opencode-starterkit 1.0.1

package/baseline/skill/memory-system/SKILL.md

@@ -0,0 +1,84 @@
+---
+name: memory-system
+description: Use when persisting learnings, loading previous context, or searching past decisions - covers memory file structure, tools, and when to update each file
+version: 1.1.0
+tags: [context, workflow]
+dependencies: []
+---
+
+# Memory System Best Practices
+
+> **Replaces** losing context between sessions — persistent knowledge that survives session boundaries
+
+## When to Use
+
+- Starting work and needing prior decisions, bugfixes, or patterns
+- Recording non-obvious decisions/learnings for future sessions
+- Creating handoffs so the next session can continue quickly
+
+## When NOT to Use
+
+- Ephemeral debugging notes that won't matter after the current task
+- Storing generated artifacts/log dumps as long-term memory
+
+## Core Principle
+
+**Progressive disclosure**: search compactly, fetch fully only when relevant, then record high-signal observations.
+
+## Session Workflow
+
+1. **Ground (search first)**
+   - Run `memory-search` with task keywords before implementation.
+   - Check recent handoffs when resuming interrupted work.
+2. **Calibrate (progressive disclosure)**
+   - Use search results as index.
+   - Fetch full entries only for relevant IDs (`memory-get`).
+   - Pull timeline context only when sequencing matters (`memory-timeline`).
+3. **Record (high-signal only)**
+   - Create `observation` for decisions, bugfixes, patterns, warnings, or durable learnings.
+   - Include searchable concepts and concrete file references.
+4. **Handoff (if session boundary)**
+   - Write a concise status note with completed work, blockers, and next steps using `memory-update` under `handoffs/`.
+
+## What Goes Where
+
+| Store | Put Here | Avoid Here |
+| --- | --- | --- |
+| `observation` (SQLite) | Events: decisions, bugfixes, reusable patterns, warnings | Temporary notes, speculative ideas without evidence |
+| `memory-update` files | Durable docs: handoffs, research, project notes | Every minor runtime detail from a single debug run |
+| Auto pipeline | Captured messages + distillations (automatic) | Manual copying of full transcripts |
+
+## Observation Quality Bar
+
+Use this checklist before creating an observation:
+
+- Is it likely useful in a future session?
+- Is it non-obvious (not already in code/comments)?
+- Can I summarize it in one clear title + short narrative?
+- Did I include strong search terms in `concepts` and relevant files?
+
+If most answers are "no", skip creating the observation.
+
+## Anti-Patterns
+
+| Anti-Pattern | Why It Fails | Instead |
+| --- | --- | --- |
+| Storing transient debugging info as permanent observations | Pollutes search results with low-value noise | Keep transient info in session context; record only durable findings |
+| Creating observations for every small finding (signal-to-noise) | Important items get buried and retrieval quality drops | Batch minor notes; publish one distilled observation per meaningful outcome |
+| Not searching memory before creating duplicate observations | Produces conflicting/duplicated records | Run `memory-search` first; update/supersede existing records when appropriate |
+| Using `memory-update` for data that should be an observation | Durable events become hard to discover and rank | Use `observation` for events; reserve `memory-update` for document-style files |
+
+## Verification
+
+After creating an observation: `memory-search` with relevant keywords should find it.
+
+## Practical Defaults
+
+- Prefer specific queries over broad ones (`"auth race condition init"` > `"auth"`).
+- For ongoing work, append to one handoff file per task/day instead of many tiny files.
+- Keep observation titles concrete and action-oriented.
+
+## See Also
+
+- `context-management`
+- `session-management`

package/baseline/skill/mockup-to-code/SKILL.md

@@ -0,0 +1,184 @@
+---
+name: mockup-to-code
+description: Use when converting UI mockups, screenshots, Figma/Sketch designs, wireframes, or building component libraries from design systems into production-ready code
+version: 1.0.0
+tags: [ui, workflow]
+dependencies: []
+---
+
+# Mockup to Code Skill
+
+> **Replaces** manual pixel-by-pixel CSS translation from designs — structured extraction of layout, colors, typography, and components from visual references
+
+## When to Use
+
+- Converting Figma/Sketch mockups to React/Vue/HTML
+- Implementing pixel-perfect designs
+- Building component libraries from design systems
+- Rapid prototyping from wireframes
+
+## When NOT to Use
+
+- No visual reference or mockup to implement.
+
+## Workflow
+
+1. **Analyze** — Use vision agent to extract: layout structure, color palette, typography, spacing, components
+2. **Map** — Match extracted elements to existing design tokens/components in the codebase
+3. **Implement** — Build components using extracted specs, reusing existing tokens where possible
+4. **Verify** — Screenshot the result and compare visually to the original mockup
+
+## Core Workflow
+
+### Phase 1: Design Analysis
+
+```
+Analyze this UI mockup and extract:
+
+1. LAYOUT STRUCTURE
+   - Grid system (columns, gutters, margins)
+   - Component hierarchy
+   - Container widths
+
+2. VISUAL SPECIFICATIONS
+   - Colors (hex values)
+   - Typography (sizes, weights)
+   - Spacing (padding, margins, gaps)
+   - Border radius, shadows
+
+3. COMPONENTS IDENTIFIED
+   - List each distinct component
+   - Note variations
+   - Identify reusable patterns
+
+4. RESPONSIVE CONSIDERATIONS
+   - How might this adapt to mobile?
+   - Collapsible sections
+   - Priority content
+
+Output as structured JSON.
+```
+
+### Phase 2: Component Breakdown
+
+```markdown
+## Component: [Name]
+
+**Priority:** High/Medium/Low
+**Complexity:** Simple/Medium/Complex
+**Reusability:** One-off/Reusable/Design System
+
+**Props Interface:**
+
+- variant: 'primary' | 'secondary'
+- size: 'sm' | 'md' | 'lg'
+- disabled?: boolean
+
+**Accessibility:**
+
+- Keyboard navigation
+- ARIA labels
+- Focus management
+```
+
+### Phase 3: Implementation
+
+Implement with comparison loop:
+
+```
+Compare mockup vs implementation:
+
+1. What differences do you see?
+2. What's missing?
+3. Spacing/sizing adjustments needed?
+4. Color accuracy?
+5. Typography match?
+
+Prioritize fixes by visual impact.
+```
+
+## Technology Patterns
+
+### React + Tailwind
+
+```
+Convert to React with Tailwind CSS.
+
+Requirements:
+- Functional components with TypeScript
+- Tailwind utility classes
+- Extract repeated patterns
+- Semantic HTML
+- Responsive classes (sm:, md:, lg:)
+```
+
+### Vue 3
+
+```
+Convert to Vue 3 component.
+
+Requirements:
+- Composition API with <script setup>
+- Scoped styles
+- Props with TypeScript
+```
+
+### Plain HTML/CSS
+
+```
+Convert to semantic HTML and CSS.
+
+Requirements:
+- Semantic HTML5 elements
+- CSS Grid/Flexbox layout
+- CSS custom properties
+```
+
+## Quality Checklist
+
+### Visual Fidelity
+
+- [ ] Colors match exactly
+- [ ] Typography matches
+- [ ] Spacing is consistent
+- [ ] Border radius matches
+- [ ] Shadows correct
+
+### Responsiveness
+
+- [ ] Desktop layout matches
+- [ ] Tablet works
+- [ ] Mobile is usable
+- [ ] No horizontal scroll
+
+### Interactions
+
+- [ ] Hover states
+- [ ] Focus states
+- [ ] Transitions smooth
+
+### Code Quality
+
+- [ ] Properly typed
+- [ ] Sensible defaults
+- [ ] Uses tokens (no hardcoded values)
+- [ ] Accessible markup
+
+## Anti-Patterns
+
+| Anti-Pattern                                                           | Why It Fails                                                | Instead                                                                 |
+| ---------------------------------------------------------------------- | ----------------------------------------------------------- | ----------------------------------------------------------------------- |
+| Hardcoding colors/sizes instead of using design tokens                 | Creates inconsistency and makes global updates expensive    | Map values to existing tokens first; add new tokens only when truly new |
+| Building from scratch when existing components cover 80% of the design | Reintroduces solved problems and increases maintenance cost | Compose and extend existing components, then patch gaps                 |
+| Pixel-perfect matching without responsive considerations               | Breaks on different viewport sizes and device classes       | Match intent at multiple breakpoints and validate mobile/tablet/desktop |
+| Not extracting reusable components from repeated patterns              | Duplicates code and drifts visual behavior over time        | Promote repeated UI blocks into reusable components with variants       |
+
+## Storage
+
+Save implementations to `.opencode/memory/design/implementations/`
+
+## See Also
+
+- `frontend-design`
+- `visual-analysis`
+- `accessibility-audit`

package/baseline/skill/mqdh/SKILL.md

@@ -0,0 +1,171 @@
+---
+name: mqdh
+description: Meta Quest Developer Hub MCP for VR/AR development. Access Meta Horizon OS docs, ADB tools, device management. Use when building Quest apps or need Meta XR documentation.
+mcp:
+  mqdh:
+    command: "${MQDH_MCP_PATH}"
+    args: []
+version: 1.0.0
+tags: [integration, mcp]
+dependencies: []
+---
+
+# Meta Quest Developer Hub MCP
+
+## When to Use
+
+- When you need Meta Quest docs, ADB tooling, or device management via MQDH MCP.
+
+## When NOT to Use
+
+- When you are not working on Meta Quest/VR development or MQDH is unavailable.
+
+
+## Prerequisites
+
+### 1. Install MQDH
+
+Download and install Meta Quest Developer Hub v6.2.1 or later:
+
+- **macOS**: [Download MQDH for Mac](https://developers.meta.com/horizon/documentation/android-apps/meta-quest-developer-hub)
+- **Windows**: [Download MQDH for Windows](https://developers.meta.com/horizon/documentation/android-apps/meta-quest-developer-hub)
+
+### 2. Set MCP Path Environment Variable
+
+The MCP server is bundled with MQDH. Set the path to the MCP executable:
+
+**macOS:**
+
+```bash
+export MQDH_MCP_PATH="/Applications/Meta Quest Developer Hub.app/Contents/Resources/mcp-server"
+```
+
+**Windows:**
+
+```powershell
+$env:MQDH_MCP_PATH = "C:\Program Files\Meta Quest Developer Hub\resources\mcp-server.exe"
+```
+
+> **Note**: Paths may vary based on your installation. Check MQDH's AI Tools settings tab for the exact path.
+
+### 3. Alternative: Use MQDH's Built-in Setup
+
+MQDH v6.2.1+ includes an **AI Tools settings tab** with:
+
+- One-click install for **Cursor** and **VS Code**
+- Guided setup for Claude Desktop, Gemini CLI, Android Studio
+- Manual configuration export for other tools
+
+## Quick Start
+
+After setting up the environment variable and loading this skill:
+
+```
+skill_mcp(skill_name="mqdh", list_tools=true)
+```
+
+Then invoke tools:
+
+```
+skill_mcp(skill_name="mqdh", tool_name="fetch_meta_quest_doc", arguments='{"query": "hand tracking setup"}')
+```
+
+## Available Tools
+
+### fetch_meta_quest_doc
+
+Search and retrieve Meta Horizon OS documentation.
+
+| Parameter | Type   | Required | Description                |
+| --------- | ------ | -------- | -------------------------- |
+| `query`   | string | Yes      | Documentation search query |
+
+**Example:**
+
+```
+skill_mcp(skill_name="mqdh", tool_name="fetch_meta_quest_doc", arguments='{"query": "passthrough API Unity"}')
+```
+
+### get_adb_path
+
+Get the path to the bundled ADB executable.
+
+**Example:**
+
+```
+skill_mcp(skill_name="mqdh", tool_name="get_adb_path", arguments='{}')
+```
+
+### device_list
+
+List connected Quest devices.
+
+**Example:**
+
+```
+skill_mcp(skill_name="mqdh", tool_name="device_list", arguments='{}')
+```
+
+### install_apk
+
+Install an APK to a connected Quest device.
+
+| Parameter   | Type   | Required | Description      |
+| ----------- | ------ | -------- | ---------------- |
+| `apk_path`  | string | Yes      | Path to APK file |
+| `device_id` | string | No       | Target device ID |
+
+**Example:**
+
+```
+skill_mcp(skill_name="mqdh", tool_name="install_apk", arguments='{"apk_path": "/path/to/app.apk"}')
+```
+
+## Use Cases
+
+- **Documentation Lookup**: Quickly search Meta Horizon OS docs for APIs, best practices
+- **Device Management**: List devices, install APKs, manage Quest headsets
+- **Development Workflow**: Integrate ADB operations into AI-assisted development
+- **Troubleshooting**: Find solutions in Meta's documentation
+
+## Workflow Examples
+
+### 1. Look Up API Documentation
+
+```
+# Search for hand tracking documentation
+skill_mcp(skill_name="mqdh", tool_name="fetch_meta_quest_doc", arguments='{"query": "hand tracking gesture detection"}')
+
+# Search for passthrough setup
+skill_mcp(skill_name="mqdh", tool_name="fetch_meta_quest_doc", arguments='{"query": "mixed reality passthrough Unity"}')
+```
+
+### 2. Device Operations
+
+```
+# List connected devices
+skill_mcp(skill_name="mqdh", tool_name="device_list", arguments='{}')
+
+# Install a build
+skill_mcp(skill_name="mqdh", tool_name="install_apk", arguments='{"apk_path": "/builds/myapp.apk", "device_id": "1234567890"}')
+```
+
+## Transport
+
+This MCP uses **STDIO** transport to communicate with the LLM agent.
+
+## Troubleshooting
+
+**"Command not found"**: Verify `MQDH_MCP_PATH` points to the correct executable. Check MQDH's AI Tools settings for the exact path.
+
+**"MQDH not installed"**: Download MQDH v6.2.1+ from [Meta Developer Portal](https://developers.meta.com/horizon/documentation/android-apps/meta-quest-developer-hub).
+
+**"Device not found"**: Ensure your Quest is connected via USB and developer mode is enabled.
+
+**One-click setup preferred**: Use MQDH's built-in AI Tools settings tab for automatic configuration with Cursor or VS Code.
+
+## References
+
+- [MQDH MCP Documentation](https://developers.meta.com/horizon/documentation/unity/ts-mqdh-mcp/)
+- [Install MQDH](https://developers.meta.com/horizon/documentation/android-apps/meta-quest-developer-hub)
+- [Meta Horizon OS Developer Docs](https://developers.meta.com/horizon/documentation/)

package/baseline/skill/obsidian/SKILL.md

@@ -0,0 +1,192 @@
+---
+name: obsidian
+description: Use when working with Obsidian vault via MCP - read/write notes, search, tag management, and vault operations
+version: 1.0.0
+tags: [integration, documentation]
+dependencies: []
+mcp:
+  server: @mauricio.wolff/mcp-obsidian
+  args: ["{env:OBSIDIAN_VAULT_PATH}"]
+---
+
+# Obsidian Vault (MCP)
+
+## When to Use
+
+- When you need MCP-based read/write/search operations in an Obsidian vault.
+
+## When NOT to Use
+
+- When the task does not involve an Obsidian vault or MCP access.
+
+
+## Available Tools
+
+### Read Operations
+
+| Tool                  | Purpose                           | Arguments                                         |
+| --------------------- | --------------------------------- | ------------------------------------------------- |
+| `read_note`           | Read note with parsed frontmatter | `path`, `prettyPrint`                             |
+| `read_multiple_notes` | Batch read (max 10)               | `paths[]`, `includeContent`, `includeFrontmatter` |
+| `get_frontmatter`     | Extract only frontmatter          | `path`                                            |
+| `get_notes_info`      | Get metadata without content      | `paths[]`                                         |
+| `list_directory`      | List files and directories        | `path`                                            |
+
+### Write Operations
+
+| Tool                 | Purpose                               | Arguments                                |
+| -------------------- | ------------------------------------- | ---------------------------------------- |
+| `write_note`         | Write note (overwrite/append/prepend) | `path`, `content`, `frontmatter`, `mode` |
+| `update_frontmatter` | Update frontmatter only               | `path`, `frontmatter`, `merge`           |
+| `delete_note`        | Delete note (requires confirmation)   | `path`, `confirmPath`                    |
+| `move_note`          | Move/rename note                      | `oldPath`, `newPath`, `overwrite`        |
+
+### Search & Tags
+
+| Tool           | Purpose                       | Arguments                                              |
+| -------------- | ----------------------------- | ------------------------------------------------------ |
+| `search_notes` | Search by content/frontmatter | `query`, `limit`, `searchContent`, `searchFrontmatter` |
+| `manage_tags`  | Add/remove/list tags          | `path`, `operation`, `tags[]`                          |
+
+## Write Modes
+
+| Mode        | Description                           |
+| ----------- | ------------------------------------- |
+| `overwrite` | Replace entire file content (default) |
+| `append`    | Add content to end of file            |
+| `prepend`   | Add content to beginning of file      |
+
+## Usage Examples
+
+### Read Notes
+
+```typescript
+// Read a single note
+skill_mcp({
+  skill_name: "obsidian",
+  tool_name: "read_note",
+  arguments: '{"path": "projects/project-ideas.md"}',
+});
+
+// Read multiple notes
+skill_mcp({
+  skill_name: "obsidian",
+  tool_name: "read_multiple_notes",
+  arguments: '{"paths": ["note1.md", "note2.md"], "includeContent": true}',
+});
+
+// List directory
+skill_mcp({
+  skill_name: "obsidian",
+  tool_name: "list_directory",
+  arguments: '{"path": "Projects"}',
+});
+```
+
+### Write Notes
+
+```typescript
+// Create new note (overwrite)
+skill_mcp({
+  skill_name: "obsidian",
+  tool_name: "write_note",
+  arguments: `{
+    "path": "meeting-notes.md",
+    "content": "# Team Meeting\\n\\n## Agenda\\n- Project updates",
+    "frontmatter": {"title": "Team Meeting", "date": "2025-02-13", "tags": ["meetings", "team"]},
+    "mode": "overwrite"
+  }`,
+});
+
+// Append to existing note
+skill_mcp({
+  skill_name: "obsidian",
+  tool_name: "write_note",
+  arguments:
+    '{"path": "daily-log.md", "content": "\\n\\n## 3:00 PM\\n- Completed review", "mode": "append"}',
+});
+```
+
+### Search & Tags
+
+```typescript
+// Search notes
+skill_mcp({
+  skill_name: "obsidian",
+  tool_name: "search_notes",
+  arguments: '{"query": "machine learning", "limit": 5, "searchContent": true}',
+});
+
+// Add tags
+skill_mcp({
+  skill_name: "obsidian",
+  tool_name: "manage_tags",
+  arguments: '{"path": "research-notes.md", "operation": "add", "tags": ["important", "ai"]}',
+});
+
+// List tags
+skill_mcp({
+  skill_name: "obsidian",
+  tool_name: "manage_tags",
+  arguments: '{"path": "research-notes.md", "operation": "list"}',
+});
+```
+
+### Delete (Safe)
+
+```typescript
+// Delete requires confirmation (both paths must match)
+skill_mcp({
+  skill_name: "obsidian",
+  tool_name: "delete_note",
+  arguments: '{"path": "old-draft.md", "confirmPath": "old-draft.md"}',
+});
+```
+
+## Configuration
+
+### Environment Variable
+
+Set your vault path:
+
+```bash
+export OBSIDIAN_VAULT_PATH="/path/to/your/obsidian/vault"
+```
+
+Or configure in opencode.json:
+
+```json
+{
+  "mcp": {
+    "obsidian": {
+      "command": "npx",
+      "args": ["@mauricio.wolff/mcp-obsidian", "/path/to/vault"]
+    }
+  }
+}
+```
+
+## Security
+
+- Path traversal protection: prevents access outside vault
+- Auto-excludes: `.obsidian`, `.git`, `node_modules`
+- Frontmatter validation: blocks dangerous objects
+- Confirmation required for deletions
+
+## Common Use Cases
+
+| Task                 | Tool             | Example                                                                       |
+| -------------------- | ---------------- | ----------------------------------------------------------------------------- |
+| List vault files     | `list_directory` | `list_directory({ path: "" })`                                                |
+| Read specific note   | `read_note`      | `read_note({ path: "tasks/project.md" })`                                     |
+| Create/update note   | `write_note`     | `write_note({ path: "new.md", content: "...", mode: "overwrite" })`           |
+| Search notes         | `search_notes`   | `search_notes({ query: "API", limit: 10 })`                                   |
+| Add tags             | `manage_tags`    | `manage_tags({ path: "note.md", operation: "add", tags: ["urgent"] })`        |
+| Append to daily note | `write_note`     | `write_note({ path: "daily/2025-02-13.md", content: "...", mode: "append" })` |
+
+## Tips
+
+- Use `prettyPrint: true` for debugging, `false` (default) for production
+- Batch reads with `read_multiple_notes` (max 10)
+- Search supports content and frontmatter filtering
+- Frontmatter is auto-parsed on read

package/baseline/skill/obsidian/mcp.json

@@ -0,0 +1,22 @@
+{
+	"obsidian": {
+		"command": "npx",
+		"args": ["-y", "@mauricio.wolff/mcp-obsidian", "{env:OBSIDIAN_VAULT_PATH}"],
+		"env": {
+			"OBSIDIAN_VAULT_PATH": "{env:OBSIDIAN_VAULT_PATH}"
+		},
+		"includeTools": [
+			"read_note",
+			"read_multiple_notes",
+			"get_frontmatter",
+			"get_notes_info",
+			"list_directory",
+			"write_note",
+			"update_frontmatter",
+			"delete_note",
+			"move_note",
+			"search_notes",
+			"manage_tags"
+		]
+	}
+}