HTML Anything

Markdown is the draft. HTML is what humans read. Your local agent writes it. The agentic HTML editor — in the agentic era, you don't hand-edit docs anymore, so the output format should be what the reader actually wants: HTML. Local-first, zero API key, reuses the CLI session you already have logged in — 8 coding-agent CLIs auto-detected on your PATH (Claude Code · Cursor Agent · Codex · Gemini CLI · GitHub Copilot CLI · OpenCode · Qwen Coder · Aider), driven by 75 composable skill templates across 9 deliverable surfaces (magazine articles · keynote decks · résumés · posters · Xiaohongshu cards · tweet cards · web prototypes · data reports · Hyperframes videos). One-click export to WeChat / X / Zhihu, or download .html / .png.

English · 简体中文

Showcase

The eight skills that surface at the top of the picker's Featured / 推荐 group — sorted by their recommended: rank in SKILL.md frontmatter (lower = higher). Each ships a real example.html you can open straight from the repo, no auth, no setup.

deck-guizang-editorial · deck · recommended: 1 Magazine × e-ink editorial deck, inspired by op7418/guizang-ppt-skill — 10 locked layouts × 5 palettes (Ink / Indigo Porcelain / Forest Ink / Kraft / Dune). Reads like a printed art-zine, not a slide deck.	deck-swiss-international · deck · recommended: 2 Swiss International deck — 16-column grid + one saturated accent (Klein Blue / Lemon / Mint / Safety Orange) across 22 locked layouts. Cold, rational, institutional. The deck that reads "a designer made this" the moment it opens.
doc-kami-parchment · doc · recommended: 3 Warm-parchment editorial document, inspired by tw93/kami. #f5f4ed ground + ink-blue accent + single serif voice — a noticeably calmer reading surface than plain-white markdown for long essays, reports, and one-pagers.	magazine-poster · poster · recommended: 4 Newsprint Sunday-paper poster — oversized serif headline, two-column body, six numbered sections, dot-pattern cream ground. Reads like a printed broadsheet, not a webpage.
video-hyperframes · frame / video · recommended: 5 Hyperframes / Remotion-compatible storyboard — 6–10 sequential 1920×1080 frames with hidden duration + transition markers and an auto-play script. Hand straight to heygen-com/hyperframes or Remotion to render .mp4.	frame-glitch-title · frame · recommended: 6 Glitch title frame — cyan/magenta chromatic offset, CRT scanlines, corrupted-data subtitle, ASCII noise in the corners. Cyberpunk hero card or video transition.
vfx-text-cursor · vfx · recommended: 7 VFX text-cursor opener — a cursor "types" across the canvas, each character revealed with a hot-pink × cyan chromatic trail and directional light leaks. Drop in a quote, get a film-grade opening frame.	frame-logo-outro · frame · recommended: 8 Logo outro frame — logo assembles piece-by-piece with glow bloom, tagline rises, CTA appears. The closing card for a product reveal or brand film.

The full skill catalog (organized by mode) is in Skills below.

Why this exists

Anthropic's Claude Code team announced they stopped writing internal docs in Markdown — they ship HTML now. The argument is simple:

HTML is the final form for humans. Markdown is just an intermediate state during writing.

But "writing HTML" used to mean writing CSS, picking type scales, snapping to a grid, doing responsive — most users won't, designers won't bother, writers don't have the patience. So what we built: after you press ⌘+Enter, your local AI agent turns any input (Markdown / CSV / Excel / JSON / SQL / raw notes) into a ship-ready single-file HTML in seconds, then one-click sends it to WeChat / X / Zhihu / anywhere. "Ship-ready" is the bar — when generation finishes, the artifact is what your audience actually sees. No "I'll touch it up later" pass.

We stand on four open-source shoulders:

• nexu-io/open-design — the agent-detection layer, the design-system model, and the SKILL.md protocol. src/lib/agents/ and src/lib/templates/skills/* mirror this architecture directly.
• mdnice/markdown-nice — proof that juice-inlined CSS pastes cleanly into WeChat and Zhihu without per-platform manual fix-up.
• gcui-art/markdown-to-image — the iframe → high-DPI PNG export path.
• alchaincyf/huashu-md-html — the anti-AI-slop discipline that maps into the hard constraints inside every SKILL.md (CJK-first font stack, 8 px baseline grid, contrast ≥ 4.5, must-use-real-data rule).

At a glance

Demo

Entry view — the top bar shows your installed CLIs, the left pane is the editor, the middle is the template + design-system picker, the right is a live iframe preview. The same surface produces magazines, decks, posters, web prototypes, and Hyperframes frame scripts.	75 templates, searchable and filterable — pick by mode (prototype / deck / frame / social / office / doc) × scenario (design / marketing / engineering / product / personal). Every skill ships an example.html you can open straight from the repo to see what the agent will produce.
SSE streaming — agent stdout JSON-line is parsed for text deltas, appended into the iframe srcdoc in real time. You watch the page render line by line. Don't like where it's going? Interrupt and re-prompt — no wasted full generation.	One-click export — WeChat (juice-inlined CSS) · X / Weibo / Xiaohongshu (modern-screenshot → 2× PNG → ClipboardItem) · Zhihu (LaTeX image placeholders) · download .html · download .png. Paste straight in, no second pass of manual formatting.
Deck mode — 20 keynote skills, including Swiss International (Helvetica grid maximalism), Guizang Editorial (magazine ink), Open Slide Canvas (1920×1080 agent-native), Magazine Web, XHS Pastel, Hermes Cyber, Replit Style. ←/→ to navigate slides, presenter notes, PDF export.	Hyperframes frames — 10 motion frame scripts (liquid hero, NYT data chart, sticky-note flowchart, glitch title, cinema light-leak, macOS notification, brand logo outro, text-cursor VFX, 3D device mockup, …) conforming to heygen-com/hyperframes; hand off straight to Remotion to render .mp4.

Quickstart

git clone https://github.com/nexu-io/html-anything
cd html-anything
pnpm install
pnpm dev
# → http://localhost:3000

Open the browser → the top bar auto-detects whichever coding-agent CLI you already have signed in → pick a template → paste content → ⌘+Enter.

No API key required. We reuse the session you already have logged in (Claude / Cursor / Codex / Gemini / Copilot subscriptions all work).

Supported coding agents

On startup we scan PATH (including ~/.local/bin, ~/.bun/bin, /opt/homebrew/bin, ~/.npm-global/bin — directories normally missed by GUI-launched Node) and surface every CLI we recognize:

The detection strategy and per-CLI adapter shape are borrowed directly from nexu-io/open-design and multica-ai/multica: one privileged process spawns CLIs, JSON-line is the wire protocol, every CLI gets a thin adapter in src/lib/agents/argv.ts.

If you've already done claude login / cursor login / gemini auth in your terminal, HTML Anything reuses that session. No second copy of the API key required.

Skills

75 skills under src/lib/templates/skills/, each a folder following the Claude Code SKILL.md convention plus an extended frontmatter (mode · scenario · surface · preview · design_system).

The two axes the picker uses:

• mode — prototype (web / SaaS landing / dashboard / data report / résumé / doc) · deck (20 horizontal-swipe presentations) · frame (10 Hyperframes motion frames) · social (4 social-card formats) · office (PM / engineering / finance / HR / operations document surfaces).
• scenario — design · marketing · engineering · product · finance · hr · sale · personal. Used to group skills in the picker.

Web prototypes & marketing pages (prototype mode)

Decks (deck mode, 20 skills)

Hyperframes video frames & VFX & device mockups (frame / vfx / mockup, 12 skills)

Frame scripts conform to the heygen-com/hyperframes spec and hand off straight to remotion-dev/remotion to render .mp4.

Social share cards (social mode)

Office & operations (office / doc mode)

Adding a skill takes one folder. Copy a similar skill, edit its SKILL.md frontmatter, restart pnpm dev, the picker shows it. See CONTRIBUTING.md for the bar a skill PR has to clear before we merge.

Six load-bearing ideas

1 · We don't ship an agent. Yours is good enough.

On boot the browser calls /api/agents. The server scans PATH — including the dirs a GUI-launched Node usually misses (~/.local/bin, ~/.bun/bin, /opt/homebrew/bin, ~/.npm-global/bin) — and surfaces whichever CLIs it finds. Each CLI has one adapter (argv + stdin protocol + stream parser) in src/lib/agents/argv.ts. The whole detection model is borrowed directly from nexu-io/open-design and multica-ai/multica: one privileged process spawns CLIs, JSON-line is the wire protocol.

2 · Skills are folders, not plugins.

Following Claude Code's SKILL.md convention — SKILL.md + assets/ + references/ + example.html. Drop a folder into src/lib/templates/skills/, restart pnpm dev, the picker shows it. deck-guizang-editorial is vendored directly from op7418/guizang-ppt-skill with original LICENSE and authorship preserved.

3 · Hard constraints stop the model from freestyling.

Every template hardcodes:

• CJK-first font stack — Noto Sans/Serif SC / source-han for Chinese, Inter / Manrope for Latin.
• 8 px baseline grid — every spacing, line-height, font-size is a multiple of 8.
• Rounded corners · soft shadow · no pure black / pure white — visual de-slop-ification.
• Color contrast ≥ 4.5, every interactive element has a real :focus state.
• Must use the user's real data, no lorem ipsum.

The discipline is lifted from alchaincyf/huashu-design's Junior-Designer mode + anti-AI-slop checklist. Constraints belong in the prompt — every SKILL.md writes them in.

4 · Streaming render = watch the AI draw.

POST /api/convert is SSE. The agent's stdout is line-delimited JSON; the server pulls out the text deltas and re-emits them as SSE events; the client appends to the iframe's srcdoc. The whole experience is the same as watching the agent type in a terminal, except the artifact is HTML, not Markdown. Interrupt at any time — you're not paying for a whole generation you don't want.

5 · One-click export = zero second-pass formatting.

• WeChat MP — juice inlines CSS + data-tool markers → paste into the editor, styles survive end to end.
• X / Weibo / Xiaohongshu — modern-screenshot renders the iframe to a 2× PNG → ClipboardItem → drop straight into the composer.
• Zhihu — same as above, plus <mjx-container> is replaced with data-eeimg LaTeX-image placeholders (Zhihu won't render KaTeX live — math has to be an image).
• Download .html / download .png — self-contained single file, shareable anywhere.

Mechanically inspired by mdnice/markdown-nice and gcui-art/markdown-to-image.

6 · Sandboxed iframe = secure + isolated.

User-emitted HTML always renders inside <iframe sandbox="allow-scripts allow-same-origin">. Third-party scripts (Tailwind CDN, Google Fonts, custom animations) still execute, but cookies and localStorage stay in the iframe's own origin — the host page is never poisoned. Opening devtools only shows the iframe's DOM, so the debugging experience matches a standalone HTML file.

Architecture

┌─────────────────────── Browser (Next.js 16) ──────────────────────┐
│  Editor / upload · top-bar agent picker · template picker · iframe │
└─────────────┬──────────────────────────────────┬──────────────────┘
              │ ⌘+Enter                            │
              ▼                                    ▼
     ┌─────────────────────┐            ┌──────────────────────┐
     │  GET /api/agents    │            │  POST /api/convert   │
     │  scan PATH, list    │            │  SSE — spawn CLI     │
     │  installed CLIs     │            │  pipe stdin / stdout │
     └─────────────────────┘            └──────────┬───────────┘
                                                   │ spawn + stdin pipe
                                                   ▼
                                ┌────────────────────────────────────┐
                                │  Your local coding-agent CLI       │
                                │  claude / codex / cursor-agent /   │
                                │  gemini / copilot / opencode /     │
                                │  qwen / aider                      │
                                │  → reuses your existing session    │
                                └────────────────────────────────────┘
                                                   │
                                                   ▼
                                stdout JSON-line ──► SSE event
                                                   │
                                                   ▼
                              iframe srcdoc append (live)
                                                   │
                              ⌘+C copy → ClipboardItem
                              ⌘+S download → .html / .png

Export targets

Roadmap

• Multi-template compare preview — generate four candidates of the same brief, pick the best one
• Hyperframes → mp4 — one-click hand-off of frame scripts to Remotion for real video output
• Shared design systems — interop with nexu-io/open-design DESIGN.md assets
• Template marketplace — community-contributed prompts & examples
• Browser extension — select on any page → convert to HTML template
• History / version diff / IndexedDB archive
• More export targets — WeChat Channels · Douyin captions · Notion · Linear · Telegraph

Status

Early but real. The closed loop — detect agent → pick skill → SSE stream → sandboxed iframe preview → one-click export — runs end-to-end against all 8 CLIs listed above. The skill library and the SKILL.md hard-constraints are where most of the leverage lives, and both are stable. The picker UX, design-system metadata, and the multi-template compare flow ship daily. If something looks broken on your machine, open an issue with the agent CLI you were using and the input — those are the bug reports that move things forward fastest.

Contributing

Issues, PRs, new skills, new agent adapters, new export targets, and translations are all welcome. The highest-leverage contributions are usually one folder, one Markdown file, or one PR-sized adapter — small surface area, big leverage. Pick the slot that matches what you want to add:

• Add a skill — drop a folder into src/lib/templates/skills/ with SKILL.md + example.html (+ optional assets/ and references/). The picker auto-discovers it after pnpm dev restart. The SKILL.md frontmatter has to set mode · scenario · surface · preview · design_system — copy a neighbour and edit.
• Wire up a new coding-agent CLI — one entry in src/lib/agents/argv.ts covering: detection binary, argv builder, stdin/stdout protocol, stream parser. Detection is exercised by src/app/api/agents/ and the spawn loop by src/app/api/convert/.
• Add an export target — drop a module under src/lib/export/ (next to wechat.ts / image.ts / clipboard.ts) and add the button to the export menu. WeChat Channels · Douyin captions · Notion · Linear · Telegraph · RSS are all open.
• Sharpen a SKILL.md — strengthen the hard-constraints (CJK font stack, 8 px baseline, contrast ≥ 4.5, must-use-real-data), add a 5-dimensional self-critique, swap in a better palette. Anti-AI-slop discipline is the most underrated PR shape we accept.
• Translations & docs — README.zh-CN.md and CONTRIBUTING.zh-CN.md are kept in parallel with the English files; please update both.

Full walkthrough, bar-for-merging, code style, and what we don't accept → CONTRIBUTING.md (简体中文).

References & lineage

Every external project this repo borrows from — what we take from each, and where it lands in the tree.

Each bundled upstream skill retains its original LICENSE and authorship inside its own src/lib/templates/skills/<skill>/ folder.

Stay in the loop

Follow @nexudotio on X for release notes, new skills, and the occasional behind-the-scenes thread on what's shipping next. The Discord is where the bigger conversations happen — both are run by the upstream open-design team, and HTML Anything piggybacks on the same channels.

Contributors

Thanks to everyone who has filed an issue, opened a PR, or added a skill / agent adapter / export target. Every real contribution counts, and the wall below is the easiest way to say so out loud.

If you've shipped your first PR — welcome. The good-first-issue / help-wanted labels are the entry point.

Star History

If the curve bends up, that's the signal we look for. ★ this repo to push it.

License

Apache-2.0 © 2026 HTML Anything contributors. See LICENSE.

Bundled work retains its original license and authorship attribution — see the per-skill LICENSE / README.md inside each src/lib/templates/skills/<skill>/ folder for what it inherits from upstream.