design-to-code is agent-read markdown (skill) from nahid-sparktales/agent-dispatcher: Turn a design, mockup, Figma frame or screenshot into implementation that actually matches it — mapping values to the codebase's existing tokens and components, covering the states the design never drew, and listing what the design left ambiguous instead of guessing. Use when handed a design to build, when asked whether an implementation matches its source, or when a build has drifted from the design. Not for deciding what the design should be, and not by itself proof that the screen works..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Design to code
A design is a set of still frames of the happy path. The implementation is every state, every
width, and every interaction. Most of the gap between them is not fidelity — it is the frames that
were never drawn.
## When this fires
A design file, mockup, screenshot or redline is the source for a UI change, or an existing
implementation is being compared against one. It does not fire when there is no design source and
the visual direction is yours to invent.
## Procedure
1. **Read the source for structure before pixels.** Find the repeating unit, the hierarchy, and
which pieces are instances of something the design system already has versus one-offs drawn for
this screen. Building a one-off as a component, or a component as a one-off, costs more later
than any spacing error.
2. **Take values from the source, not from the picture.** Where the design tool exposes variables,
tokens, styles or layer measurements, read them. Measuring a screenshot yields a scaled
approximation, and approximations accumulate. If you only have an image, say so — that changes
what "matches" can mean.
…
Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
GET https://markdownregistry.com/api/v1/artifacts/art_f3v6kysepl47i5vt
GET https://markdownregistry.com/api/v1/resolve?ref=nahid-sparktales/agent-dispatcher/design-to-code
GET https://markdownregistry.com/api/v1/blob/b01d11be1066cfd4ad7666a400a1e12e2a204b19688fae688bacacb08b2966c5
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
nahid-sparktales/agent-dispatcher · skills/agent-dispatcher/SKILL.md · Route work to a specialist role and load its task-specific guidance. Use when the user invokes /agent-dispatcher, names…
nahid-sparktales/agent-dispatcher · skills/ai/agent-design/SKILL.md · Scope an agent or subagent before it is built — the one job it owns, the smallest tool set that closes that job, what…
nahid-sparktales/agent-dispatcher · skills/ai/agent-evals/SKILL.md · Build an eval suite that can actually detect a regression — cases pulled from real traffic, graders that check…
nahid-sparktales/agent-dispatcher · skills/ai/context-engineering/SKILL.md · Decide what actually occupies the model's window — progressive disclosure through an index, retrieval versus inlining…
nahid-sparktales/agent-dispatcher · skills/ai/llm-observability/SKILL.md · See what an agent actually did — one trace per run with nested model, tool and retrieval spans, token and latency…
nahid-sparktales/agent-dispatcher · skills/ai/mcp-design/SKILL.md · Build an MCP server, or bring an existing one into a project — choosing the transport, deciding which tools, resources…
nahid-sparktales/agent-dispatcher · skills/ai/memory-design/SKILL.md · Decide what an agent should remember, which layer holds it, who it is scoped to, and how a stale or contradicted memory…
nahid-sparktales/agent-dispatcher · skills/ai/model-routing/SKILL.md · Pick a model per job and degrade sensibly when one fails — a quality bar per call site, candidates compared on the same…
nahid-sparktales/agent-dispatcher · skills/ai/prompt-engineering/SKILL.md · Write or revise a prompt so it holds up — output contract, instruction placement, examples that earn their place, an…
nahid-sparktales/agent-dispatcher · skills/ai/prompt-injection-defense/SKILL.md · Treat everything an agent reads but did not author as data rather than instructions — an explicit trust boundary, a…
nahid-sparktales/agent-dispatcher · skills/ai/retrieval-rag/SKILL.md · Build and fix retrieval that actually returns the right passage — structure-aware chunking, one pinned embedding model…
nahid-sparktales/agent-dispatcher · skills/ai/structured-output/SKILL.md · Get parseable, trustworthy structured results out of a model — schema design, the enforcement mechanism the provider…
yonatangross/orchestkit · src/skills/design-to-code/SKILL.md · Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts a screenshot, a description, or…
yonatangross/orchestkit · plugins/ork/skills/design-to-code/SKILL.md · Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts a screenshot, a description, or…
jpeetz/agent-skills · skills/frontend/design-to-code/SKILL.md · Use this skill when translating UI/UX designs into production-ready frontend code. Handles design source ingestion…
jdanigo/hydraia · skills/design-to-code/SKILL.md · Elite render-to-code skill. The user brings a finished website design render (jpg/png); this skill distills it into…