Preview logo

Preview

Community
kv0906
preview

Render vault notes as styled HTML and open in browser. Turn markdown docs, decisions, progress reports into readable previews. Use for "/preview docs/project-a/checkout-flow.md", "/preview progress all", "/preview decide auth-approach", or when user wants to see a doc before sharing.

Overview

Publisherkv0906
Repositorypm-kit
Skill namepreview
Stars
140
Forks
35
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by kv0906 on GitHub. Read the source before you install it.

Installation

Install the Preview 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/kv0906/pm-kit/tree/main/.claude/skills/preview
  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/kv0906/pm-kit.git /tmp/pm-kit
mkdir -p .claude/skills
cp -r /tmp/pm-kit/.claude/skills/preview .claude/skills/preview
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Preview 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 Preview 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 Preview 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.

/preview — HTML Preview

Render vault content as styled HTML for browser viewing. Markdown stays the source of truth; HTML is the presentation layer.

Context

Today's date: !date +%Y-%m-%d

Config: @_core/config.yaml Preview rules: @.claude/rules/preview-formats.md HTML shells: @_templates/html/ Processing logic: @_core/PROCESSING.md

Usage

/preview docs/project-a/checkout-flow.md
/preview decisions/project-a/2026-06-29-auth-approach.md
/preview progress all
/preview progress project-a --week
/preview decide auth-approach
/preview block api-rate-limit
/preview meet 2026-06-29-sync-sprint-review
/preview reports/2026-06-29-progress-all.md

Flags

FlagEffect
--with-linksInline first paragraph from linked notes
--no-openWrite HTML only, do not open browser
--shell memo|prd|status|executiveForce template shell
--linkWrite preview: path to source note frontmatter

Session Task Progress

TaskCreate: "Resolve preview source"
  activeForm: "Resolving preview source..."

TaskCreate: "Render HTML"
  activeForm: "Rendering HTML preview..."

TaskCreate: "Open and verify"
  activeForm: "Opening preview in browser..."

Processing Steps

1. Parse Input

Determine source mode:

Input patternAction
Path to .md fileRead that file directly
progress {project|all}Synthesize like /progress, use status shell
decide {slug}Glob decisions/*/*{slug}*.md, pick latest
block {slug}Glob blockers/*/*{slug}*.md
meet {slug}Glob meetings/*{slug}*.md
doc {project} {slug}Read docs/{project}/{slug}.md

If ambiguous, ask user to clarify path.

2. Gather Content

File mode: Read markdown + frontmatter.

Synthesis mode (progress): Follow /progress gather steps:

  • Scan dailies, blockers, docs, decisions for project/timeframe
  • Build structured sections: Shipped, In Progress, Blockers, Decisions
  • Count metrics for status shell

3. Select HTML Shell

Auto-detect from source:

SourceShell
docs/shell-prd.html
decisions/, meetings/, blockers/shell-memo.html
progress synthesisshell-status.html
reports/*executive*shell-executive.html
Othershell-memo.html (default)

Override with --shell flag.

4. Convert Markdown → HTML

  • Remove YAML frontmatter block
  • Map frontmatter to shell vars: project, status, date, title (from H1 or filename)
  • Convert body markdown to semantic HTML
  • Resolve [[wikilinks]] per preview-formats.md
  • Escape user content in HTML (no XSS — literal text only)

5. Write Output

  • Ensure reports/previews/ exists
  • Filename: {date}-{slug}.html (slug from source file or synthesis type)
  • Load shell template, replace all {{PLACEHOLDER}} tokens
  • Write complete self-contained HTML file

6. Open Browser

Unless --no-open:

bash
# macOS
open "reports/previews/{filename}.html"

# Linux
xdg-open "reports/previews/{filename}.html" 2>/dev/null

# Windows
start "" "reports/previews/{filename}.html"

7. Optional: Link Back to Source

If --link and source is a single vault note:

  • Edit source frontmatter: preview: reports/previews/{filename}.html

8. Append Vault Log

Append to 01-index/_vault-log.md:

  • Action: preview
  • Files: output HTML path + source path
  • Details: shell used, synthesis or file mode

Output

Preview ready: reports/previews/2026-06-29-checkout-flow.html
Shell: prd
Source: docs/project-a/checkout-flow.md
Opened in browser.

Error Handling

SituationAction
Source file not foundSuggest similar paths via Glob
Empty vault (progress)Report "no data in timeframe" — do not write empty HTML
Browser open failsReport file path; user can open manually

Design Principles

  • Typography first — readable fonts, generous line-height, print-ready
  • No dependencies — pure HTML/CSS, no npm/pip required
  • Self-contained — single file, embedded styles, works offline
  • Source preserved — never modify markdown body unless --link requested

Frequently asked questions

What does the Preview AI skill do?

Render vault notes as styled HTML and open in browser. Turn markdown docs, decisions, progress reports into readable previews. Use for "/preview docs/project-a/checkout-flow.md", "/preview progress all", "/preview decide auth-approach", or when user wants to see a doc before sharing.

Why use Preview on TypingMind?

Because you install it once and use it with any model. Preview 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 Preview in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kv0906/pm-kit/tree/main/.claude/skills/preview. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Preview?

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 Preview?

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

Is the Preview AI skill free?

Yes. It is published on GitHub by kv0906 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 👇