clikit-plugin 0.1.0

package/skill/playwright/SKILL.md

@@ -0,0 +1,37 @@
+---
+name: playwright
+description: Use for browser automation, E2E testing, form filling, screenshots, and responsive design validation.
+---
+
+# Playwright Skill
+
+You are running the **playwright** skill. Browser automation via Playwright MCP.
+
+## Capabilities
+
+| Action | Description |
+|--------|-------------|
+| Navigate pages | Load URLs, handle redirects, wait for content |
+| Fill forms | Input text, select options, upload files |
+| Take screenshots | Full page, element-specific, mobile viewports |
+| Test responsive | Switch viewports, validate breakpoints |
+| Validate UX | Check interactions, accessibility, flows |
+| Test auth flows | Login sequences, session persistence |
+
+## Usage
+
+1. Specify the URL or local dev server
+2. Define actions (navigate, click, fill, assert)
+3. Set viewport if testing responsive design
+4. Capture screenshots for verification
+
+## MCP Loading
+
+This skill loads the Playwright MCP server **only when used**. Clean browser context per session.
+
+## Best Practices
+
+- Use `await page.waitForLoadState('networkidle')` for dynamic content
+- Take before/after screenshots for visual diffs
+- Test both happy and error paths
+- Clean up sessions to prevent resource leaks

package/skill/playwriter/SKILL.md

@@ -0,0 +1,56 @@
+---
+name: playwriter
+description: Use when automating browser interactions, web scraping, or testing with existing Chrome sessions. 90% less context than traditional browser MCP.
+---
+
+# Playwriter Skill
+
+Browser automation via Chrome extension integration. Provides a single `execute` tool with full Playwright API access while using your existing browser with all extensions, sessions, and cookies intact.
+
+## Capabilities
+
+- **Session Reuse**: Works with your logged-in browser sessions
+- **Extension Support**: Full access to Chrome extensions during automation
+- **Full Playwright API**: Navigation, clicks, inputs, screenshots, waits
+- **Cookie Persistence**: No need to re-authenticate
+- **Lightweight**: Minimal context usage compared to traditional browser MCPs
+
+## When to Use
+
+- Web scraping behind logins
+- Automating repetitive browser tasks
+- Testing web applications with existing sessions
+- Taking screenshots of authenticated pages
+- Form filling and submission
+- Multi-step browser workflows
+
+## Usage Pattern
+
+```
+Use the execute tool with Playwright-style commands:
+- navigate(url)
+- click(selector)
+- fill(selector, value)
+- screenshot()
+- wait(selector)
+- evaluate(script)
+```
+
+## Example
+
+```javascript
+execute({
+  actions: [
+    { type: "navigate", url: "https://example.com/dashboard" },
+    { type: "wait", selector: ".data-table" },
+    { type: "screenshot", path: "dashboard.png" }
+  ]
+})
+```
+
+## Notes
+
+- Requires Chrome extension installation
+- Browser must be running with remote debugging enabled
+- Supports headless and headed modes
+- Maintains state between execute calls

package/skill/polar/SKILL.md

@@ -0,0 +1,39 @@
+---
+name: polar
+description: Use for Polar payment integration, subscriptions, license keys, and customer portal implementation.
+---
+
+# Polar Skill
+
+You are running the **polar** skill. Polar payment platform integration.
+
+## Capabilities
+
+| Action | Description |
+|--------|-------------|
+| Create products | Define products, pricing, billing cycles |
+| Implement checkout | Embedded checkout, custom flows |
+| Manage subscriptions | Create, update, cancel, webhook handling |
+| License keys | Generate, validate, manage keys |
+| Customer portal | Self-service billing management |
+
+## Usage
+
+1. Configure Polar credentials in environment
+2. Create or reference products in Polar dashboard
+3. Implement checkout flow with webhooks
+4. Handle subscription state in your app
+
+## Key Integration Points
+
+- Checkout: `POST /checkout/`
+- Webhooks: subscription events, payment status
+- License validation: server-side key verification
+- Customer portal: embeddable billing UI
+
+## Best Practices
+
+- Always verify webhooks using signature validation
+- Store Polar IDs, not email addresses, for user linking
+- Handle all subscription states (active, past_due, canceled)
+- Test with Polar sandbox before production

package/skill/receiving-code-review/SKILL.md

@@ -0,0 +1,47 @@
+---
+name: receiving-code-review
+description: Use when receiving code review feedback. Technical evaluation, not emotional response.
+---
+
+# Receiving Code Review Skill
+
+You are running the **receiving-code-review** skill. Respond professionally.
+
+## Mindset
+
+- Technical evaluation, not emotional
+- Never say "You're absolutely right!" without verification
+- Verify before implementing changes
+- Push back with technical reasoning when appropriate
+
+## Response Protocol
+
+1. **Read carefully** — Understand the actual concern
+2. **Verify locally** — Reproduce or confirm the issue
+3. **Categorize** — Is this a bug, style, optimization, or preference?
+4. **Respond** — Acknowledge, question, or push back with data
+
+## When to Push Back
+
+| Scenario | Response |
+|----------|----------|
+| Suggestion adds complexity without value | "This adds N lines for hypothetical future need. YAGNI applies." |
+| Change breaks existing behavior | "This would break X. Current approach handles Y correctly." |
+| Style preference disguised as bug | "Noted, but current pattern matches codebase conventions." |
+| Requested feature is "professional" polish | "This works correctly. The suggested enhancement is not in scope." |
+
+## YAGNI Check
+
+Before implementing "improvements":
+- Does this solve a real problem or hypothetical one?
+- Is the complexity justified by actual usage?
+- Would a simpler solution suffice?
+
+If answer is "hypothetical" or "no" — push back.
+
+## Red Flags
+
+- Agreeing immediately without verification
+- Implementing suggestions that increase complexity unnecessarily
+- Treating style preferences as bugs
+- Adding "professional" features that nobody asked for

package/skill/requesting-code-review/SKILL.md

@@ -0,0 +1,47 @@
+---
+name: requesting-code-review
+description: Use after completing a task. Dispatch @review subagent for quality gate.
+---
+
+# Requesting Code Review Skill
+
+You are running the **requesting-code-review** skill. Never skip review.
+
+## When to Request
+
+- After major features
+- Before merging
+- After significant refactors
+- When unsure about approach
+
+## Information to Provide
+
+| Item | Example |
+|------|---------|
+| Git SHAs | "Changed: a1b2c3d..e4f5g6h" |
+| What was implemented | "Added user authentication with JWT" |
+| Plan/requirements | "Per spec in .opencode/memory/specs/auth.md" |
+| Known issues | "Edge case X not handled yet" |
+
+## Review Workflow
+
+1. Dispatch @review subagent
+2. Wait for review results
+3. Fix Critical issues immediately
+4. Address High issues before merge
+5. Medium/Low can be follow-up tickets
+
+## Issue Severity Response
+
+| Severity | Action |
+|----------|--------|
+| Critical | Fix NOW, re-review |
+| High | Fix before merge |
+| Medium | Create ticket, fix soon |
+| Low | Document, fix later |
+
+## Red Flags
+
+- Skipping review "because it's small"
+- Merging without addressing Critical issues
+- Not providing context for reviewer

package/skill/resend/SKILL.md

@@ -0,0 +1,85 @@
+---
+name: resend
+description: Use when sending transactional emails, receiving inbound emails, creating email templates with React Email, or handling email webhooks.
+---
+
+# Resend Skill
+
+Comprehensive Resend email platform integration for transactional emails, inbound email handling, template management with React Email, and webhook processing.
+
+## Capabilities
+
+- **Send Emails**: Transactional and bulk email sending
+- **Inbound Email**: Receive and process incoming emails
+- **React Email Templates**: Create emails with React components
+- **Webhook Handling**: Process email events (delivered, opened, bounced)
+- **Domain Management**: Configure sending domains and DNS
+- **Analytics**: Track email delivery and engagement metrics
+
+## When to Use
+
+- Sending transactional emails (password resets, notifications)
+- Building email templates with React
+- Receiving and processing inbound emails
+- Setting up email webhooks
+- Managing sending domains
+- Implementing email workflows
+
+## Key Tools
+
+- `send_email`: Send single or batch emails
+- `create_template`: Create React Email templates
+- `get_inbound`: Retrieve inbound emails
+- `list_domains`: Manage sending domains
+- `get_events`: Query email events
+- `create_webhook`: Set up event webhooks
+
+## Example Usage
+
+```
+// Send email
+send_email({
+  to: "user@example.com",
+  subject: "Welcome!",
+  html: "<h1>Welcome aboard!</h1>",
+  from: "noreply@myapp.com"
+})
+
+// React Email template
+create_template({
+  name: "password-reset",
+  component: "./emails/PasswordReset.tsx"
+})
+
+// Handle inbound
+get_inbound({
+  limit: 10,
+  status: "unread"
+})
+```
+
+## React Email Integration
+
+```tsx
+// emails/Welcome.tsx
+import { Html, Body, Container, Text } from '@react-email/components';
+
+export default function Welcome({ name }) {
+  return (
+    <Html>
+      <Body>
+        <Container>
+          <Text>Welcome, {name}!</Text>
+        </Container>
+      </Body>
+    </Html>
+  );
+}
+```
+
+## Notes
+
+- Requires Resend API key
+- Domain verification needed for sending
+- Supports attachments up to 40MB
+- Rate limits apply based on plan

package/skill/ritual-workflow/SKILL.md

@@ -0,0 +1,101 @@
+---
+name: ritual-workflow
+description: Use when starting any task. Enforces DISCOVER → PLAN → IMPLEMENT → VERIFY → COMPLETE workflow with hard gates.
+---
+
+# Ritual Workflow Skill
+
+You are running the **ritual-workflow** skill. Every task follows a strict phase structure.
+
+## Phases (in order)
+
+```
+DISCOVER → PLAN → IMPLEMENT → VERIFY → COMPLETE
+```
+
+### Phase 1: DISCOVER
+- Understand the problem
+- Gather requirements
+- Identify stakeholders and constraints
+- Define success criteria
+- **Gate**: Can articulate the problem clearly
+
+### Phase 2: PLAN
+- Design the solution
+- Break into tasks
+- Identify dependencies
+- Estimate effort
+- **Gate**: Plan approved (user confirms)
+
+### Phase 3: IMPLEMENT
+- Write code
+- Follow plan
+- Create tests
+- **Gate**: All planned tasks done
+
+### Phase 4: VERIFY
+- Run tests
+- Type check
+- Lint
+- Build
+- **Gate**: All checks pass
+
+### Phase 5: COMPLETE
+- Document changes
+- Create PR
+- Clean up
+- **Gate**: Merged or deployed
+
+## Hard Gates
+
+| Current Phase | Must Complete Before Advancing |
+|---------------|-------------------------------|
+| DISCOVER | Problem statement written |
+| PLAN | User approves plan |
+| IMPLEMENT | All tasks checked off |
+| VERIFY | Tests pass, build succeeds |
+| COMPLETE | PR merged |
+
+## Ritual State
+
+State is tracked in `.opencode/memory/ritual-state.json`:
+
+```json
+{
+  "taskId": "bead-123",
+  "phases": [
+    { "name": "discover", "status": "done" },
+    { "name": "plan", "status": "in_progress" },
+    ...
+  ],
+  "currentPhase": 1
+}
+```
+
+## Commands
+
+| Command | Phase | Action |
+|---------|-------|--------|
+| `/create` | DISCOVER | Initialize ritual, gather requirements |
+| `/plan` | PLAN | Create implementation plan |
+| `/start` | IMPLEMENT | Begin implementation |
+| `/verify` | VERIFY | Run checks |
+| `/ship` | COMPLETE | Finalize and deploy |
+
+## Enforcement
+
+- Cannot skip phases
+- Cannot implement without approved plan
+- Cannot complete without passing verify
+- Each phase requires explicit completion
+
+## Status Check
+
+Run `checkRitualProgress()` to see current phase and blockers.
+
+## Red Flags
+
+- Skipping to IMPLEMENT without PLAN
+- Marking COMPLETE with failing tests
+- Moving forward without user approval
+- Ignoring phase gates

package/skill/root-cause-tracing/SKILL.md

@@ -0,0 +1,73 @@
+---
+name: root-cause-tracing
+description: Trace bugs backward through call chain to original trigger. Never fix where error appears.
+---
+
+# Root Cause Tracing Skill
+
+You are running the **root-cause-tracing** skill. Fix the origin, not the symptom.
+
+## Core Principle
+
+The error appears at point A. The cause is at point B. Always trace backward to B.
+
+## Tracing Process
+
+### Step 1: Locate the Error
+- Find where the error manifests
+- DO NOT fix here yet
+- This is the symptom location
+
+### Step 2: Trace the Call Chain
+- Who called this function?
+- Who called that function?
+- Keep going until you find the trigger
+
+### Step 3: Find the Root Cause
+- The first place where incorrect data/state originated
+- The decision point that led to wrong path
+- The missing validation that allowed bad input
+
+### Step 4: Fix at Origin
+- Apply fix at the root cause location
+- NOT where the error appeared
+- Verify symptom disappears
+
+## Instrumentation
+
+```javascript
+// At each layer, add:
+console.error('[TRACE] Function:', functionName);
+console.error('[TRACE] Args:', JSON.stringify(args, null, 2));
+console.error('[TRACE] Stack:', new Error().stack);
+```
+
+## Bisection for Test Polluters
+
+When tests fail in batch but pass individually:
+
+1. Run first half of tests → passing?
+2. If yes: bug in second half
+3. If no: bug in first half
+4. Repeat until isolated to single test
+5. That test is polluting shared state
+
+## Red Flags
+
+- Fixing where error is thrown (not where caused)
+- "Let me add a null check here" (defensive, not corrective)
+- Not tracing the full call chain
+- Assuming you know the cause without evidence
+
+## Example
+
+```
+Error: Cannot read property 'length' of undefined
+  at processItems (line 42)      ← DO NOT FIX HERE
+  at handleRequest (line 28)
+  at parseInput (line 15)        ← FIX HERE: null should be []
+```
+
+## Rule
+
+**Never fix at the symptom. Always trace to the root.**

package/skill/session-management/SKILL.md

@@ -0,0 +1,53 @@
+---
+name: session-management
+description: Use for managing context growth, task switching, and session continuity in long-running work.
+---
+
+# Session Management Skill
+
+You are running the **session-management** skill. Context and continuity management.
+
+## Context Thresholds
+
+| State | Context % | Action |
+|-------|-----------|--------|
+| Green | < 50% | Normal operation |
+| Yellow | 50-75% | Start summarizing, offload to memory |
+| Orange | 75-90% | Aggressive context pruning, handoff prep |
+| Red | > 90% | Initiate session handoff |
+
+## Session Tools
+
+| Tool | Purpose |
+|------|---------|
+| Memory artifacts | Save state to `.opencode/memory/` |
+| Handoff docs | Session state for next agent |
+| Beads sync | Persist tasks to `.beads/` |
+| Git commits | Checkpoint progress |
+
+## Workflow Patterns
+
+### Starting a Session
+1. Check Beads for in-progress tasks
+2. Read handoff if continuing previous session
+3. Claim ready tasks
+4. Begin work
+
+### During Session
+1. Monitor context usage
+2. Write specs/plans to memory as created
+3. Commit incremental progress
+4. Sync Beads regularly
+
+### Ending a Session
+1. Complete or checkpoint current task
+2. Write handoff document
+3. Sync all state to git/Beads
+4. Release file reservations
+
+## Best Practices
+
+- Check context percentage periodically
+- Write to memory before hitting thresholds
+- Use handoff documents for continuity
+- Keep session state in version control

package/skill/sharing-skills/SKILL.md

@@ -0,0 +1,50 @@
+---
+name: sharing-skills
+description: Use when contributing skills to the community. One skill per PR.
+---
+
+# Sharing Skills Skill
+
+You are running the **sharing-skills** skill. Contribute effectively.
+
+## When to Share
+
+- Broadly useful across projects
+- Solves common workflow problems
+- Encapsulates best practices
+- Not project-specific
+
+## Keep Personal
+
+- Project-specific configurations
+- Team-specific conventions
+- Environment-dependent logic
+- One-off automations
+
+## Contribution Workflow
+
+1. **Branch** — Create feature branch from main
+2. **Edit/Create** — Add or modify skill file
+3. **Commit** — Clear commit message describing skill
+4. **Push** — Push to your fork
+5. **PR** — Open pull request with description
+
+## PR Guidelines
+
+- One skill per PR
+- Include rationale in PR description
+- Reference any related issues
+- Be responsive to feedback
+
+## Skill File Structure
+
+```
+skill-name/
+  SKILL.md
+```
+
+## Red Flags
+
+- Sharing project-specific skills as general
+- Bundling multiple skills in one PR
+- Not documenting when/why to use the skill