Skip to content
Back to search

html-anything

SkillWorks with Claude CodeGitHub

Turn rich agent answers and any file, folder, URL, or export into a polished single-file HTML page. Auto-picks a default route plus 17 concrete design systems (teaching, dashboard, atlas, timeline-story, document, …).

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/clockless-org--html-anything/badge.svg)](/listings/clockless-org--html-anything)

HTML

<a href="/listings/clockless-org--html-anything"><img src="/api/listings/clockless-org--html-anything/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Pick the path for your agent: [Claude Code](#claude-code) · [Codex](#codex) · [claude.ai](#claudeai-web) · [Claude API](#claude-api) · [Cursor / Cline / Windsurf / OpenCode / Goose / Letta / …](#one-command-for-most-cli-and-editor-agents) · [ClawHub](#clawhub-publish)

One command for most CLI and editor agents

npx skills add clockless-org/html-anything

Works with **Claude Code**, **Codex**, **Cursor**, **Cline**, **Windsurf**, **OpenCode**, **Goose**, **Letta**, **Roo Code**, **Kiro**, and any other agent following the [open agent-skills spec](https://agentskills.io). The CLI also pings [skills.sh](https://skills.sh/clockless-org/html-anything) so installs feed the public leaderboard.

Claude Code

git clone https://github.com/clockless-org/html-anything ~/.claude/skills/html-anything

Restart Claude Code so it loads `SKILL.md`. To update later: `git -C ~/.claude/skills/html-anything pull`.

Codex

git clone https://github.com/clockless-org/html-anything "${CODEX_HOME:-$HOME/.codex}/skills/html-anything"

Restart Codex.

claude.ai (web)

1. Download [`html-anything-skill.zip`](https://github.com/clockless-org/html-anything/releases/latest/download/html-anything-skill.zip) (`SKILL.md` + `prompts/`, including style references). 2. In claude.ai: **Settings → Features → Skills → Upload a Skill** → drop the zip.

Requires **Pro / Max / Team / Enterprise** with code execution enabled. Custom skills on claude.ai are per-user; each teammate uploads their own copy.

Claude API

curl https://api.anthropic.com/v1/skills \
  -H "x-api-key: $ANTHROPIC_API_KEY" \
  -H "anthropic-beta: skills-2025-10-02,code-execution-2025-08-25,files-api-2025-04-14" \
  -F file=@html-anything-skill.zip

Then reference the returned `skill_id` in the `container` of any message. See the [Skills API guide](https://platform.claude.com/docs/en/build-with-claude/skills-guide). Uploaded skills are workspace-wide.

ClawHub (publish)

This repo carries `.clawhubignore` so only `SKILL.md` + `prompts/` ship, including canonical style references used by installed agents:

npm i -g clawhub && clawhub login
clawhub publish . --slug html-anything --version 0.1.1 --tags latest

Where it does not work

| Surface | Status | |---|---| | ChatGPT / chatgpt.com | ❌ Custom GPTs are a different format. Use **OpenAI Codex CLI** instead (above). | | Gemini web / Google Gems | ❌ Different format. Use **Gemini CLI** (`npx skills add`) instead. | | Anthropic / Claude Desktop | ✅ Reads `~/.claude/skills/` — same as Claude Code. |

> ℹ Custom Skills do not sync across surfaces. The same skill uploaded to claude.ai is **not** automatically available on Claude Code or the API — each surface keeps its own copy.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

SKILL.md · Manifest · 458 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. ---
  2. name: html-anything
  3. description: Turn rich agent answers and any file, folder, URL, or export into a polished single-file HTML page. Auto-picks a default route plus 17 concrete design systems (teaching, dashboard, atlas, timeline-story, document, …).
  4. version: 0.1.0
  5. homepage: https://github.com/clockless-org/html-anything
  6. when_to_use: User says "make a webpage", "create a teaching site", "make an interactive studio", "explore this object/system", "turn this into HTML", "visualize/analyze this", "make a dashboard/report/atlas", "make it beautiful/readable/shareable", gives a file/folder/URL to make browsable, names a data source they want exported and converted, or asks for a rich deliverable that would otherwise become a long Markdown answer.
  7. metadata:
  8. openclaw:
  9. emoji: "🧩"
  10. homepage: https://github.com/clockless-org/html-anything
  11. ---
  12. # html-anything
  13. You are the `html-anything` skill.
  14. Your job is to turn **an idea, file, folder, URL, exported dataset, or rich
  15. deliverable request** into a polished live HTML page the user can open, share,
  16. or publish.
  17. Do not present this as a parser, CLI, or internal pipeline. The user only
  18. needs to understand:
  19. - **Input**: an idea, file, folder, URL, or source they want help exporting.
  20. - **Output**: a live HTML page, usually `output.html`, sometimes with an
  21. `assets/` folder when generated images or local media are useful.
  22. Everything else is your responsibility: source understanding, export
  23. guidance, style choice, page design, asset generation, implementation,
  24. browser verification, and final handoff.
  25. Two constraints are non-negotiable:
  26. 1. **Style fidelity**: if a style is based on a reference design, reproduce
  27. the reference's layout system, first viewport, component vocabulary,
  28. typography roles, color/surface language, and motion grammar. Do not merely
  29. borrow the mood.
  30. 2. **Final HTML compliance**: the delivered HTML must visibly and structurally
  31. follow the selected style, not a generic html-anything report with different
  32. colors.
  33. ## User-Facing Promise
  34. Accept requests like:
  35. - "Create an interactive teaching site about the solar system."
  36. - "Turn my Amazon order history into a personal spending atlas."
  37. - "Make this WhatsApp export into a relationship rhythm report."
  38. - "Turn this transcript into a meeting scorecard."
  39. - "Make this CSV into a dashboard I can share."
  40. - "Use this GitHub repo URL and make a browsable architecture page."
  41. Return a working HTML artifact, not a proposal.
  42. ## Canonical Example Parity
  43. The checked-in examples are the quality bar for installed users. Treat them as
  44. canonical usage patterns, not as loose inspiration.
  45. When a user asks for something similar to an official example, route to the
  46. same source family and style system, then produce a page with comparable
  47. structure, interaction depth, visual specificity, and browser-verified polish.
  48. For example:
  49. - "Create a three-panel interactive teaching studio about the solar system,
  50. with a selectable model, compare controls, and live inspector." should route
  51. to `Teaching Studios` + `teaching`, with an actual visual model/stage.
  52. - "Turn this PDF guide into an interactive e-guide." should route to
  53. `Files & Work Data` + `digital-eguide`, with a guide-shaped reading surface.
  54. - "Analyze this 1:1 chat export as a private relationship recap." should route
  55. to `Conversation Analysis` + `love-romance-3d`, with masked names and
  56. privacy-first evidence.
  57. - "Turn this CI log into a terminal-style debugging evidence page." should
  58. route to `Files & Work Data` + `terminal-cli`, with terminal-native panes and
  59. actionable evidence.
  60. Do not answer those requests with Markdown summaries or generic reports. Build
  61. the live HTML artifact.
  62. ### Reference Example Loading
  63. When the selected catalog style has `referenceHtml`, read that file before
  64. writing new HTML. It lives under `prompts/styles/references/` so installed skill
  65. users get the same visual target as the repo examples. If `referenceHtml` is
  66. absent, fall back to `examples/<example>/output.html` when available.
  67. Reference packs should be style-scoped:
  68. - `prompts/styles/references/<style>/<name>.html`
  69. - `prompts/styles/references/<style>/assets/...`
  70. For exact topic or usage matches, such as another solar-system teaching
  71. studio, use the reference HTML as the structural target: first viewport
  72. geometry, CSS token overrides, surface treatment, component classes,
  73. interaction wiring, and asset references should be adapted, not reinvented.
  74. Also inspect `referenceAssets` and any `examples/<example>/assets/` folder when
  75. they exist. Reuse or copy matching local assets before generating substitutes.
  76. When a `referenceAssets` path contains `/assets/`, copy that subtree into the
  77. output folder's `assets/` directory preserving the path after `/assets/`.
  78. If a style skin or token override appears in the reference HTML, fold the
  79. useful variables and background treatment into the new output, but do not copy
  80. visible demo-only labels such as style badges unless the user asks for them.
  81. For non-exact matches, still read the example and extract only the reusable
  82. style invariants. The generated page can change content, but it should remain
  83. recognizably in the same design system.
  84. ## Default Artifact Behavior
  85. When the final answer would be long, visual, structured, comparative,
  86. educational, report-like, recap-like, or meant to be shared, prefer creating a
  87. polished HTML artifact over writing a long Markdown answer.
  88. Use HTML by default when the user asks to:
  89. - teach or explain a topic as a learning experience,
  90. - present research, analysis, or a decision brief,
  91. - compare options, timelines, entities, places, people, or files,
  92. - recap personal/work data,
  93. - audit a dataset, transcript, chat, repo, folder, or export,
  94. - make something easier to read, beautiful, browsable, interactive, or
  95. shareable.
  96. Do **not** use HTML when the user wants:
  97. - a quick factual answer,
  98. - a small code edit or debugging explanation,
  99. - a short command, snippet, or config change,
  100. - a normal conversational answer,
  101. - Markdown/text only,
  102. - a change inside an existing app where the correct deliverable is source code,
  103. not a standalone HTML artifact.
  104. If the user asks for "a page", "site", "visual", "report", "dashboard",
  105. "explainer", "recap", "atlas", "gallery", "timeline", "teaching site", or
  106. "shareable output", create the HTML artifact unless there is a clear reason not
  107. to.
  108. ## Inputs
  109. Handle these input modes automatically:
  110. | Input mode | What to do |
  111. |---|---|
  112. | Idea / brief | Expand the brief into a concrete content plan, choose an auto style, create the HTML, and generate assets when useful. |
  113. | Local file | Inspect the file, sample it if large, identify the source type, and create the page. |
  114. | Folder | Inspect structure and representative files, then create an atlas / audit / browser for the folder. |
  115. | URL | Fetch or inspect the URL when possible, then create a page from the page/repo/article content. |
  116. | Export request | If the user names a platform/source but has no file yet, read the relevant source prompt's export instructions and guide them first. |
  117. Do not ask the user to pick a style by default. Use `auto`.
  118. Ask a question only when the target is genuinely ambiguous or the next
  119. step could expose private data unexpectedly.
  120. ## Outputs
  121. Default output:
  122. - `output.html` next to the source, or in a clear project/example folder
  123. when starting from a brief.
  124. - If the user gives `foo.csv`, `foo.html` is also acceptable when it is
  125. more natural for the local workflow.
  126. Asset outputs:
  127. - If generated images, sprite sheets, thumbnails, or other local media make
  128. the page materially better, create an `assets/` folder next to the HTML.
  129. - If the user asks for "single-file", inline CSS, JS, data, and assets into
  130. one HTML file where practical.
  131. Final response:
  132. - Give the path/link to the HTML.
  133. - Mention important generated assets if any.
  134. - Mention browser verification.
  135. - Do not explain the internal pipeline unless the user asks.
  136. ## Use-Case Taxonomy
  137. Route every request through one of four user-facing use cases before choosing
  138. the style system. Source prompts can be many; use cases should stay stable.
  139. | Use case | User means | Likely styles |
  140. |---|---|---|
  141. | Teaching Studios | Turn an idea, article, lesson, long text, or document into an interactive or guided learning surface, not a scrolling article. | `teaching`, `architectural-spread`, `kami-reading` |
  142. | Files & Work Data | Transform files and work artifacts: CSV/spreadsheet-style exports, PDFs, DOCX, Markdown, logs, CI output, email/support archives, finance, calendars, issue trackers, repos, research records, and slide-style carousel outputs. | `dashboard`, `soft-saas`, `document`, `kami-reading`, `architectural-spread`, `digital-eguide`, `editorial-carousel`, `developer`, `terminal-cli` |
  143. | Conversation Analysis | Analyze private chats, relationship exports, team channels, or message archives. | `love-romance-3d`, `kinetic-scoreboard`, `network-map` |
  144. | Personal Data & Places | Make a recap/timeline/story/map from personal exports: orders, health, browsing, media, payments, professional networks, notes, AI chats, saved places, travel history, and routes. | `timeline-story`, `global-travel`, `living-essay`, `network-map`, `map-atlas` |
  145. Do not expose this as a required choice to the user. Use it internally to make
  146. auto-routing predictable.
  147. ## Auto Style
  148. Pick a style automatically from the user's intent and source. Treat styles
  149. as behavior and page shape, not a superficial CSS skin.
  150. Styles are **underlying systems**. Choose the system first, then design the
  151. page inside it. Do not create a generic report and recolor it. The style must
  152. change the first viewport, layout scaffold, component vocabulary, interaction
  153. model, density, chart grammar, and voice.
  154. | Auto style | Use for | Page shape |
  155. |---|---|---|
  156. | `default` | Unknown, mixed, or weakly classified briefs/sources | **Insight Brief**: answer header, primary insight panel, evidence stack, local drill-down |
  157. | `teaching` | Tutorials, lessons, "teach me", interactive explainers, course-like pages | **Lesson Lab**: visual stage, step rail, try-it controls, concept cards, check-yourself, recap |
  158. | `love-romance-3d` | 1:1 chats, couple/friend/family chats, WhatsApp/WeChat/iMessage relationship exports | **Keepsake 3D Rhythm**: soft 3D cover, pulse boards, comparison lanes, privacy-first evidence |
  159. | `living-essay` | Kindle highlights, reflective essays, idea notes, concept-heavy reading archives | **Mycelium Writing Environment**: paper manuscript, vertical margin question, inline spore words, living SVG threads, quiet appendix |
  160. | `dashboard` | Finance/admin data, logs, operational data, issue trackers, dense tabular queues | **Ops Console**: command bar, KPI rail, work surface, flag queue, searchable data grid |
  161. | `soft-saas` | Support mailboxes, email campaigns, onboarding programs, customer-success queues, lightweight SaaS metrics | **Soft SaaS Console**: pale app canvas, profile/source card, central metric bloom, campaign panels, leaderboard, activity strip |
  162. | `kinetic-scoreboard` | Multi-participant activity streams, team chats, ranked contributors, owners/reps/players by contribution or workload | **Kinetic Championship**: full-viewport lanes, live ranks, big counters, kinetic activity body, telemetry footer, linked evidence pits |
  163. | `timeline-story` | Personal histories — chronological (Amazon, browser, Spotify, YouTube, Twitch, Health, AI chats) **and** topical (Notion exports, Obsidian vaults, markdown folders) | **Timeline Story**: time lens, timeline spine, chapter panels, rhythm strip, memory drawer (or cluster cards for topical sources) |
  164. | `global-travel` | Travel history, Uber/Lyft trip exports, airport patterns, and personal mobility recaps | **Global Travel Map**: centered headline, source selector, dotted world map, warm pins, metric runway, itinerary browser |
  165. | `map-atlas` | Saved places, routes, location history, geotagged photo metadata | **Map Atlas**: spatial stage, place drawer, period/place filters, waypoint browser |
  166. | `network-map` | Contacts, LinkedIn, Venmo/PayPal, people/org graphs, community relationship maps | **Network Map**: graph canvas, entity inspector, cluster controls, hub cards, linked records |
  167. | `document` | Essays, articles, reading lists, bookmarks, research collections, PDFs, DOCX, legal/medical/lab/academic records | **Document Review**: cover, reading rail, body sheet, evidence margin, drill-down. Tone shifts narrative ↔ formal based on source. |
  168. | `kami-reading` | Long prose, DOCX memos, articles, essays, and manuscripts meant for sustained reading | **Kami Longform Reader**: warm parchment document, serif cover, inline contents, printable chapters, source appendix |
  169. | `architectural-spread` | Long-form visual explainers, object-focused articles, manifestos, and reference requests that look like the split Mars architectural HTML | **Architectural Editorial Spread**: left visual bay, right cream content panel, serif italic emphasis, corner anchors, pagination dots |
  170. | `digital-eguide` | E-guides, PDF guides, creator guides, playbooks, lead magnets, downloadable course previews | **Digital E-Guide Spread**: two paper pages on a warm desk, cover + TOC, inside lesson, pull quote, steps, exercise strip |
  171. | `editorial-carousel` | Brand strategy essays, founder letters, article takeaways, lightweight reports meant to be shared as a sequence | **Editorial Carousel**: issue cover, spread rail, 4-8 argument spreads, evidence drawer, copy actions |
  172. | `developer` | Diffs, PR patches, CI logs, stack traces, repos | **Terminal Evidence Workbench**: prompt line, hotspots, risk checklist, raw artifact navigator, copyable handoff |
  173. Explicit override styles:
  174. | Style | Use for | Page shape |
  175. |---|---|---|
  176. | `terminal-cli` | User asks for a terminal, CLI, shell, mainframe, hacker, server-console, or tmux feel | **Terminal CLI**: shell prompt, status rail, terminal pane grid, command controls, raw console, scanline overlay |
  177. Honor explicit style direction in natural language:
  178. - "make it a tutorial" / "teach me" → lean `teaching`.
  179. - "make it more app-like" / "explore this object" / "interactive studio" → lean `teaching` with the object/model as the main stage.
  180. - "less academic" → reduce formal `document` voice.
  181. - "make it a carousel" / "magazine feel" / "social post" → lean `editorial-carousel`.
  182. - "make it an e-guide" / "PDF guide" / "playbook" / "lead magnet"
  183. → use `digital-eguide` and follow `prompts/styles/digital-eguide.md` exactly.
  184. - "make it like a SaaS panel" / "support console" / "email campaign" /
  185. "onboarding dashboard" → lean `soft-saas`.
  186. - "more dashboard-like" → increase density, filters, charts.
  187. - "more editorial" without carousel/deck language → narrative `document` voice.
  188. - "make it like this Mars architectural HTML" / "split-screen editorial" /
  189. "architectural spread" → use `architectural-spread` and follow
  190. `prompts/styles/architectural-spread.md` exactly.
  191. - "make it a map" / "spatial" → lean `map-atlas`.
  192. - "travel history" / "Uber history" / "Lyft history" → lean `global-travel`.
  193. - "show relationships/network" → lean `network-map`.
  194. - "who contributed most" / "make it feel like a race" → lean `kinetic-scoreboard`.
  195. - "make it a year-in-review" / "story over time" → lean `timeline-story`.
  196. - "make it terminal/CLI/mainframe" / "like a shell" / "hacker console"
  197. → use `terminal-cli` and follow `prompts/styles/terminal-cli.md` exactly.
  198. - "more playful" → richer visuals, while keeping content accurate.
  199. - If nothing fits cleanly → use `default`.
  200. ## Standard Workflow
  201. 1. **Understand the request.**
  202. Decide whether the user supplied an idea, file, folder, URL, or export
  203. request.
  204. 2. **Onboard exports when needed.**
  205. If the user names a source but has no file yet, read the matching
  206. prompt in `prompts/sources/<source>.md` and give concise export steps. Stop
  207. after the export guidance unless the file is already available.
  208. 3. **Inspect the source or brief.**
  209. - For files/folders, read a representative sample and gather stats.
  210. - For URLs, fetch/inspect enough content to understand shape.
  211. - For ideas/briefs, create a structured content plan yourself. Use
  212. web verification for current or high-stakes facts.
  213. 4. **Load guidance.**
  214. Read `prompts/styles/_design.md`, `prompts/styles/catalog.json`, and the
  215. closest source prompt. If no source prompt fits, use
  216. `prompts/sources/default.md`. Apply shared family prompts when relevant
  217. (`_chat`, `_finance`, `_developer`, `_geo`, etc.). Use the catalog entry for
  218. the chosen style as the compact preflight checklist: system name, example,
  219. required primitives, and avoid rules. Then read and follow
  220. `prompts/styles/<style>.md`. If a style prompt contains a reference contract
  221. or compliance gate, treat it as a hard requirement for the final HTML, not a
  222. mood board.
  223. If the catalog entry names `referenceHtml`, read that file as well. If it
  224. only names an example, read `examples/<example>/output.html` when available.
  225. For exact usage matches, inspect the first viewport markup, the main CSS
  226. token block, the style-specific classes, the primary JS state/update
  227. functions, and any local asset references. The reference HTML is the binding
  228. visual contract when prose and the checked-in demo differ.
  229. 5. **Choose auto style.**
  230. Pick the page style internally. Do not ask the user to choose unless
  231. they explicitly want style options.
  232. 6. **Extract the style contract.**
  233. Before writing HTML, identify the selected style's 5-8 core invariants:
  234. first viewport geometry, layout scaffold, typography roles, color/surface
  235. language, component vocabulary, primary interaction, motion grammar, and
  236. what must be absent. Pull required primitives and avoid rules from
  237. `catalog.json`, then pull visual details from the full style prompt and the
  238. reference HTML. If the style came from a reference HTML/screenshot,
  239. match those invariants as closely as the new content allows.
  240. 7. **Build the page.**
  241. Create the HTML/CSS/JS directly. Keep the page useful, interactive,
  242. mobile-responsive, and content-specific. Include search/filter/copy
  243. where it genuinely helps. Put `data-ha-style="<selected-style>"` on the
  244. root `<html>` element and use the style's class/component vocabulary.
  245. 8. **Generate assets when they improve the artifact.**
  246. Before generating new assets, inspect any matching `referenceAssets` or
  247. official example asset folder and reuse appropriate files when licensing and
  248. context allow.
  249. Use the `imagegen` skill/tool for raster assets such as object models,
  250. cover art, sprites, textures, or preview images. Save project-bound
  251. assets into the output folder. Do not leave referenced assets only in
  252. `$CODEX_HOME/generated_images`.
  253. 9. **Verify in a browser.**
  254. For frontend artifacts, open the HTML via local file or local HTTP.
  255. Check:
  256. - page is nonblank,
  257. - desktop and mobile viewports render cleanly,
  258. - no obvious horizontal overflow,
  259. - contrast is readable and focus states are visible,
  260. - keyboard and touch paths exist for core interactions,
  261. - primary interactions work,
  262. - generated assets load.
  263. Also check style fidelity:
  264. - first viewport clearly matches the selected style's required scaffold,
  265. - source-required modules are translated into the style's native component
  266. vocabulary,
  267. - the page does not fall back to generic hero/KPI/card/table patterns unless
  268. that is the selected style.
  269. If any of these fails, revise the HTML before handoff.
  270. 10. **Handoff.**
  271. Give the user the local path or live link. Keep the explanation short.
  272. ## Style Fidelity Gate
  273. Before final handoff, the HTML must pass this internal checklist:
  274. - The root `<html>` declares `data-ha-style`.
  275. - The first viewport is built from the selected style's scaffold.
  276. - If the selected style has a catalog `referenceHtml`, the generated first
  277. viewport visibly matches that reference's scaffold, token system, surface
  278. language, and interaction grammar unless the user explicitly requested a
  279. different style.
  280. - At least four style-specific class names/components from the style prompt
  281. appear in the HTML.
  282. - The primary interaction is native to the style and works with local data.
  283. - Required source modules are present, but shaped in the style's vocabulary.
  284. - Text contrast, focus states, keyboard access, and touch targets meet the UI
  285. quality gate.
  286. - Charts and dense visuals have visible values or list/table fallbacks and do
  287. not rely on color alone.
  288. - There is no accidental body-level horizontal overflow; intentional
  289. horizontal stages have explicit controls.
  290. - Motion follows the style's motion grammar and respects
  291. `prefers-reduced-motion`.
  292. - The page is complete, offline-capable, and not just a recolored default
  293. report.
  294. If the page fails, revise the HTML before presenting it.
  295. ## Design Requirements
  296. Read [`prompts/styles/_design.md`](./prompts/styles/_design.md) for Clockless tokens and
  297. apply them by default.
  298. General requirements:
  299. - Mobile-first responsive layout.
  300. - WCAG AA contrast for meaningful text, visible focus states, labeled
  301. controls, and 44px primary touch targets where possible.
  302. - Light + dark mode when the page is a report/data artifact; for app-like
  303. examples, a polished light-mode Clockless surface is acceptable.
  304. - Inline CSS and JS in the HTML.
  305. - No external JS/CDN dependencies unless the user explicitly allows them.
  306. - The only default external font call is the Google Fonts import from
  307. `prompts/styles/_design.md`.
  308. - Use generated bitmap assets when the experience needs rich visual
  309. subjects; use SVG/CSS/canvas for deterministic diagrams and UI.
  310. - Do not build a generic landing page when the user asked for a tool,
  311. teaching site, dashboard, report, or explorer. Build the actual usable
  312. experience as the first screen.
  313. ## Data And Privacy Defaults
  314. - Treat generated HTML as sensitive as the source data because it may
  315. embed source records client-side.
  316. - For intimate chats, do not include a raw-message appendix by default.
  317. Use aggregate charts and small anonymized evidence snippets.
  318. - For medical, legal, tax, accounting, immigration, insurance, or
  319. investment-adjacent sources, stay observational and include caveats.
  320. Do not provide professional advice.
  321. - For contacts, payments, chats, and personal exports, mask or omit
  322. sensitive identifiers unless the user asks to reveal them.
  323. - For Google Photos-style sources, prefer metadata-only analysis unless
  324. the user explicitly asks to inspect actual media.
  325. ## Sampling Guidance
  326. Read enough to understand the source shape without loading huge private
  327. exports into the model unnecessarily.
  328. - Tabular data: header, first rows, last rows, column stats, date ranges,
  329. categories, numeric summaries.
  330. - Chat: first/last messages, sender list, time span, daily/monthly counts,
  331. media/deleted/transfer counts if present.
  332. - Long text: headings, first sections, word count, section outline.
  333. - Email: thread counts, sender counts, first/last messages, open loops.
  334. - Transcript: speaker stats, first/last cues, longest cues, decisions and
  335. action-item clues.
  336. - Event/log stream: inferred schema, severity/category counts,
  337. time-bucket histogram, representative errors/outliers.
  338. - Finance/admin: in/out/net or status totals, categories, recurring items,
  339. duplicates/outliers.
  340. - Geo/routes: bbox, distance, points, elevation/pace if present, waypoint
  341. list.
  342. - Folder/repo: tree, README/index files, representative key files.
  343. ## Source Prompts
  344. The source prompts under [`prompts/sources/`](./prompts/sources/) contain export steps and
  345. content-specific analysis guidance. Use the closest one, then roll it up to
  346. the use-case taxonomy above:
  347. - Teaching Studios: `url-article`, `markdown`, `docx`, `pdf`, `default`
  348. when the user wants a lesson, guided reading surface, or explainer.
  349. - Conversation Analysis: `wechat`, `whatsapp`, `slack`, `discord`,
  350. `telegram`, `imessage`, `multi-sender-chat`.
  351. - Personal Data & Places: `amazon-orders`, `youtube-watch-history`,
  352. `spotify-history`, `iphone-health`, `kindle-highlights`, `twitch-history`,
  353. `browser-history`, `venmo-paypal-payments`, `linkedin-connections`,
  354. `vcard-contacts`, `chatgpt-export`, `claude-chat-export`, `ai-chat-export`,
  355. `notion-export`, `obsidian-vault`, `markdown-folder`, `google-maps-stars`,
  356. `google-photos-takeout`, `rideshare-history` / travel history, `gpx`, `kml`,
  357. `travel-itinerary`, `location-history`.
  358. - Files & Work Data: `csv`, `json`, `jsonl`, `log`, `email`, `bank-transactions`,
  359. `invoices`, `quickbooks`, `ics-calendar`, `issue-tracker`, `trello-board`,
  360. `markdown`, `pdf`, `docx`, `bookmarks`, `url-list`, `reading-list`,
  361. `bibliography`, `medical-visit`, `lab-results`, `legal-chronology`,
  362. `git-diff`, `pr-review`, `ci-log`, `stack-trace`, `github-repo`.
  363. - General fallback: `default`.
  364. If no prompt fits, proceed from `prompts/sources/default.md` and the user's
  365. brief.
  366. Style prompts under [`prompts/styles/`](./prompts/styles/) define reusable page
  367. systems such as `Timeline Story`, `Map Atlas`, `Network Map`, `Lesson Lab`,
  368. `Keepsake 3D Rhythm`, `Global Travel Map`,
  369. `Ops Console`, `Soft SaaS Console`, `Kami Longform Reader`, `Terminal CLI`,
  370. `Terminal Evidence Workbench`, `Mycelium Writing Environment` (`living-essay`),
  371. `Editorial Carousel`, and `Digital E-Guide Spread`. They complement source
  372. prompts; they do not replace source-specific analysis. The style prompt is
  373. binding for the final HTML's layout and interaction system.
README.md · README · 400 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # html-anything
  2. > **The agent skill that turns anything into a beautiful, shareable HTML page.**
  3. > Rich answers, files, folders, URLs, and messy service exports become verified
  4. > single-file `.html` artifacts with source-aware parsing, automatic style
  5. > routing, **60 source prompts**, and **17 concrete style systems**. Short chats
  6. > stay short; page-worthy answers become pages.
  7. <p align="center">
  8. <a href="https://skills.sh/clockless-org/html-anything"><img alt="skills.sh" src="https://skills.sh/b/clockless-org/html-anything"></a>
  9. <a href="https://github.com/clockless-org/html-anything/stargazers"><img alt="GitHub stars" src="https://img.shields.io/github/stars/clockless-org/html-anything?style=flat-square"></a>
  10. <a href="https://github.com/clockless-org/html-anything/blob/main/LICENSE"><img alt="License" src="https://img.shields.io/github/license/clockless-org/html-anything?style=flat-square"></a>
  11. <a href="./prompts/sources"><img alt="60 source prompts" src="https://img.shields.io/badge/sources-60%20prompts-7b40e0?style=flat-square"></a>
  12. <a href="./prompts/styles"><img alt="17 style systems" src="https://img.shields.io/badge/styles-17%20systems-a03b00?style=flat-square"></a>
  13. <a href="https://clockless-org.github.io/html-anything/examples/"><img alt="11 demos" src="https://img.shields.io/badge/examples-11%20demos-0f766e?style=flat-square"></a>
  14. </p>
  15. <p align="center">
  16. <a href="https://clockless-org.github.io/html-anything/examples/"><strong>→ Open the live demo gallery</strong></a>
  17. </p>
  18. `html-anything` works inside Codex and Claude Code. Ask for a teaching site,
  19. drop in a PDF, upload a CSV, point it at a folder, or hand it an export like
  20. Amazon orders, Kindle highlights, Spotify history, WeChat / iMessage,
  21. Google Photos Takeout, logs, GPX, and more. The skill figures out the source,
  22. chooses the right use case and style, builds the page, checks it in a browser,
  23. and hands back a live HTML artifact instead of a long Markdown reply.
  24. ## Why this exists
  25. AI agents are outgrowing plain Markdown. Inspired by Claude Code team member
  26. Thariq Shihipar's viral
  27. [“The Unreasonable Effectiveness of HTML”](https://x.com/trq212/status/2052809885763747935),
  28. `html-anything` treats HTML as the richer response format: denser, more visual,
  29. more interactive, and easier to share when the answer is really a page.
  30. <table>
  31. <tr>
  32. <td width="100%" valign="top">
  33. <h3>Before: plain response</h3>
  34. <p>A long scroll of text for “Teach me solar system”. Useful, but hard to explore.</p>
  35. <img src="./docs/plain-response-before.jpg" alt="Plain AI response about the solar system" width="100%">
  36. </td>
  37. </tr>
  38. <tr>
  39. <td align="center">
  40. <strong>↓</strong><br>
  41. <sub>Same intent, richer response format</sub>
  42. </td>
  43. </tr>
  44. <tr>
  45. <td width="100%" valign="top">
  46. <h3>After: live HTML artifact</h3>
  47. <p>The same teaching goal becomes a visual, interactive learning page.</p>
  48. <a href="https://clockless-org.github.io/html-anything/examples/solar-system-studio/output.html"><img src="./docs/example-demos/solar-system-studio.gif" alt="html-anything solar system teaching studio (animated demo)" width="100%"></a>
  49. </td>
  50. </tr>
  51. </table>
  52. ## Preview
  53. <sub>Each card shows the kind of question a user would naturally ask. The skill detects intent, picks the right design system, and ships a polished HTML page — without anyone mentioning HTML. Open the [live demo gallery](https://clockless-org.github.io/html-anything/examples/) to see the rendered outputs.</sub>
  54. ### Teaching Studios
  55. <table>
  56. <tr>
  57. <td width="50%" valign="top">
  58. <a href="https://clockless-org.github.io/html-anything/examples/solar-system-studio/output.html"><img src="./docs/example-demos/solar-system-studio.gif" alt="Teach a concept demo" width="100%"></a><br>
  59. <strong><a href="https://clockless-org.github.io/html-anything/examples/solar-system-studio/output.html">Teach a concept →</a></strong><br>
  60. <sub>Source: teaching brief · Style: <code>teaching</code></sub><br>
  61. <sub><strong>Ask:</strong> <code>Teach me the solar system.</code></sub>
  62. </td>
  63. <td width="50%" valign="top">
  64. <a href="https://clockless-org.github.io/html-anything/examples/markdown/output.html"><img src="./docs/example-demos/markdown.gif" alt="Learn from long-form text demo" width="100%"></a><br>
  65. <strong><a href="https://clockless-org.github.io/html-anything/examples/markdown/output.html">Learn from long-form text →</a></strong><br>
  66. <sub>Source: Markdown file · Style: <code>architectural-spread</code></sub><br>
  67. <sub><strong>Ask:</strong> <code>Help me understand this essay.</code> (with a markdown file attached)</sub>
  68. </td>
  69. </tr>
  70. <tr>
  71. <td width="50%" valign="top">
  72. <a href="https://clockless-org.github.io/html-anything/examples/docx/output.html"><img src="./docs/example-demos/docx.gif" alt="Learn from a document demo" width="100%"></a><br>
  73. <strong><a href="https://clockless-org.github.io/html-anything/examples/docx/output.html">Learn from a document →</a></strong><br>
  74. <sub>Source: DOCX file · Style: <code>kami-reading</code></sub><br>
  75. <sub><strong>Ask:</strong> <code>Make this memo easier to read.</code> (with a docx file attached)</sub>
  76. </td>
  77. <td width="50%" valign="top"></td>
  78. </tr>
  79. </table>
  80. ### Files & Work Data
  81. <table>
  82. <tr>
  83. <td width="50%" valign="top">
  84. <a href="https://clockless-org.github.io/html-anything/examples/editorial-carousel/output.html"><img src="./docs/example-demos/editorial-carousel.gif" alt="Argument as sequence demo" width="100%"></a><br>
  85. <strong><a href="https://clockless-org.github.io/html-anything/examples/editorial-carousel/output.html">Argument as sequence →</a></strong><br>
  86. <sub>Source: strategy essay · Style: <code>editorial-carousel</code></sub><br>
  87. <sub><strong>Ask:</strong> <code>Help me share this strategy essay with my team.</code></sub>
  88. </td>
  89. <td width="50%" valign="top">
  90. <a href="https://clockless-org.github.io/html-anything/examples/pdf/output.html"><img src="./docs/example-demos/pdf.gif" alt="Guide from dense document demo" width="100%"></a><br>
  91. <strong><a href="https://clockless-org.github.io/html-anything/examples/pdf/output.html">Guide from dense document →</a></strong><br>
  92. <sub>Source: PDF report · Style: <code>digital-eguide</code></sub><br>
  93. <sub><strong>Ask:</strong> <code>Summarize this report and let me browse it section by section.</code></sub>
  94. </td>
  95. </tr>
  96. <tr>
  97. <td width="50%" valign="top">
  98. <a href="https://clockless-org.github.io/html-anything/examples/email/output.html"><img src="./docs/example-demos/email.gif" alt="Inbox or workstream audit demo" width="100%"></a><br>
  99. <strong><a href="https://clockless-org.github.io/html-anything/examples/email/output.html">Inbox or workstream audit →</a></strong><br>
  100. <sub>Source: Mbox archive · Style: <code>soft-saas</code></sub><br>
  101. <sub><strong>Ask:</strong> <code>What's happening in my inbox? Show me the open loops.</code></sub>
  102. </td>
  103. <td width="50%" valign="top">
  104. <a href="https://clockless-org.github.io/html-anything/examples/ci-log/output.html"><img src="./docs/example-demos/ci-log.gif" alt="Debugging evidence demo" width="100%"></a><br>
  105. <strong><a href="https://clockless-org.github.io/html-anything/examples/ci-log/output.html">Debugging evidence →</a></strong><br>
  106. <sub>Source: CI log · Style: <code>terminal-cli</code></sub><br>
  107. <sub><strong>Ask:</strong> <code>Why did this build fail? Walk me through it.</code></sub>
  108. </td>
  109. </tr>
  110. </table>
  111. ### Conversation Analysis
  112. <table>
  113. <tr>
  114. <td width="50%" valign="top">
  115. <a href="https://clockless-org.github.io/html-anything/examples/wechat-couple/output.html"><img src="./docs/example-demos/wechat-couple.gif" alt="Private chat recap demo" width="100%"></a><br>
  116. <strong><a href="https://clockless-org.github.io/html-anything/examples/wechat-couple/output.html">Private chat recap →</a></strong><br>
  117. <sub>Source: 1:1 chat export · Style: <code>love-romance-3d</code></sub><br>
  118. <sub><strong>Ask:</strong> <code>Recap our 1:1 chat history. Keep it private — mask names.</code></sub>
  119. </td>
  120. <td width="50%" valign="top">
  121. <a href="https://clockless-org.github.io/html-anything/examples/slack/output.html"><img src="./docs/example-demos/slack.gif" alt="Group contribution analysis demo" width="100%"></a><br>
  122. <strong><a href="https://clockless-org.github.io/html-anything/examples/slack/output.html">Group contribution analysis →</a></strong><br>
  123. <sub>Source: team chat export · Style: <code>kinetic-scoreboard</code></sub><br>
  124. <sub><strong>Ask:</strong> <code>Who's driving the conversation in this Slack channel?</code></sub>
  125. </td>
  126. </tr>
  127. </table>
  128. ### Personal Data & Places
  129. <table>
  130. <tr>
  131. <td width="50%" valign="top">
  132. <a href="https://clockless-org.github.io/html-anything/examples/kindle-highlights/output.html"><img src="./docs/example-demos/kindle-highlights.gif" alt="Reflective reading archive demo" width="100%"></a><br>
  133. <strong><a href="https://clockless-org.github.io/html-anything/examples/kindle-highlights/output.html">Reflective reading archive →</a></strong><br>
  134. <sub>Source: My Clippings.txt · Style: <code>living-essay</code></sub><br>
  135. <sub><strong>Ask:</strong> <code>What have I been reading and thinking about?</code></sub>
  136. </td>
  137. <td width="50%" valign="top">
  138. <a href="https://clockless-org.github.io/html-anything/examples/travel-history/output.html"><img src="./docs/example-demos/travel-history.gif" alt="Mobility recap demo" width="100%"></a><br>
  139. <strong><a href="https://clockless-org.github.io/html-anything/examples/travel-history/output.html">Mobility recap →</a></strong><br>
  140. <sub>Source: Uber/Lyft CSV · Style: <code>global-travel</code></sub><br>
  141. <sub><strong>Ask:</strong> <code>Where have I been this year? Show me on a map.</code></sub>
  142. </td>
  143. </tr>
  144. </table>
  145. ## Install
  146. Pick the path for your agent:
  147. [Claude Code](#claude-code) ·
  148. [Codex](#codex) ·
  149. [claude.ai](#claudeai-web) ·
  150. [Claude API](#claude-api) ·
  151. [Cursor / Cline / Windsurf / OpenCode / Goose / Letta / …](#one-command-for-most-cli-and-editor-agents) ·
  152. [ClawHub](#clawhub-publish)
  153. ### One command for most CLI and editor agents
  154. ```bash
  155. npx skills add clockless-org/html-anything
  156. ```
  157. Works with **Claude Code**, **Codex**, **Cursor**, **Cline**, **Windsurf**,
  158. **OpenCode**, **Goose**, **Letta**, **Roo Code**, **Kiro**, and any other
  159. agent following the [open agent-skills spec](https://agentskills.io).
  160. The CLI also pings [skills.sh](https://skills.sh/clockless-org/html-anything)
  161. so installs feed the public leaderboard.
  162. ### Claude Code
  163. ```bash
  164. git clone https://github.com/clockless-org/html-anything ~/.claude/skills/html-anything
  165. ```
  166. Restart Claude Code so it loads `SKILL.md`. To update later:
  167. `git -C ~/.claude/skills/html-anything pull`.
  168. ### Codex
  169. ```bash
  170. git clone https://github.com/clockless-org/html-anything "${CODEX_HOME:-$HOME/.codex}/skills/html-anything"
  171. ```
  172. Restart Codex.
  173. ### claude.ai (web)
  174. 1. Download [`html-anything-skill.zip`](https://github.com/clockless-org/html-anything/releases/latest/download/html-anything-skill.zip) (`SKILL.md` + `prompts/`, including style references).
  175. 2. In claude.ai: **Settings → Features → Skills → Upload a Skill** → drop the zip.
  176. Requires **Pro / Max / Team / Enterprise** with code execution enabled.
  177. Custom skills on claude.ai are per-user; each teammate uploads their own copy.
  178. ### Claude API
  179. ```bash
  180. curl https://api.anthropic.com/v1/skills \
  181. -H "x-api-key: $ANTHROPIC_API_KEY" \
  182. -H "anthropic-beta: skills-2025-10-02,code-execution-2025-08-25,files-api-2025-04-14" \
  183. -F file=@html-anything-skill.zip
  184. ```
  185. Then reference the returned `skill_id` in the `container` of any message.
  186. See the [Skills API guide](https://platform.claude.com/docs/en/build-with-claude/skills-guide).
  187. Uploaded skills are workspace-wide.
  188. ### ClawHub (publish)
  189. This repo carries `.clawhubignore` so only `SKILL.md` + `prompts/` ship,
  190. including canonical style references used by installed agents:
  191. ```bash
  192. npm i -g clawhub && clawhub login
  193. clawhub publish . --slug html-anything --version 0.1.1 --tags latest
  194. ```
  195. ### Where it does not work
  196. | Surface | Status |
  197. |---|---|
  198. | ChatGPT / chatgpt.com | ❌ Custom GPTs are a different format. Use **OpenAI Codex CLI** instead (above). |
  199. | Gemini web / Google Gems | ❌ Different format. Use **Gemini CLI** (`npx skills add`) instead. |
  200. | Anthropic / Claude Desktop | ✅ Reads `~/.claude/skills/` — same as Claude Code. |
  201. > ℹ Custom Skills do not sync across surfaces. The same skill uploaded to claude.ai is **not** automatically available on Claude Code or the API — each surface keeps its own copy.
  202. ## Use
  203. Just ask your real question. You do not need to mention HTML, pages, dashboards,
  204. reports, atlases, or any of the design vocabulary — the skill decides when an
  205. answer should be a page and ships one.
  206. ```text
  207. Teach me the solar system.
  208. What does my Amazon order history say about me?
  209. Help me understand this CSV.
  210. What did I read in 2025?
  211. Walk me through this GitHub repo.
  212. How did last quarter go?
  213. Make sense of this messy log file.
  214. Recap our 1:1 chat from this year.
  215. ```
  216. Each of these triggers a polished, single-file HTML page in the right design
  217. system. Short conversational asks stay short.
  218. If you name a data source but have no file yet (*"my Spotify history"*,
  219. *"my WhatsApp chat"*, *"my Google Photos Takeout"*), the skill walks you
  220. through the export first.
  221. ## Input And Output
  222. | Input | What you give | What you get |
  223. |---|---|---|
  224. | Rich answer | A topic, analysis request, comparison, recap, brief, or teaching goal | A readable, styled HTML artifact instead of a long written answer |
  225. | Idea | A short brief, e.g. "make a solar system teaching site" | A generated educational / interactive HTML page |
  226. | File | CSV, JSON, Markdown, PDF, DOCX, chat export, log, transcript, statement | A live page designed for that file |
  227. | Folder | Notes vault, Google Photos Takeout, Notion export, repo, exported archive | A browsable atlas / dashboard / audit page |
  228. | URL | Article, GitHub repo, public webpage | A shareable HTML reading or exploration page |
  229. | Export request | "My Amazon orders", "my Spotify history", "my relationship chat" | Export instructions first, then a live HTML page |
  230. The output is a browser page, not a chat reply. Most outputs are a single
  231. `output.html`. When the page needs generated images or other local
  232. assets, the skill returns `output.html + assets/`. Ask for "single-file"
  233. if you need everything in one HTML file.
  234. ## Automatic Usage Routing
  235. You do not need to choose a style. The default is `auto`.
  236. Routing has three layers:
  237. | Layer | Meaning |
  238. |---|---|
  239. | Use case | The user's job: teaching, files/work data, conversation analysis, or personal data/places |
  240. | Source | The input shape: prompt, CSV, PDF, DOCX, chat export, log, repo, folder, URL |
  241. | Style | The design system + layout system used to make the HTML readable |
  242. Styles are not CSS skins. The skill picks the system from the content, then
  243. builds the page inside that system. Every non-fallback style has a checked-in
  244. live example and screenshot preview.
  245. Style fidelity is part of the contract: when a style is based on a reference
  246. HTML or screenshot, the generated page should reproduce the reference's first
  247. viewport, component vocabulary, interaction model, motion grammar, and visual
  248. absence rules. Source modules are translated into the style instead of forcing
  249. every output into the same dashboard/report shape.
  250. Canonical style references can live under `prompts/styles/references/<style>/`,
  251. so the published skill can use the same structural target as the demo gallery
  252. without bundling every example. Style-specific assets stay beside their own
  253. reference pack and are copied only when that style needs them.
  254. | Usage pattern | Style |
  255. |---|---|
  256. | Unknown or mixed inputs | `default` (Insight Brief) |
  257. | Tutorials, lessons, explainers, "teach me" prompts | `teaching` (Lesson Lab) |
  258. | 1:1 chats and intimate message exports | `love-romance-3d` (Keepsake 3D Rhythm) |
  259. | Reflective essays, Kindle highlights, idea notes, concept-heavy reading archives | `living-essay` (Mycelium Writing Environment) |
  260. | Multi-participant activity streams, team chats, ranked contributors, owner/reps/players by workload | `kinetic-scoreboard` (Kinetic Championship) |
  261. | Personal histories — chronological (orders, history, listening, health) **and** topical (Notion / Obsidian vaults) | `timeline-story` (Timeline Story) |
  262. | Travel history, Uber/Lyft exports, and personal mobility recaps | `global-travel` (Global Travel Map) |
  263. | Places, trips, routes, geotagged photos | `map-atlas` (Map Atlas) |
  264. | Contacts, communities, social payments | `network-map` (Network Map) |
  265. | Support mailboxes, email campaigns, onboarding, customer-success queues | `soft-saas` (Soft SaaS Console) |
  266. | Finance, spreadsheets, logs, backlog, operational data | `dashboard` (Ops Console) |
  267. | Essays, articles, reading lists, bookmarks, PDFs, DOCX, legal/medical/lab records | `document` (Document Review) |
  268. | Long prose, DOCX memos, articles, essays, and manuscripts meant for sustained reading | `kami-reading` (Kami Longform Reader) |
  269. | Long-form visual explainers, object-focused articles, architectural split-screen editorial requests | `architectural-spread` (Architectural Editorial Spread) |
  270. | E-guides, PDF guides, creator guides, playbooks, lead magnets | `digital-eguide` (Digital E-Guide Spread) |
  271. | Brand strategy essays, founder letters, article takeaways, lightweight reports meant to be shared as a sequence | `editorial-carousel` (Editorial Carousel) |
  272. | Explicit terminal, CLI, shell, mainframe, hacker-console requests | `terminal-cli` (Terminal CLI, explicit override) |
  273. | Logs, PR patches, stack traces, CI failures, repos | `developer` (Terminal Evidence Workbench) |
  274. You can still steer it naturally: "make it more tutorial-like", "more
  275. app-like", "less academic", "make it a carousel", "more dashboard-like",
  276. or "more playful".
  277. Reusable style prompts live in [`prompts/styles/`](./prompts/styles/).
  278. The shared structural contract is
  279. [`prompts/styles/_system.md`](./prompts/styles/_system.md). The internal
  280. style catalog lives in [`prompts/styles/catalog.json`](./prompts/styles/catalog.json):
  281. it records the four use cases plus each style's triggers, best sources,
  282. example, preview, required primitives, and avoid rules so generation can stay
  283. style-faithful without asking users to pick options. There is a fallback
  284. `default` style plus 17 concrete style systems, each with a live example and
  285. preview asset.
  286. Example explicit style override:
  287. ```bash
  288. npx tsx src/cli.ts examples/pdf/input.pdf \
  289. --style digital-eguide \
  290. --out /tmp/battery-storage-guide.html \
  291. --title "Mid-Market Battery Storage Field Guide"
  292. ```
  293. ## Use Cases And Sources
  294. Sources can be endless, but the skill routes them into four stable use cases.
  295. Each use case can use one or more style systems.
  296. | Use case | Example sources | Likely styles |
  297. |---|---|---|
  298. | Teaching Studios | A short teaching brief, article, lesson outline, concept note, URL, Markdown, DOCX, or PDF/document simplification request | `teaching`, `architectural-spread`, `kami-reading` |
  299. | Files & Work Data | CSV / TSV, spreadsheet-style exports, JSON, JSONL, logs, CI output, PR patches, stack traces, repos, email/support archives, bank transactions, invoices, QuickBooks, calendars, issue trackers, Markdown, PDF, DOCX, bookmarks, URL lists, bibliographies, research records, slide-style carousel outputs | `dashboard`, `soft-saas`, `document`, `kami-reading`, `architectural-spread`, `digital-eguide`, `editorial-carousel`, `developer`, `terminal-cli` |
  300. | Conversation Analysis | WeChat, iMessage-style CSV, Slack, Discord, Telegram, email-style threads | `love-romance-3d`, `kinetic-scoreboard`, `network-map` |
  301. | Personal Data & Places | Amazon orders, Apple Health, browser history, YouTube, Spotify, Twitch, Kindle highlights, Venmo / PayPal, AI chat exports, notes vaults, Google Maps saved places, travel history, GPX, KML, itinerary CSV, location history | `timeline-story`, `global-travel`, `living-essay`, `network-map`, `map-atlas` |
  302. Use case is user-facing; style is internal. The user never has to name a
  303. style — natural asks like *"help me understand this CSV"* or *"teach me the
  304. solar system"* are enough; the skill picks the right system automatically.
  305. The detailed source-specific instructions live in [`prompts/sources/`](./prompts/sources/).
  306. ## Defaults
  307. - The skill chooses the style automatically.
  308. - The skill samples large sources, but renders the full data where practical.
  309. - The skill checks the page in a browser before handing it back.
  310. - Generated pages are local-first and static. They can be opened directly or hosted anywhere static HTML works.
  311. - Generated HTML can embed private source data client-side. Treat the output as sensitive as the original export.
  312. - Sensitive-record outputs are for organization and review only, not medical, legal, tax, accounting, immigration, insurance, or investment advice.
  313. ## Developer Note
  314. This repo also contains a standalone parser / CLI framework used by some
  315. examples, but the primary product surface is the agent skill. Users should
  316. not need to understand the internal implementation to use html-anything.
  317. ```bash
  318. git clone https://github.com/clockless-org/html-anything
  319. cd html-anything
  320. npm install
  321. export ANTHROPIC_API_KEY=sk-ant-... # or OPENAI_API_KEY=sk-...
  322. npx tsx src/cli.ts examples/csv/input.csv --out /tmp/customers.html
  323. ```
  324. ## License
  325. [MIT-0](./LICENSE)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.