design-to-html
Skill1 starsChanged 57 days agoMITView on GitHub
Turn an approved design or description into clean, dependency-free HTML.
In this repository67 other files it gives its agents.
- architect-reviewerSkill
- backend-architectSkill
- backend-developerSkill
- code-architectSkill
- codebase-explorerSkill
- code-reviewerSkill
- code-simplifierSkill
- debuggerSkill
- error-detectiveSkill
- fullstack-developerSkill
- git-workflow-managerSkill
- legacy-modernizerSkill
- pragmatic-architectSkill
- prdSkill
- qa-expertSkill
- research-technical-spikeSkill
- sdd-spec-writerSkill
- security-auditorSkill
- supply-chain-securitySkill
- task-decomposition-expertSkill
- technical-debt-managerSkill
- test-engineerSkill
- typescript-proSkill
- architecture-decision-recordsSkill
- hermes-sdd-packagingSkill
- bug-diagnosisSkill
- build-craftSkill
- code-healthSkill
- code-review-checklistSkill
- commit-smartSkill
- context-architectureSkill
- design-explorationSkill
- developer-experience-reviewSkill
- diagram-tripletSkill
- dispatching-parallel-agentsSkill
- document-diataxisSkill
- e2e-testing-patternsSkill
- executing-plansSkill
- module-designSkill
- openspec-apply-changeSkill
- openspec-archive-changeSkill
- openspec-bulk-archive-changeSkill
- openspec-continue-changeSkill
- openspec-exploreSkill
- openspec-ff-changeSkill
- openspec-new-changeSkill
- openspec-onboardSkill
- openspec-proposeSkill
- openspec-sync-specsSkill
- openspec-update-changeSkill
- openspec-verify-changeSkill
- plan-scope-reviewSkill
- project-learningsSkill
- qa-test-plannerSkill
- requirements-claritySkill
- review-structuralSkill
- security-evidence-firstSkill
- agency-invocationSkill
- hermes-sdd-orchestrationSkill
- openspec-sddSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 30
Verify rendering (view it / measure) and that it reflows at a narrower width and a larger text scale.
- Distinctive: line 36
No speculative framework or component library "just because".
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<!-- hermes-add-skill: concept adapted from gstack /design-html (garrytan/gstack, MIT). The gstack
runtime (Pretext) is not portable here; this keeps the *standard*: approved design → self-contained
HTML, text that reflows, no heavy deps. -->Design to HTML
Turn an approved design (mockup, layout, or a clear user description) into clean, self-contained, production-quality HTML/CSS with zero or minimal runtime dependencies.
What "good" means here
- The text actually reflows — layout adapts to content, heights are computed, nothing is a fixed-pixel box that breaks at a different font scale or width.
- Zero/small deps — the page carries its own CSS; no framework loaded for a static page unless the project already uses one.
- Matches the design — spacing, hierarchy, typography and color follow the approved mockup, not a reinterpretation.
- Correct semantics (headings, landmarks, labels) and keyboard/screen-reader usability come standard, not as an afterthought.
Workflow
- Confirm the design is approved and named; if it's a description without an approved shape, that's a design step, do the design first.
- Build the page as self-contained HTML/CSS per the design.
- Verify rendering (view it / measure) and that it reflows at a narrower width and a larger text scale.
- Report the file and what was verified (per
rules/quality.md).
Rules
- No speculative framework or component library "just because". If it doesn't need a runtime, it doesn't get one.
- A design you don't fully understand is a question, not a guess — ask before building.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

