SKILL.md8.6 KB
  • CHANGELOG.md6.1 KB
  • LICENSE.txt11.0 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Stitch Design

Use this as the entrypoint for Google Stitch work. The old local monolithic Stitch guidance has been consolidated into narrower skills imported from https://github.com/google-labs-code/stitch-skills at commit 7b53207b94e62911777d53d4238b5f8c88c2b519. This file now routes tasks and carries shared safety rules; detailed workflows live in the dedicated stitch-* skills.

When to Use This Skill

  • The user asks for Stitch, Google Stitch, Stitch MCP, DESIGN.md, Stitch screen generation, Stitch upload, or Stitch-to-code work.
  • The task is unclear and needs routing to the correct Stitch design, build, or utility workflow.
  • A previous broad Stitch workflow would have mixed upload, prompt, design-system, code, and video steps in one place.

Route Selection

SkillUse when
stitch-code-to-designConvert an existing frontend into Stitch-ready design assets by extracting static HTML, writing DESIGN.md, creating the design system, and uploading approved files.
stitch-generate-designPrepare Stitch screen-generation, edit, image-to-design, and variant prompts with verified tool checks and design-system-aware wording.
stitch-manage-design-systemCreate, list, and apply Stitch design systems from DESIGN.md using the verified Stitch MCP design-system tools and safe upload fallbacks.
stitch-extract-design-mdExtract a Stitch-compatible DESIGN.md from frontend source code, stylesheets, Tailwind config, theme files, and component patterns.
stitch-extract-static-htmlCapture a self-contained static HTML snapshot from a running app or mock component so it can be reviewed or uploaded to Stitch.
stitch-upload-to-stitchUpload approved local HTML, markdown, or image assets to a Stitch project using direct MCP for small DESIGN.md files or the bundled API script for larger files.
stitch-react-componentsConvert Stitch HTML and screenshots into modular Vite/React/TypeScript components, or sync existing components to updated Stitch designs, with local architecture and validation checks.
stitch-react-vite-dashboardConvert approved Stitch exports into accessible React and Vite dashboards with DESIGN.md tokens, TanStack Query data boundaries, responsive layouts, and optional read-only Web3 integrations.
stitch-react-nativeConvert Stitch HTML designs into React Native screens, or sync existing native components to updated Stitch designs, using native primitives, StyleSheet rules, and mobile platform checks.
stitch-remotionCreate Remotion walkthrough videos from Stitch screen exports with ordered assets, transitions, captions, and render checks.
stitch-shadcn-uiIntegrate Stitch-derived UI direction into shadcn/ui React projects with registry-aware setup, ownership rules, theming, and validation.
stitch-design-mdAnalyze existing Stitch project evidence and synthesize a semantic DESIGN.md for consistent future Stitch generation.
stitch-enhance-promptTransform rough UI requests into structured Stitch prompts with platform, layout, component, and design-system context.
stitch-loopRun an iterative Stitch website-building loop using .stitch/next-prompt.md, SITE.md, DESIGN.md, generated pages, and verification checkpoints.
stitch-taste-designCreate opinionated premium DESIGN.md guidance for Stitch, emphasizing calibrated typography, restrained color, layout discipline, motion, and anti-generic UI rules.

Consolidation Decision

The previous stitch-design skill repeated design-md, React conversion, build-loop, prompt-enhancement, Remotion, and shadcn/ui guidance in one large file. Those important parts were not removed; they were moved into dedicated skills with clearer triggers, support assets, and verification protocols. This entrypoint stays small so agents choose the narrowest Stitch workflow first.

Verified Stitch MCP Surface

Verified in this workspace on 2026-06-15: create_project, upload_design_md, create_design_system_from_design_md, list_design_systems, and apply_design_system. This 2026-07-29 source refresh did not re-verify a broader live MCP surface. Treat screen lookup, screen generation, screen editing, and variant generation tools as optional host-specific capabilities. Use them only when they are present in the active tool list.

Common Workflow

  1. Classify the task as prompt work, design-system work, static extraction, upload, screen generation, code generation, video generation, or iterative site building.
  2. Open and follow the narrowest related Stitch skill.
  3. Check the available Stitch MCP tools before naming or calling a tool.
  4. Keep .stitch/DESIGN.md, .stitch/metadata.json, screenshots, and static HTML as the local evidence trail when the workflow creates them.
  5. Ask before external uploads unless the current user request already approves that exact upload target and artifact.
  6. Verify with Stitch MCP when the requested operation matches the available tool surface; otherwise document the web UI/API/local fallback used.

Anti-Patterns

  • Using this entrypoint as a replacement for reading the dedicated skill that matches the task.
  • Claiming unavailable Stitch MCP screen tools exist because an upstream skill mentioned them.
  • Uploading assets or creating external Stitch state without a clear project target and approval.
  • Combining Stitch-specific skills into generic frontend skills when Stitch project IDs, DESIGN.md, or MCP evidence matter.

Verification Protocol

Before claiming Stitch work is complete:

  1. Pass/fail: The correct dedicated Stitch skill was selected and followed.
  2. Pass/fail: The active Stitch MCP tool surface was checked and any unavailable tools were handled honestly.
  3. Pass/fail: Local artifacts or external Stitch IDs were recorded with enough detail to reproduce the result.
  4. Pass/fail: Uploads and external state changes had user-approved artifact and destination details.
  5. Pressure-test scenario: Re-run the route selection with only the verified design-system MCP tools available and confirm the fallback path still works.
  6. Success metric: The final response names the selected Stitch skill, evidence used, and whether verification was local, MCP-backed, or manual.
<!-- MCP:START --> <!-- PORTABILITY:START -->

Cross-Client Portability

This skill is written to stay usable across GitHub Copilot, Claude Code, and Codex.

  • GitHub Copilot: keep the folder in a Copilot-visible skill path or wrap the workflow in project instructions when folder discovery is unavailable.
  • Claude Code: keep the folder in a local skills directory or a compatible plugin source.
  • Codex: install or sync the folder into $CODEX_HOME/skills/stitch-design and restart Codex after major changes.
<!-- PORTABILITY:END -->

MCP Availability And Fallback

Preferred MCP Server: Stitch MCP

  • Fallback prompt: "Use the Stitch Design router without Stitch MCP. Route to the correct local Stitch skill, use local artifacts or the Stitch web UI where needed, and show the exact evidence used before concluding."
  • Use screenshots, exported HTML, DESIGN.md files, local scripts, and metadata files when Stitch MCP is not exposed by the host.
  • Treat generated React, design assets, and uploaded screens as drafts until verified through local render, Stitch MCP, or the Stitch UI.
<!-- MCP:END -->

Related Skills

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

AI-powered adeno-associated virus (AAV) vector design for gene therapy including capsid engineering, promoter selection, and tropism optimization.

日本語の概要は準備中です。原文の説明を表示しています。

bg-szy/TOP-SKILLS62026年9月8日 更新

Improve the clarity and voice of AI-assisted academic writing (papers, theses, rebuttals) and

日本語の概要は準備中です。原文の説明を表示しています。

bg-szy/TOP-SKILLS62026年9月8日 更新

12-agent academic paper writing pipeline. 11 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure/rebuttal-audit). 6 paper types, 5 citation formats, bilingual abstracts, LaTeX/DOCX-via-Pandoc/PDF output. Style Calibration + Writing Quality Check + Anti-Patterns with IRON RULE markers. Triggers: write paper, academic paper, guide my paper, parse reviews, audit my rebuttal, check my response draft, AI disclosure, 寫論文, 學術論文, 引導我寫論文, 審查意見, 評估回覆, 논문 작성, 초록 작성, 논문 수정, 논문 계획을 도와줘, 심사 의견 반영, 답변서 점검, AI 사용 고지.

日本語の概要は準備中です。原文の説明を表示しています。

bg-szy/TOP-SKILLS62026年9月8日 更新

Systematic writing framework for philosophy and interdisciplinary academic papers from optimized outline to submission-ready manuscript. Use when users want to: (1) write a paper from a detailed outline, (2) ensure quality control during writing, (3) maintain consistency across chapters, (4) prepare a submission-ready manuscript, or (5) systematically execute a planned paper. Triggered by phrases like 'write the paper from this outline,' 'compose the full manuscript,' 'execute the outline,' or when users have completed strategic planning (academic-paper-strategist skill) and are ready to write. Takes optimized outline as input; outputs complete manuscript with iterative quality checks.

日本語の概要は準備中です。原文の説明を表示しています。

bg-szy/TOP-SKILLS62026年9月8日 更新

Multi-perspective academic paper review with dynamic reviewer personas. Runs a 5-seat, role-separated review panel (Journal-Fit Reviewer + 3 peer-review roles + Devil's Advocate) with field-specific expertise; role separation is not a claim of independent error processes. Supports full review, re-review (verification), quick assessment, methodology focus, Socratic guided, and calibration modes. Triggers on: review paper, peer review, manuscript review, referee report, review my paper, critique paper, simulate review, editorial review, calibrate reviewer, reviewer calibration, measure reviewer accuracy, 審查論文, 論文審查, 模擬審查, 同儕審查, 幫我審這篇, 以審查人角度評估, 審查者校準, 논문 심사, 동료 심사, 모의 심사, 심사자 관점에서 평가, 심사자 보정.

日本語の概要は準備中です。原文の説明を表示しています。

bg-szy/TOP-SKILLS62026年9月8日 更新

Systematic strategic planning framework for philosophy and interdisciplinary academic papers targeting preprint platforms (PhilArchive, arXiv, PhilSci-Archive). Use when users want to: (1) plan a paper on a specific topic, (2) identify research gaps and assess originality, (3) develop optimized paper outlines, (4) prepare for preprint submission, or (5) understand platform requirements and writing standards. Triggered by phrases like 'plan a paper on,' 'help me design a paper about,' 'identify research gaps in,' 'is this idea original,' or when users need structured research planning. The skill guides through three phases: Platform Analysis (identifying target venue and studying sample papers), Theoretical Framework (AI-driven literature search and gap identification), and Outline Optimization (structured design with reviewer-perspective self-assessment). Each phase includes quality evaluation standards and validation checkpoints.

日本語の概要は準備中です。原文の説明を表示しています。

bg-szy/TOP-SKILLS62026年9月8日 更新

bg-szy のスキルをすべて見る

このスキルの問題を報告する