跳到正文
cccskills
免费在 GitHub 公开

HTML

Turn completed research, analysis, reports, or plans from the current session into a self-contained HTML artifact. A renderer controls layout, typography, and color, using structured content and a choice of two visual styles.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Renders the current session's output (analysis, research, red team, report, plan) as an extremely well-designed, self-contained HTML artifact via a deterministic renderer — the model distills content into typed JSON, the tool owns all layout/typography/color. USE WHEN /HTML, HTML artifact, render this as HTML, make this an HTML page, artifact of this analysis, designed HTML output. NOT FOR deployed websites or web apps (build the project directly), web UI design systems (use Webdesign), static images or diagrams (use Art), or writing the underlying analysis itself (run the analysis first, then /HTML renders it).

查看安装方法

适用场景

  • Turn research findings into an HTML artifact
  • Format a cost analysis with tables and callouts
  • Present investigation findings as a designed document
  • Convert a completed plan into a single HTML file

包含的文件(3)

  • SKILL.md4.0 KB
  • Tools/Render.ts12.9 KB
  • Workflows/Render.md2.7 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

HTML

Turns whatever the session just produced into one self-contained, designed HTML file and publishes it as an Artifact. Deterministic split: the model's only job is distilling the session output into a typed content JSON and picking a design register; Tools/Render.ts owns every layout, typography, and color decision.

Voice Notification

When executing a workflow, do BOTH:

  1. Send voice notification:

    curl -s -X POST http://localhost:31337/notify \
      -H "Content-Type: application/json" \
      -d '{"message": "Running the Render workflow in the HTML skill to build a designed HTML artifact"}' \
      > /dev/null 2>&1 &
    
  2. Output text notification:

    Running **Render** in **HTML**...
    

Workflow Routing

WorkflowTriggerFile
Render/HTML, "HTML artifact", "render this as HTML"Workflows/Render.md

Quick Reference

  • Renderer: bun ~/.claude/skills/HTML/Tools/Render.ts --json content.json --register dossier --out artifact.html
  • --schema prints the content JSON shape with an example; --registers lists registers.
  • Registers: dossier (dark ink-green / orange, condensed display + typewriter — evidence files, red teams, investigations) and ledger (dark navy / gold, old-style serif — reports, finance, plans, comparisons). Alternate between them so consecutive outputs don't converge; add new registers to Render.ts rather than hand-styling one-offs.
  • Output is Artifact-CSP safe: inline CSS, fonts embedded as data URIs from local font files, zero external requests.

Gotchas

  • DOM-render screenshot pipelines drop CSS pseudo-element generated content (counters, ::before labels render in the browser but vanish from DOM-render captures, and they're invisible to text extraction). Render.ts therefore emits all numbering and labels as real DOM text. Never add CSS counters to a register. (Discovered 2026-07-11.)
  • Artifacts block all external requests — a Google Fonts <link> fails silently and you get the fallback stack. Embed via data-URI @font-face (Render.ts does this when the register's font file exists locally) or design on system stacks.
  • The artifact viewer wraps your file in its own document skeleton — emit <title> + <style> + body content only; no <!doctype>/<html>/<head>/<body> tags.
  • A published artifact is private to its owner's claude.ai account — verifying it in a browser signed into a different account/org 404s. Verify the render by serving the HTML file locally and capturing that; verify publication via the Artifact tool's list action.
  • Numbered section markers must mean something. Render.ts numbers sections (document order — legitimate). Don't number list items unless the content is a true sequence; use list blocks with bold lead-ins instead.

Examples

Example 1: After a research or red-team session

User: "/HTML"
→ Render workflow: distill the session's findings into content JSON
→ bun Tools/Render.ts --json content.json --register dossier --out artifact.html
→ Publish via Artifact tool (load artifact-design skill first), pixel-verify, hand over URL

Example 2: Different subject, different register

User: "render the quarterly cost analysis as HTML"
→ Same flow with --register ledger (tables, callouts)
→ Alternates the look from the last artifact so outputs don't converge

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Compare a component's own design needs with the goals of the larger system through three structured passes. The result identifies conflicts, recommends an appropriate scope, and assesses whether the proposed design fits the whole.

中文简介正在准备中。当前显示英语简介。

  • Choosing between a service, a library, and inline code
  • Comparing feature requests with product goals
  • Checking how new components fit an existing system
danielmiessler/LifeOS2万2026年9月4日 更新

Aphorisms

免费

Find quotes that fit a text’s themes, with attribution and a short reason for each suggestion. Add sourced quotes, research thinkers, and organize a quote collection by theme and usage history to avoid repetition.

中文简介正在准备中。当前显示英语简介。

  • Finding a fitting quote for a newsletter
  • Saving sourced quotes without duplicates
  • Researching a thinker’s quotes by theme
danielmiessler/LifeOS2万2026年9月4日 更新

Apify

免费

Collect social posts, business listings, and product reviews through Apify actors, ready-made data collection tools. Filter results by date, rating, or engagement in code before sending relevant records to the AI for research or lead generation.

中文简介正在准备中。当前显示英语简介。

  • Find competitors' most popular social posts
  • Build a contact list of local businesses
  • Extract recent negative Amazon reviews
danielmiessler/LifeOS2万2026年9月4日 更新

Art

免费

Create blog illustrations, technical diagrams, comparisons, comics, and icons through workflows tailored to each format. The skill guides composition, color, and model selection, then stages generated images for review before they are used in a project.

中文简介正在准备中。当前显示英语简介。

  • Creating blog header illustrations
  • Explaining a system with a technical diagram
  • Visualizing comparisons and timelines
danielmiessler/LifeOS2万2026年9月4日 更新

ArXiv

免费

Find arXiv papers by topic, research category, or paper ID. Retrieve titles, authors, abstracts, and links, check new submissions, and add AlphaXiv's AI-generated overviews when available to help decide which papers to read.

中文简介正在准备中。当前显示英语简介。

  • Checking new AI and machine learning papers
  • Finding papers on a specific research topic
  • Looking up a paper by its ID or arXiv URL
danielmiessler/LifeOS2万2026年9月4日 更新

Clean spoken recordings by transcribing words, identifying filler and false starts, and joining cuts with short audio fades. Preview proposed edits, reduce breaths, repair noise-gate clicks, and optionally use Cleanvoice for additional cloud processing.

中文简介正在准备中。当前显示英语简介。

  • Removing filler words and long silences from a podcast
  • Reviewing proposed edits before applying them
  • Repairing clicks caused by a noise gate
danielmiessler/LifeOS2万2026年9月4日 更新

查看 danielmiessler 的全部技能

报告此技能的问题