MVPavan/via / .claude/skills/html-artifact
html-artifact
VerifiedUse for requested standalone HTML documents or interactive explanations when that format materially helps. Skip agent-facing files, Markdown-native deliverables, and ordinary short answers.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.4 KB |
| agents/openai.yaml | config | 42 B |
| references/preset-dashboard.md | markdown | 2.4 KB |
| references/preset-editor.md | markdown | 3.5 KB |
| references/preset-explainer.md | markdown | 2.6 KB |
| references/preset-report.md | markdown | 3.7 KB |
| references/svg-craft.md | markdown | 4.2 KB |
| references/visual-style.md | markdown | 4.1 KB |
SKILL.md
View on GitHub---
name: html-artifact
description: Use for requested standalone HTML documents or interactive explanations when that format materially helps. Skip agent-facing files, Markdown-native deliverables, and ordinary short answers.
---
# HTML Artifact
Create a self-contained HTML document for human reading or interaction. Use it
when explicitly requested or when a standalone visual materially helps explain,
compare or explore the content. A report, plan or one-pager alone is not a trigger.
Keep agent instructions, source documents and Markdown-native deliverables in
Markdown; brief inline explanations need no HTML scaffold.
## Artifact contract
- One file with inline CSS/JS, viewport metadata and no build step. Work offline
from a local file: no external fonts, trackers, API fetches or runtime assets.
- Semantic markup, keyboard access and adequate contrast. Layout adapts to narrow
screens; honor reduced motion for animation and provide readable print styles.
- Explanatory content exists before scripts run. With JS disabled, preserve the
explanation, data and limitations even when interactive computation is unavailable.
- Use project visual conventions where compatible with this contract. Show only
sourced data; label assumptions and illustrative values explicitly.
## Choose the shape
Select the matching preset when its layout helps:
| Main purpose | Reference |
|---|---|
| Narrative report or comparison | `references/preset-report.md` |
| Charts carry the argument | `references/preset-dashboard.md` |
| Teach a concept | `references/preset-explainer.md` |
| User edits values or copies a configuration | `references/preset-editor.md` |
For an unfamiliar figure, consult `references/svg-craft.md`; for optional default
styling/components, use `references/visual-style.md`. Read only relevant sections,
and do not invent content to satisfy a preset. Prefer a simpler shape when it
communicates the source faithfully.
## Deliver and verify
Use the supplied output location, otherwise a descriptive file under scratchpad.
Provide a link/path rather than pasting HTML source. Check content fidelity and
local links, then exercise key interactions and responsive/print behavior using
available browser tools. Inspect JS-disabled readability and motion settings when
relevant. Report checks that could not run; do not automatically assign them to
the user. Name material omissions or transformations when condensing a source.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |