richdoc
This skill should be used when the user asks to "write a research report", "create a plan document for review", "produce a polished design doc", "draft a comparison sheet", "generate a richdoc", "make a one-pager", "write a status report", "produce an executive summary", "create a decision document", "build a dashboard page", or any other rich HTML deliverable intended for human review in a browser. Authors plain .html files using a small fixed vocabulary of rd-* web components for layout and rich blocks. Includes a CLI for scaffolding, asset installation, schema introspection, and validation.
What this skill does
# richdoc
richdoc is for **AI-authored, human-read HTML documents**. The agent writes a normal `.html` file using a closed vocabulary of `rd-*` custom elements. Two shipped assets (`richdoc.css`, `richdoc.js`) give every component its editorial look and behavior. No build step on the consumer side; the file opens in any browser, with or without a server.
## When to use richdoc
Plans, research reports, design docs, status one-pagers, decision memos, comparisons, postmortems, dashboards — anything where the reader is a person in a browser. Use markdown only when the renderer might be anything else (GitHub, chat, CLI). Anywhere else, richdoc is the better default.
## Authoring rules
When writing a richdoc, the agent **must**:
1. Produce a complete HTML5 document with exactly one `<rd-page>` directly inside `<body>`. Link `richdoc.css` and `richdoc.js` from `<head>`.
2. Use **only** the `rd-*` tags listed below. Inventing new ones causes lint errors and renders as empty boxes.
3. For prose, use plain semantic HTML — `<p>`, `<ul>`, `<ol>`, `<li>`, `<a>`, `<strong>`, `<em>`, `<code>`, `<pre>`, `<h1>`–`<h6>`, `<blockquote>`, `<hr>`, `<img>`, `<table>`. These are styled automatically.
4. Prefer `<rd-callout>` over bold-italic emphasis for asides longer than a few words.
5. Use `<rd-cols>` for genuinely parallel content (cards, stats, comparisons). Do not use it to force a two-column paragraph layout.
6. Put code in `<rd-code lang="…">`, diffs in `<rd-diff lang="…">`, math in `<rd-math>`, diagrams in `<rd-diagram lang="…">`. Don't fall back to `<pre>`.
7. **Never self-close custom elements.** Write `<rd-foo ...></rd-foo>`, not `<rd-foo ... />` — HTML5 ignores the slash on non-void custom elements and the tag silently absorbs the following siblings. `richdoc lint` catches this as `self-closing-custom-element`.
8. Run `richdoc lint <file>` before declaring the doc done.
## CLI
Path: `./richdoc-cli/richdoc` (relative to this SKILL.md). Requires [`uv`](https://docs.astral.sh/uv/); the first call provisions the Python environment.
| Command | Description |
| --- | --- |
| `richdoc new <output> [-t <template>]` | Scaffold a new `.html` from a template. |
| `richdoc init [dir]` | Copy `richdoc.css` and `richdoc.js` into a directory. |
| `richdoc update [dir] [--apply]` | Refresh stale shipped assets. |
| `richdoc lint <file-or-dir> [--fix]` | Validate against the rd-* schema and book-mode authoring rules. `--fix` autofixes `hero-nav-redundant`. |
| `richdoc components [--tag <name>]` | Print the vocabulary from the live schema. |
| `richdoc export md\|docx <file>` | Export to markdown or DOCX. (HTML is the source format — no export needed.) See [references/export.md](references/export.md). |
| `richdoc export confluence <file-or-dir>` | Build an offline Confluence storage bundle (storage XML + attachments + manifest). Runs `richdoc lint` first. The bundle is published by the separate `confluence` skill, never by `richdoc` itself. See [references/export.md](references/export.md). |
Templates: `plan`, `research`, `comparison`, `onepager`, `adr`, `runbook`, `book-index`, `book-chapter`.
## Minimal example
```html
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>My plan</title>
<link rel="stylesheet" href="./richdoc.css">
<script src="./richdoc.js" defer></script>
</head>
<body>
<rd-page>
<rd-hero title="My plan" eyebrow="Design doc"></rd-hero>
<rd-callout type="tldr">
<p>Two-sentence summary of what changes and why it matters.</p>
</rd-callout>
<rd-section title="Problem">
<p>Plain prose, lists, and links work as usual.</p>
</rd-section>
<rd-section title="Options">
<rd-cols n="2">
<rd-card title="Option A" accent="success">Pros, cons.</rd-card>
<rd-card title="Option B" accent="warn">Pros, cons.</rd-card>
</rd-cols>
</rd-section>
</rd-page>
</body>
</html>
```
## Element index
One line per tag, grouped by purpose. For attributes, run `richdoc components --tag rd-xxx` or see [references/elements.md](references/elements.md).
### Structure
- `<rd-page>` — outer container. Exactly one per doc, directly under `<body>`. Supports `theme`, `mode`, `width`, `toc`, `prefs`, `diagram-endpoint`.
- `<rd-hero>` — magazine title block.
- `<rd-section>` — titled section with eyebrow numeral.
- `<rd-cols>` — multi-column grid (`n="2|3|4"` or `template="2fr 1fr"`).
- `<rd-card>` — bordered block with optional accent.
### Information
- `<rd-callout>` — `info|success|warn|danger|note|tldr` aside.
- `<rd-kv>` / `<rd-row>` — spec block (`layout="inline"`) or glossary (`layout="stacked"`).
- `<rd-badge>` — inline status tag.
- `<rd-stat>` — big-number tile, optional sparkline slot.
- `<rd-progress>` — capacity bar.
- `<rd-update>` — dated changelog entry (`release|change|note`).
### Code, math, diagrams
- `<rd-code lang="…">` — fenced code with syntax highlighting.
- `<rd-diff lang="…">` — unified diff.
- `<rd-shell>` / `<rd-prompt>` / `<rd-output>` — terminal session.
- `<rd-math>` — KaTeX math.
- `<rd-diagram lang="…">` — Kroki diagram. See [Diagrams](#diagrams).
- `<rd-chart>` — Observable Plot chart or sparkline.
### Comparison, decision, planning
- `<rd-compare>` / `<rd-row-cells>` / `<rd-cell>` — decision matrix.
- `<rd-rubric>` / `<rd-criterion>` / `<rd-score>` — weighted scoring grid.
- `<rd-pros-cons>` / `<rd-pro>` / `<rd-con>` — ✓/✗ evaluation.
- `<rd-decision>` — ADR-style record (`proposed|accepted|superseded|rejected`).
### Sequenced & interactive
- `<rd-steps>` / `<rd-step>` — numbered procedure.
- `<rd-timeline>` / `<rd-event>` — vertical timeline.
- `<rd-checklist>` / `<rd-task>` — task list.
- `<rd-detail>` — collapsible (`panel|hairline|question|reveal`).
- `<rd-tabs>` / `<rd-tab>` — tabbed content (specialist; usually a section is clearer).
### Reference & navigation
- `<rd-api>` / `<rd-param>` / `<rd-response>` — single-endpoint API doc.
- `<rd-references>` / `<rd-ref>` / `<rd-cite>` — bibliography + inline citations.
- `<rd-toc>` / `<rd-chapter>` — auto TOC; book-mode for multi-file docs. See [references/multi-file-books.md](references/multi-file-books.md).
- `<rd-icon>` — Lucide icon (~1,900 names; see [ICONS.md](ICONS.md)).
- `<rd-figure>` — captioned media wrapper.
- `<rd-banner>` — doc-status ribbon (`draft|frozen|archived|confidential|info`).
## Pick the right element
| You want to … | Use |
| --- | --- |
| Show a side-by-side options matrix with headers | `<rd-compare>` |
| Score options on weighted criteria | `<rd-rubric>` |
| List ✓ / ✗ trade-offs for one or more options | `<rd-pros-cons>` |
| Show a key / value spec block at the top | `<rd-kv>` (inline) |
| Define terms in a glossary | `<rd-kv layout="stacked">` |
| Show a fenced code sample | `<rd-code>` |
| Show a terminal session with commands and output | `<rd-shell>` (NOT `<rd-code>`) |
| Show a diff between two versions | `<rd-diff>` |
| Highlight a single number with trend | `<rd-stat>` |
| Show progress / capacity / utilisation | `<rd-progress>` |
| Show a trend over time | `<rd-chart kind="line">` or sparkline in `<rd-stat>` |
| Mark a doc as draft / frozen / confidential | `<rd-banner>` (top of page) |
| Status-tag a row of content inline | `<rd-badge>` |
| Aside or "callout" of any length | `<rd-callout>` (not bold/italic emphasis) |
| Render a flow / sequence / state / class diagram | `<rd-diagram lang="…">` |
| Pull-quote, epigraph | native `<blockquote>` (auto-styled) |
| Cite a source inline | `<rd-cite key="…">` paired with `<rd-ref>` |
## Recipes
Each recipe lists the 5–10 tags you'll actually need. Reach beyond the list only with reason.
**Status one-pager** — `rd-page`, `rd-hero`, `rd-kv`, `rd-stat`, `rd-progress`, `rd-callout`, `rd-update`, `rd-checklist`.
**Plan / design doc** — `rd-page`, `rd-hero`, `rd-callout` (tldr + problem), `rd-section`, `rd-pros-cons`, `rd-steps`, `rd-detail` (open questions).
**Research reportRelated in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.