Html Summary logo

Html Summary

Organization
testdouble
html-summary

Convert a stakeholder summary markdown file into a single self-contained HTML executive report — bottom line and decision asks up front, supporting detail later — styled with a Test Double-derived palette and self-contained mermaid diagrams. Use when the user wants to turn a stakeholder summary, executive summary, or business summary into an HTML report, generate an HTML version of a summary doc, or produce a shareable HTML file from a summary markdown. Produces an HTML sibling file only; does not publish anything.

Overview

Publishertestdouble
Repositoryhan
Skill namehtml-summary
Stars
320
Forks
26
Bundled files
6
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 6 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by testdouble on GitHub. Read the source before you install it.

Installation

Install the Html Summary AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/testdouble/han/tree/main/han-reporting/skills/html-summary
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/testdouble/han.git /tmp/han
mkdir -p .claude/skills
cp -r /tmp/han/han-reporting/skills/html-summary .claude/skills/html-summary
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Html Summary in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Html Summary on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Html Summary is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Project Context

  • personal config directory: !bash "${CLAUDE_PLUGIN_ROOT}/scripts/han-config-dir.sh" 2>/dev/null || echo "$HOME/.claude"
  • project .han/config.md: !cat .han/config.md 2>/dev/null || echo ""

As your first action, use the Read tool on .han/config.md inside the personal config directory path above. A read that returns no file is no personal configuration: continue silently. When that file or the project .han/config.md probe supplies content, apply it per config-rule.md, which governs precedence between the two files, relative-path resolution, and what to do with a file that reads but cannot be used.

HTML Summary

Convert a stakeholder summary markdown file into a single self-contained HTML report tailored for executive readers — bottom line and decision asks up front, supporting detail later — styled with a Test Double-derived palette. The skill produces one HTML file next to the source markdown and stops there.

Inputs

  • Source markdown file — usually a stakeholder-summary.md inside a planning folder. If the user does not name one, ask. Do not guess.

Output

  • HTML sibling file — written next to the source markdown, same basename, .html extension. Example: filters-and-saved-views/stakeholder-summary.md → filters-and-saved-views/stakeholder-summary.html. This is the only artifact the skill produces.

Hard rules

  • Single file, no external network resources. No <link rel="stylesheet">, no <script src=...> pointing at a CDN, no remote font loading, no remote images. Inlined JavaScript libraries (such as mermaid.js) are allowed and expected — they keep the file self-contained.
  • Inline all CSS in a <style> block in <head>. The file must render correctly offline.
  • Do not modify the source markdown. This skill is one-way: markdown in, HTML out.
  • Do not commit, push, or publish. The skill writes the HTML file to disk and reports its path. Sharing the file is the user's call, outside this skill.
  • Executive ordering is non-negotiable. Bottom line (TL;DR) and the stakeholder asks appear before any other content, in that order. Restructure if the source markdown puts them later. See references/layout-principles.md.
  • Use the report palette only. Colors, typography, spacing, and component patterns come from references/report-style.md. Do not invent new accent colors.
  • Header: subject as the title, fixed subtitle, no brand mark. The <h1> is the summary subject (the feature name). The .subtitle beneath it is the literal string Han: Stakeholder Summary on every report. The header carries no logo or brand mark.
  • No superlatives in user-visible text. Banned word lists and rewrite patterns live in references/writing-conventions.md. Verify before finishing.
  • Apply the shared readability standard to prose. Source the standard by invoking han-communication:readability-guidance and apply it to the prose content this skill writes or transfers, holding the named audience — the non-technical stakeholder. The report's visual layout stays governed by references/layout-principles.md and references/report-style.md.
  • Preserve the source's plain-language framing. Do not rewrite content to be more technical or more abstract. Keep the source's wording where it works; tighten only when restructuring for the executive layout.

Process

1. Locate the source markdown

If the source path is not in the conversation, ask for it. Resolve to an absolute path and confirm it exists. The output HTML path is the source path with .md replaced by .html.

2. Read the source end-to-end

Read the entire markdown file. Identify which of these sections (or equivalents) are present, in any order:

  • The bottom line / executive summary / TL;DR (sometimes implicit — derive from the opening paragraph)
  • The stakeholder asks / open decisions (sometimes titled "What we are asking stakeholders" or similar)
  • The problem statement
  • What the change opens up / outcomes
  • User experience walkthrough
  • Today-vs-after data flow comparisons (sometimes with mermaid diagrams)
  • What is intentionally not in scope

Section titles in the source may not match these names exactly — map by content, not heading text.

3. Load the references

Read all references before producing HTML:

4. Produce the HTML

Write the HTML file to the output path. Required structure, in order:

  1. Header — <h1> set to the summary subject (the feature name) with the most evocative noun phrase wrapped in <span class="highlight">; .subtitle set to the literal string Han: Stakeholder Summary. No brand mark.
  2. Bottom line card — purple accent strip; one-sentence lead in larger type; 4–8 outcome bullets in a two-column list.
  3. Stakeholder asks card — orange accent strip; numbered list of decisions the team needs from stakeholders. Each ask has a short title and a one-paragraph question ending with **Confirm ...?**. If the source has no asks section, omit this card entirely — do not invent decisions.
  4. Problem statement section.
  5. What this opens up section — outcome bullets.
  6. User experience walkthrough section — numbered walk list.
  7. Data flow section — today and after cards stacked one per row, each card spanning the page wrap's content width. Do not place data-flow cards side-by-side in a .grid-2 wrapper. Each card contains a <pre class="mermaid"> block with the source's mermaid syntax preserved (branching, decision diamonds, labeled edges). Normalize style directives to the report palette per references/report-style.md.
  8. Intentionally not in scope section — out-of-scope list.

Readability of the prose. Invoke han-communication:readability-guidance to surface the shared readability standard into your context; the text in these sections follows that standard — do not duplicate its text, apply it. Lead with the main point (bottom line up front, which the executive ordering already enforces), give each heading a descriptive name rather than a generic label, keep one idea per paragraph with the first sentence carrying it, number sequential steps and bullet non-sequential items, and reveal detail in layers. This governs the prose only; the visual layout stays governed by the layout conventions above.

The template includes a mermaid bundle placeholder near the end of <body>:

html
<script id="mermaid-bundle">
  <!-- MERMAID_BUNDLE_INLINE_HERE -->
</script>
<script>
  mermaid.initialize({ ... });
</script>

Leave the placeholder string <!-- MERMAID_BUNDLE_INLINE_HERE --> exactly as written. The inliner script in Step 6 replaces it with the vendored mermaid.min.js bundle. The mermaid initialization block (with the report palette theme variables) is also part of the template — paste it verbatim.

Section omission rules:

  • Omit any section the source markdown does not address. Do not invent content to fill a section.
  • The bottom line card is the only required section other than the header — if the source has no explicit TL;DR, derive one from the opening paragraph and clearly mark it as such in your work notes.

Markup rules:

  • Use the entity &mdash; not — for em-dashes in HTML body content (the template does this consistently).
  • Use the entity &rarr; for arrows in flow diagrams.
  • Apply class names verbatim from the template — tldr, ask-block, ask, walk, flow, node, node.good, node.bad, node.start, out-of-scope, chip, chip.good, chip.bad.
  • Wrap the feature-name portion of the <h1> in <span class="highlight"> for the green background.

5. Verify the HTML

Open the file you just wrote and confirm:

  • The <style> block exists in <head> and contains the :root palette variables from references/report-style.md.
  • There are no <link>, <script src=...>, or external url(...) references in <head> or <body>.
  • The <h1> is the summary subject and the .subtitle reads Han: Stakeholder Summary.
  • Every section that exists in the source markdown has a corresponding section in the HTML.
  • The bottom-line card and asks card (if present) appear before any other content section.
  • No banned superlatives appear in user-visible text (see references/writing-conventions.md).

Then run the standardized readability self-check (the shared standard is in your context from han-communication:readability-guidance) over the report's PROSE content only — never inside HTML tags, attributes, class names, mermaid/diagram bodies, or code. The visual layout stays governed by the existing layout conventions. This skill runs no rewrite pass, so this self-check is the fidelity guard on the prose; the fidelity criterion is not optional. Confirm each criterion and fix any failure before finalizing:

Run the readability rule's standardized self-check, which is already in your context from the readability-guidance invocation above. Correct every failure before Step 6. Its fidelity criterion is not optional: the standard governs how the content is said, and drops a required fact only when the reader asked for less and losing it would not change what they do next.

The vocabulary blocklist for this skill is the shared one plus its supplementary domain terms in writing-conventions.md.

If any check fails, fix it before Step 6.

6. Inline the mermaid bundle

Make the file self-contained by inlining the vendored mermaid bundle in place of the placeholder: run ${CLAUDE_SKILL_DIR}/scripts/inline-mermaid.sh <path-to-html-file> and capture its output.

The script is idempotent: it replaces the <!-- MERMAID_BUNDLE_INLINE_HERE --> placeholder with the contents of assets/mermaid.min.js. If the report has no diagrams (no placeholder), it leaves the file untouched and exits cleanly. If the script exits non-zero, surface the error to the user; do not retry blindly — read the error.

7. Report

Tell the user:

  • The output file path.
  • That the diagrams were inlined (or that the report had no diagrams to inline).

If you had to derive the bottom line because the source had no explicit TL;DR, mention that so the user can review the framing.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Html Summary AI skill do?

Convert a stakeholder summary markdown file into a single self-contained HTML executive report — bottom line and decision asks up front, supporting detail later — styled with a Test Double-derived palette and self-contained mermaid diagrams. Use when the user wants to turn a stakeholder summary, executive summary, or business summary into an HTML report, generate an HTML version of a summary doc, or produce a shareable HTML file from a summary markdown. Produces an HTML sibling file only; does not publish anything.

Why use Html Summary on TypingMind?

Because you install it once and use it with any model. Html Summary is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Html Summary in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/testdouble/han/tree/main/han-reporting/skills/html-summary. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Html Summary?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Html Summary?

As many as you like. As long as a model supports skills, you can use Html Summary with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Html Summary AI skill free?

Yes. It is published on GitHub by testdouble under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇