clikit-plugin 0.1.0

package/skill/dispatching-parallel-agents/SKILL.md

@@ -0,0 +1,94 @@
+---
+name: dispatching-parallel-agents
+description: Use when facing 3+ independent failures. Dispatches concurrent subagent workflows, one agent per problem domain.
+---
+
+# Dispatching Parallel Agents Skill
+
+You are running the **dispatching-parallel-agents** skill. Solve multiple independent problems concurrently.
+
+## When to Use
+
+**Use when:**
+- 3+ independent failures detected
+- Problems are in different domains/files
+- Each issue can be solved independently
+- Results can be merged after completion
+
+**Do NOT use when:**
+- Failures are related/dependent
+- Agents would edit the same files
+- Order of fixes matters
+- One fix might break another
+
+## Dispatch Protocol
+
+### 1. Problem Analysis
+```
+For each failure:
+  - Identify problem domain
+  - Determine affected files
+  - Check for file overlap with other problems
+  - Estimate complexity
+```
+
+### 2. Agent Assignment
+```
+Map problems to domains:
+  - Frontend issues → @build with fe context
+  - Backend issues → @build with be context
+  - Test issues → @build with qa context
+  - Config issues → @build with devops context
+```
+
+### 3. Parallel Execution
+- Launch all agents simultaneously
+- Each agent works in isolation
+- No cross-agent communication during work
+- Track progress independently
+
+### 4. Result Merging
+```
+After all agents complete:
+  1. Collect all changes
+  2. Verify no conflicts
+  3. Run integration tests
+  4. Merge results
+```
+
+## Example Scenario
+
+```
+Failures detected:
+1. Login button not rendering (frontend) → Agent A
+2. API timeout on /users (backend) → Agent B
+3. E2E test flaky (testing) → Agent C
+
+Dispatch 3 agents in parallel.
+Each fixes their domain.
+Merge after completion.
+```
+
+## Conflict Detection
+
+Before dispatching, verify:
+- No file overlap between assignments
+- No shared state modifications
+- No ordering dependencies
+
+## Rules
+
+| Rule | Why |
+|------|-----|
+| Minimum 3 problems | Overhead worth it at scale |
+| Independent only | Avoid conflicts |
+| Different files | Safe parallel edits |
+| Merge verification | Catch integration issues |
+
+## Failure Handling
+
+If any agent fails:
+1. Report failure immediately
+2. Other agents continue
+3. Address failed agent's issue separately
+4. Do not block successful completions

package/skill/executing-plans/SKILL.md

@@ -0,0 +1,54 @@
+---
+name: executing-plans
+description: Use when a plan exists and you need to execute tasks with checkpoints and review.
+---
+
+# Executing Plans Skill
+
+You are running the **executing-plans** skill. Execute implementation plans systematically with checkpoints.
+
+## Batch Execution
+
+Default: **3 tasks per batch**
+
+After each batch:
+1. Run verification commands
+2. Summarize changes made
+3. Ask for confirmation to continue
+
+## Execution Flow
+
+```
+Read plan → Select next batch → Execute → Verify → Checkpoint → Continue/Adjust
+```
+
+## Checkpoint Questions
+
+After each batch, ask:
+- "Continuing with next 3 tasks. Proceed? (yes/skip/stop/adjust)"
+- If "skip": Skip current batch, move to next
+- If "stop": Halt execution, summarize progress
+- If "adjust": Modify batch size or plan
+
+## Per-Task Execution
+
+1. **Read** the task completely
+2. **Verify** the file exists (or will be created)
+3. **Apply** the exact change specified
+4. **Run** the verification command
+5. **Confirm** expected result
+
+## Error Handling
+
+| Error Type | Action |
+|------------|--------|
+| File not found | Create it or ask for clarification |
+| Test fails | Debug, fix, re-run before continuing |
+| Unexpected state | Stop, report, ask for guidance |
+
+## Red Flags
+
+- Skipping verification
+- Making changes not in the plan
+- Continuing after failure without fixing
+- Modifying batch size without asking

package/skill/figma/SKILL.md

@@ -0,0 +1,34 @@
+---
+name: figma
+description: Use when you need to access Figma design data, layouts, or assets for implementation.
+---
+
+# Figma Skill
+
+You are running the **figma** skill. Access Figma design data via Framelink MCP.
+
+## Capabilities
+
+| Action | Description |
+|--------|-------------|
+| Fetch layout | Get component hierarchy, spacing, dimensions |
+| Get styles | Colors, typography, shadows, borders |
+| Get components | Extract reusable component definitions |
+| Download assets | SVG/PNG export for icons, images |
+
+## Usage
+
+1. Provide Figma file URL or frame ID
+2. Specify what you need (layout, styles, assets)
+3. Skill fetches via Framelink MCP (on-demand)
+4. Convert to code matching your tech stack
+
+## MCP Loading
+
+This skill loads the Framelink MCP server **only when used**. No persistent connection overhead.
+
+## Best Practices
+
+- Request specific frames, not entire files
+- Export assets at appropriate resolutions
+- Match design tokens to your CSS variables

package/skill/finishing-a-development-branch/SKILL.md

@@ -0,0 +1,127 @@
+---
+name: finishing-a-development-branch
+description: Use when completing development work on a branch. Verifies tests, presents options, executes choice with cleanup.
+---
+
+# Finishing a Development Branch Skill
+
+You are running the **finishing-a-development-branch** skill. Safe branch completion with user control.
+
+## Prerequisites
+
+- Development work complete
+- In a worktree (recommended)
+- Branch has commits
+
+## Workflow
+
+### 1. Verify Tests
+```bash
+# Run all tests
+npm test
+
+# If tests fail:
+# - STOP
+# - Report failures
+# - Do NOT proceed to options
+```
+
+**Never merge with failing tests.**
+
+### 2. Present Options
+
+```
+Branch [branch-name] ready. Choose:
+
+1. MERGE    - Merge to main and clean up
+2. PR       - Create pull request (keep branch)
+3. KEEP     - Keep branch, continue later
+4. DISCARD  - Delete branch and all changes
+
+What would you like to do?
+```
+
+### 3. Execute Choice
+
+#### Option 1: MERGE
+```bash
+# Switch to main
+git checkout main
+git pull origin main
+
+# Merge branch
+git merge <branch-name>
+
+# Push to remote
+git push origin main
+
+# Clean up
+git branch -d <branch-name>
+git worktree remove <worktree-path>  # if applicable
+```
+
+#### Option 2: PR
+```bash
+# Push branch
+git push origin <branch-name>
+
+# Create PR
+gh pr create --title "[title]" --body "[body]"
+
+# Keep worktree for iteration
+```
+
+#### Option 3: KEEP
+```bash
+# Just ensure pushed
+git push origin <branch-name>
+
+# Leave worktree intact
+# User can return later
+```
+
+#### Option 4: DISCARD
+```
+⚠️  WARNING: This will DELETE all changes on this branch.
+
+Type "discard" to confirm:
+```
+
+```bash
+# After typing "discard"
+git checkout main
+git branch -D <branch-name>
+git worktree remove <worktree-path>
+```
+
+## Safety Rules
+
+| Rule | Enforcement |
+|------|-------------|
+| Tests must pass | Block on failure |
+| DISCARD requires typed confirmation | Prevent accidents |
+| Never force merge | User controls flow |
+| Always clean up worktrees | After merge/discard |
+
+## Decision Matrix
+
+| Situation | Recommended |
+|-----------|-------------|
+| Feature complete, tested | MERGE |
+| Needs review | PR |
+| Work in progress | KEEP |
+| Wrong direction | DISCARD |
+
+## Post-Completion
+
+After any option:
+1. Report result
+2. Show current branch status
+3. Suggest next steps if applicable
+
+## Anti-Patterns
+
+- Merging without test verification
+- Discarding without confirmation
+- Leaving stale worktrees
+- Force pushing to main

package/skill/frontend-aesthetics/SKILL.md

@@ -0,0 +1,63 @@
+---
+name: frontend-aesthetics
+description: Use when building UI components or pages. Prevents AI slop aesthetic with distinctive design direction.
+---
+
+# Frontend Aesthetics Skill
+
+You are running the **frontend-aesthetics** skill. No generic AI designs. No purple gradients.
+
+## Core Principle
+
+Pick ONE aesthetic direction. Commit fully. No hybrid compromises.
+
+## Aesthetic Directions
+
+| Direction | Typography | Colors | Motion |
+|-----------|------------|--------|--------|
+| Neo-Brutalist | Bold sans-serif, high contrast | Black/white + 1 accent | Sharp, instant |
+| Glass Morphism | Light, geometric | Translucent overlays | Smooth blur transitions |
+| Swiss Design | Grid-aligned, minimal | Primary + neutrals | Subtle, functional |
+| Retro-Future | Geometric, display | Warm gradients | Smooth, nostalgic |
+| Dark Industrial | Monospace, condensed | Dark + neon accent | Glitch, scan effects |
+| Organic Minimal | Rounded, friendly | Earth tones | Gentle, springy |
+
+## Typography Rules
+
+- NEVER: Inter, Roboto, Arial, Helvetica, system-ui
+- PICK: Space Grotesk, JetBrains Mono, Instrument Sans, Clash Display, Satoshi, DM Sans, Outfit, Plus Jakarta Sans
+- Pair: 1 display font (headlines) + 1 UI font (body)
+- Scale: Use typographic scale (1.25 or 1.333 ratio), not arbitrary sizes
+
+## Color Rules
+
+- Maximum 3 colors: Primary, Secondary, Accent
+- No purple gradients (the hallmark of AI-generated design)
+- Define semantic colors: success, warning, error, info
+- Use CSS variables - no hardcoded hex values in components
+
+## Motion Rules
+
+- Motion must be meaningful: state change, attention, feedback
+- Duration: 150-300ms for micro, 300-500ms for transitions
+- Easing: Use custom easings, not just ease-in-out
+- Reduce motion: Respect prefers-reduced-motion
+
+## Checklist
+
+- [ ] One aesthetic direction chosen and documented
+- [ ] Typography: Display + UI font selected (not Inter/Roboto)
+- [ ] Color palette: Max 3 colors + semantics defined
+- [ ] Motion tokens: Duration, easing, reduction defined
+- [ ] No purple gradients anywhere
+- [ ] No centered hero with 3-column cards layout
+
+## Red Flags
+
+- Make it look modern without direction
+- Inter or Roboto in font stack
+- Purple-to-pink gradients
+- Centered hero + 3-column feature cards
+- Generic placeholder images (stock photos)
+- Inconsistent spacing (use 4px or 8px grid)
+- Multiple competing aesthetic styles

package/skill/gemini-large-context/SKILL.md

@@ -0,0 +1,80 @@
+---
+name: gemini-large-context
+description: Use when context exceeds session limits or analyzing 100KB+ files. Leverages Gemini CLI's 1M token window.
+---
+
+# Gemini Large Context Skill
+
+You are running the **gemini-large-context** skill. When you hit limits, scale up.
+
+## When to Use
+
+| Scenario | Why Gemini |
+|----------|------------|
+| Single file >100KB | Won't fit in standard context |
+| Project-wide pattern search | Need full codebase visibility |
+| Multi-file diff analysis | Compare across dozens of files |
+| Legacy code archaeology | Understand decade-old systems |
+| Full test suite review | See all tests at once |
+
+## Process
+
+### 1. Prepare Input
+
+```bash
+# Single large file
+gemini -p "Analyze this file for [task]: $(cat large_file.ts)"
+
+# Multiple files
+cat file1.ts file2.ts file3.ts | gemini -p "Compare these files:"
+
+# Full directory
+find src -name "*.ts" -exec cat {} \; | gemini -p "Find patterns in codebase:"
+```
+
+### 2. Structure Your Prompt
+
+```
+Context: [what you're analyzing]
+Task: [specific question or goal]
+Constraints: [limitations, requirements]
+Output: [expected format]
+```
+
+### 3. Handle Output
+
+- Gemini returns full analysis
+- Extract actionable items
+- If incomplete, prompt for continuation
+- Save important findings to memory
+
+## Use Cases
+
+### Large File Analysis
+```
+gemini -p "Map all exports and their dependencies in this file: $(cat huge_api.ts)"
+```
+
+### Pattern Detection
+```
+cat src/**/*.ts | gemini -p "Find all authentication patterns and security issues:"
+```
+
+### Multi-file Comparison
+```
+cat v1/api.ts v2/api.ts | gemini -p "Breaking changes between v1 and v2:"
+```
+
+## Checklist
+
+- [ ] Confirmed file/directory size justifies large context
+- [ ] Prompt includes specific task (not "analyze this")
+- [ ] Output format specified
+- [ ] Results saved to `.opencode/memory/` for reference
+
+## Red Flags
+
+- Using for small files (wastes resources)
+- Vague prompts ("what do you think?")
+- Not saving results (lose context on next session)
+- Ignoring token limits still exists (1M isn't infinite)

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

@@ -0,0 +1,98 @@
+---
+name: mockup-to-code
+description: Use when converting UI mockups, screenshots, or Figma/Sketch designs into production-ready code.
+---
+
+# Mockup to Code Skill
+
+You are running the **mockup-to-code** skill. Pixels to production.
+
+## Input Types
+
+| Source | Extraction Method |
+|--------|-------------------|
+| Screenshot | Visual analysis via Gemini |
+| Figma export | Design tokens + component mapping |
+| Sketch file | Layer structure + styles |
+| Design URL | Direct inspection or screenshot |
+
+## Process
+
+### 1. Extract Design Tokens
+
+```bash
+gemini -p "Extract design tokens from this mockup as JSON: $(cat mockup.png)"
+```
+
+Expected output structure:
+```json
+{
+  "colors": { "primary": "#...", "secondary": "#..." },
+  "typography": { "heading": "...", "body": "..." },
+  "spacing": { "base": 8, "scale": [8, 16, 24, 32] },
+  "shadows": ["0 2px 4px rgba(...)", ...],
+  "radii": [4, 8, 16]
+}
+```
+
+### 2. Identify Components
+
+```
+Component: [Name]
+- Props: [list]
+- Variants: [list]
+- States: [default, hover, active, disabled]
+- Dependencies: [child components]
+```
+
+### 3. Map to Tech Stack
+
+| Design Element | Implementation |
+|----------------|----------------|
+| Typography | Tailwind classes / CSS variables |
+| Colors | CSS custom properties |
+| Spacing | Tailwind spacing scale |
+| Components | React/Vue/Svelte components |
+| Icons | Lucide / Heroicons / custom SVG |
+
+### 4. Build Incrementally
+
+1. Structure: Semantic HTML
+2. Layout: Flexbox/Grid
+3. Styling: Tokens → classes
+4. Interaction: States and events
+5. Responsive: Breakpoint adjustments
+6. Polish: Animations and details
+
+## Component Library Handling
+
+### Existing Library
+- Check for matching components first
+- Extend or compose before creating new
+- Document any custom overrides
+
+### New Components
+- Follow existing patterns
+- Use established tokens
+- Ensure accessibility built-in
+
+## Checklist
+
+- [ ] Design tokens extracted and defined
+- [ ] Components identified and documented
+- [ ] Semantic HTML structure
+- [ ] Responsive breakpoints handled
+- [ ] All interactive states implemented
+- [ ] Accessibility attributes added
+- [ ] Matches mockup pixel-perfectly
+- [ ] Code follows project conventions
+
+## Red Flags
+
+- Skipping semantic HTML for div soup
+- Hardcoded values instead of tokens
+- Ignoring component library
+- Missing interactive states
+- No accessibility attributes
+- Inline styles over classes
+- Breaking responsive behavior

package/skill/mqdh/SKILL.md

@@ -0,0 +1,54 @@
+---
+name: mqdh
+description: Use when building Meta Quest VR/AR applications, needing Meta Horizon OS documentation, or managing Quest devices via ADB.
+---
+
+# Meta Quest Developer Hub (MQDH) Skill
+
+MCP integration for Meta Quest Developer Hub providing VR/AR development tools, documentation access, and device management capabilities.
+
+## Capabilities
+
+- **Documentation Access**: Query Meta Horizon OS and XR development docs
+- **ADB Tools**: Device debugging, app installation, log streaming
+- **Device Management**: Connect, configure, and manage Quest devices
+- **Build Tools**: APK management, app deployment workflows
+- **Debugging**: Performance profiling, log analysis
+- **Project Setup**: Quest project scaffolding and configuration
+
+## When to Use
+
+- Building applications for Meta Quest headsets
+- Looking up Meta XR SDK documentation
+- Debugging Quest applications on device
+- Managing Quest device settings and configurations
+- Deploying builds to Quest devices
+- Setting up XR development environments
+
+## Key Tools
+
+- `query_docs`: Search Meta Horizon OS documentation
+- `device_list`: List connected Quest devices
+- `device_install`: Install APK to device
+- `device_logs`: Stream device logs
+- `adb_command`: Execute ADB commands
+- `project_configure`: Set up Quest project settings
+
+## Example Usage
+
+```
+// Query documentation
+query_docs({ query: "hand tracking setup Quest 3" })
+
+// Install app
+device_install({ apk_path: "./build/app.apk", device_id: "quest-3" })
+
+// Stream logs
+device_logs({ device_id: "quest-3", filter: "Unity" })
+```
+
+## Prerequisites
+
+- Meta Quest Developer Hub installed
+- Developer mode enabled on Quest device
+- USB connection or ADB over Wi-Fi configured

package/skill/notebooklm/SKILL.md

@@ -0,0 +1,71 @@
+---
+name: notebooklm
+description: Use when querying Google NotebookLM notebooks for source-grounded answers with citations, or managing notebook libraries.
+---
+
+# NotebookLM Skill
+
+Query Google NotebookLM notebooks for source-grounded, citation-backed answers. Provides browser automation for notebook access, library management, and persistent authentication.
+
+## Capabilities
+
+- **Query Notebooks**: Ask questions against uploaded sources
+- **Citation-Backed Answers**: Responses reference specific source documents
+- **Notebook Management**: Create, update, delete notebooks
+- **Source Management**: Add/remove sources from notebooks
+- **Persistent Auth**: Maintain Google session across sessions
+- **Library Access**: Browse and search notebook collections
+
+## When to Use
+
+- Research with document-grounded answers
+- Querying knowledge bases with citations
+- Extracting insights from uploaded documents
+- Building research workflows
+- Creating Q&A systems from documents
+- Getting answers with verifiable sources
+
+## Key Tools
+
+- `query_notebook`: Ask questions to a specific notebook
+- `list_notebooks`: Get all available notebooks
+- `create_notebook`: Create new notebook with sources
+- `add_sources`: Add documents/URLs to notebook
+- `get_answer_sources`: Retrieve citations for an answer
+
+## Example Usage
+
+```
+// Query notebook
+query_notebook({
+  notebook_id: "research-papers",
+  question: "What are the key findings about LLM hallucinations?"
+})
+
+// Returns answer with citations:
+// "According to Source 1, LLM hallucinations occur when..."
+// Citations: [Source 1, p.3], [Source 2, Section 4.2]
+
+// List notebooks
+list_notebooks()
+
+// Create notebook
+create_notebook({
+  name: "Project Documentation",
+  sources: ["https://docs.example.com", "./local-docs/"]
+})
+```
+
+## Authentication
+
+- Browser-based OAuth flow
+- Session persistence in secure storage
+- Automatic token refresh
+- Supports multiple Google accounts
+
+## Notes
+
+- Requires Google account access
+- Browser automation handles auth
+- Source limits based on NotebookLM tiers
+- Answers grounded in uploaded sources only