@minhduydev/mdpi 0.3.0

package/dist/template/.pi/skills/chrome-devtools/SKILL.md

@@ -0,0 +1,129 @@
+---
+name: chrome-devtools
+description: Gives agents the ability to inspect, screenshot, and verify UI behavior using Chrome DevTools Protocol. Use for agent-legible UI verification — bug reproduction, visual validation, DOM inspection.
+---
+
+# Chrome DevTools — Agent-Legible UI Verification
+
+Enables agents to verify UI behavior programmatically — the same way OpenAI's Harness team wires CDP into Codex for DOM snapshots, screenshots, and navigation.
+
+## Prerequisites
+
+- Playwright must be available: `npx playwright install chromium`
+- The app must be bootable locally (dev server, vite, next dev, etc.)
+
+## Usage
+
+### 1. Launch App (per-task worktree or local dev)
+
+```bash
+# If using worktrees:
+git worktree add ../review-{task-id} {branch}
+cd ../review-{task-id}
+npm install
+npm run dev &
+APP_PID=$!
+
+# Or for local dev:
+npm run dev &
+APP_PID=$!
+```
+
+### 2. Take DOM Snapshot
+
+```bash
+npx playwright eval --browser chromium "document.documentElement.outerHTML"
+```
+
+### 3. Capture Screenshot
+
+```bash
+npx playwright screenshot --browser chromium http://localhost:5173 screenshot.png
+```
+
+### 4. Verify UI State
+
+Use playwright script to check specific conditions:
+
+```bash
+cat > verify-state.mjs << 'SCRIPT'
+import { chromium } from 'playwright';
+const browser = await chromium.launch();
+const page = await browser.newPage();
+await page.goto('http://localhost:5173');
+
+// Check element exists
+const exists = await page.locator('[data-testid="submit-btn"]').count() > 0;
+
+// Check text content
+const text = await page.locator('h1').textContent();
+console.log(JSON.stringify({ heading: text, buttonExists: exists }));
+
+await browser.close();
+SCRIPT
+node verify-state.mjs
+```
+
+### 5. Reproduce Bug
+
+Given a bug description, navigate to the page, interact, and capture the erroneous state:
+
+```bash
+npx playwright eval --browser chromium "..." 2>&1 | head -100
+```
+
+## When to Use
+
+- After implementing UI changes, verify they render correctly
+- Before shipping, verify critical user journeys
+- When debugging UI bugs, reproduce and inspect DOM state
+- Validating responsive behavior at different viewport sizes
+
+## When NOT to Use
+
+- For API-level testing (use curl or direct tests instead)
+- For unit tests (use the testing framework directly)
+- When the app isn't bootable locally
+
+## Verification Contract
+
+After any UI change, the agent should verify:
+
+1. App boots without errors (no uncaught exceptions in console)
+2. Key elements render with expected content
+3. Interactive elements respond to user input
+4. Error states display correctly when data/async fails
+
+## Remediation
+
+If UI verification fails:
+1. Check the browser console for errors (see `console.error` calls)
+2. Check if the app needs specific environment variables
+3. Verify the correct port is being used
+4. Check for JS errors from the page itself
+
+## Common Rationalizations
+
+| Rationalization | Reality |
+|---|---|
+| "The console looks clean" | Clean console ≠ correct behavior. Inspect DOM state, network requests, and paint. |
+| "I'll just use the browser manually" | Programmatic DevTools access provides reproducible evidence. Manual testing is not enough. |
+| "Performance looks fine on my machine" | DevTools throttling exists for a reason. Test on target hardware profiles. |
+
+## Red Flags
+
+- Console errors ignored as "probably fine"
+- Network requests returning 4xx/5xx not investigated
+- Performance traces not captured before optimization
+- Memory snapshots not taken when investigating leaks
+- DevTools used only for console, ignoring Network, Performance, and Application tabs
+
+## Verification
+
+After using Chrome DevTools:
+
+- [ ] Console errors are resolved or documented with justification
+- [ ] Network tab shows no failed requests (4xx/5xx investigated)
+- [ ] Performance trace captured for user-facing flows
+- [ ] Memory snapshot analyzed if investigating leaks
+- [ ] Findings are documented with screenshots and action items

package/dist/template/.pi/skills/ci-cd-and-automation/SKILL.md

@@ -0,0 +1,199 @@
+---
+name: ci-cd-and-automation
+description: Use when setting up CI/CD pipelines, GitHub Actions workflows, automated testing in CI, or deployment automation — covers pipeline design, caching, secrets management, and release workflows
+---
+
+# CI/CD & Automation
+
+> **Replaces** manual deployment checklists and ad-hoc scripts with repeatable, auditable automation pipelines
+
+## When to Use
+
+- Setting up or modifying CI/CD pipelines (GitHub Actions, GitLab CI, etc.)
+- Adding automated testing, linting, or type-checking to a repository
+- Configuring deployment automation or release workflows
+- Optimizing CI performance (caching, parallelism, conditional runs)
+
+## When NOT to Use
+
+- Local development scripts (use Makefile or package.json scripts)
+- One-time migration scripts that don't repeat
+- Infrastructure provisioning (use infrastructure-as-code tools directly)
+
+## Overview
+
+CI/CD pipelines are the quality gates between code and production. A well-designed pipeline catches problems early, runs fast, and deploys safely.
+
+**Core principle:** Every step that a human does manually before merging or deploying should be automated in the pipeline. If it can be automated, it must be.
+
+## Pipeline Design
+
+### Verification Pipeline (PR/Push)
+
+```yaml
+# Ordered by speed: fastest gates first
+steps:
+  1. Lint          # seconds — catches formatting/style issues
+  2. Typecheck     # seconds — catches type errors
+  3. Unit tests    # seconds-minutes — catches logic bugs
+  4. Build         # minutes — catches compilation issues
+  5. Integration   # minutes — catches integration bugs
+  6. E2E tests     # minutes — catches user-facing bugs (optional per-PR)
+```
+
+**Fail-fast rule:** Run cheapest checks first. Don't waste 10 minutes on E2E tests if linting fails in 5 seconds.
+
+### Deployment Pipeline (Main/Release)
+
+```
+1. All verification steps pass
+2. Build production artifacts
+3. Deploy to staging
+4. Run smoke tests against staging
+5. Deploy to production (manual gate or auto)
+6. Run smoke tests against production
+7. Monitor error rates for rollback window
+```
+
+## GitHub Actions Patterns
+
+### Basic PR Verification
+
+```yaml
+name: verify
+on: [pull_request]
+jobs:
+  check:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version-file: ".node-version"
+          cache: "pnpm"
+      - run: pnpm install --frozen-lockfile
+      - run: pnpm lint
+      - run: pnpm typecheck
+      - run: pnpm test
+      - run: pnpm build
+```
+
+### Caching Strategy
+
+| What         | Cache Key         | Restore Key | Impact       |
+| ------------ | ----------------- | ----------- | ------------ |
+| Dependencies | `lockfile hash`   | `os-deps-`  | 30-60s saved |
+| Build output | `source hash`     | `os-build-` | 1-5min saved |
+| Test cache   | `test files hash` | `os-test-`  | Variable     |
+
+```yaml
+- uses: actions/cache@v4
+  with:
+    path: ~/.pnpm-store
+    key: ${{ runner.os }}-pnpm-${{ hashFiles('**/pnpm-lock.yaml') }}
+    restore-keys: ${{ runner.os }}-pnpm-
+```
+
+### Parallel Jobs
+
+```yaml
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps: [checkout, setup, "pnpm lint"]
+
+  typecheck:
+    runs-on: ubuntu-latest
+    steps: [checkout, setup, "pnpm typecheck"]
+
+  test:
+    runs-on: ubuntu-latest
+    steps: [checkout, setup, "pnpm test"]
+
+  build:
+    needs: [lint, typecheck, test] # Only build after all checks pass
+    runs-on: ubuntu-latest
+    steps: [checkout, setup, "pnpm build"]
+```
+
+## Secrets Management
+
+| Rule                                       | Reason                                        |
+| ------------------------------------------ | --------------------------------------------- |
+| Never echo secrets in CI logs              | Logs are often accessible to all contributors |
+| Use GitHub Secrets / environment variables | Encrypted at rest, masked in logs             |
+| Rotate secrets on exposure                 | Assume compromised if ever logged             |
+| Separate secrets per environment           | Staging keys ≠ production keys                |
+| Use OIDC for cloud providers               | No long-lived credentials needed              |
+
+## Release Automation
+
+### Semantic Versioning
+
+```
+MAJOR.MINOR.PATCH
+  │      │     └── Bug fixes (backward compatible)
+  │      └──────── New features (backward compatible)
+  └─────────────── Breaking changes
+```
+
+### Tag-Based Release
+
+```yaml
+on:
+  push:
+    tags: ["v*"]
+jobs:
+  release:
+    steps:
+      - uses: actions/checkout@v4
+      - run: pnpm build
+      - run: pnpm publish # or deploy
+      - uses: softprops/action-gh-release@v2
+        with:
+          generate_release_notes: true
+```
+
+## Common Rationalizations
+
+| Excuse                              | Rebuttal                                                                          |
+| ----------------------------------- | --------------------------------------------------------------------------------- |
+| "CI is slow, I'll test locally"     | Local tests miss environment-specific issues. Optimize CI instead of skipping it. |
+| "We can add CI later"               | Every merged PR without CI is a potential regression. Set up day one.             |
+| "The pipeline is too complex"       | Complexity means you're catching real issues. Simplify steps, not coverage.       |
+| "Manual deploy is faster"           | Until someone deploys the wrong branch. Automation prevents human error.          |
+| "Caching is premature optimization" | 5 minutes saved per PR × 20 PRs/week = 100 minutes/week. Cache from day one.      |
+
+## CI Performance Optimization
+
+| Technique              | Savings                   | Effort                 |
+| ---------------------- | ------------------------- | ---------------------- |
+| Dependency caching     | 30-60s per run            | Low — add cache action |
+| Parallel jobs          | 50-70% of sequential time | Low — split into jobs  |
+| Conditional runs       | Skip unchanged paths      | Medium — path filters  |
+| Build artifact caching | 1-5min per run            | Medium — cache config  |
+| Self-hosted runners    | Faster hardware           | High — infrastructure  |
+
+## Red Flags — STOP
+
+- CI pipeline takes >15 minutes for a PR check
+- Secrets hardcoded in workflow files
+- No caching configured despite slow builds
+- Tests skipped in CI "to save time"
+- Manual deployment steps in the release process
+- No rollback mechanism for failed deployments
+
+## Verification
+
+- [ ] All verification steps run on every PR
+- [ ] Pipeline fails fast (cheapest checks first)
+- [ ] Dependencies are cached
+- [ ] Secrets are never printed in logs
+- [ ] Release process is tag-triggered and automated
+- [ ] Rollback procedure is documented and tested
+
+## See Also
+
+- **verification-gates** — Detecting project type and running appropriate checks
+- **git-workflow-and-versioning** — Branch strategy and commit conventions
+- **security-and-hardening** — Secrets management and supply chain security

package/dist/template/.pi/skills/cloudflare/SKILL.md

@@ -0,0 +1,271 @@
+---
+name: cloudflare
+description: Use when deploying to or configuring ANY Cloudflare service — Workers, Pages, KV, D1, R2, AI, Tunnel, WAF. MUST load before writing Cloudflare Workers code, wrangler configs, or infrastructure-as-code for Cloudflare.
+---
+
+# Cloudflare Platform Skill
+
+## When to Use
+
+- When you need guidance or references for building on Cloudflare products.
+
+## When NOT to Use
+
+- When the task doesn't involve Cloudflare services or infrastructure.
+
+
+## How to Use This Skill
+
+### Reference File Structure
+
+Each product in `./references/<product>/` contains a `README.md` as the entry point, which may be structured in one of two ways:
+
+**Multi-file format (5 files):**
+| File | Purpose | When to Read |
+|------|---------|--------------|
+| `README.md` | Overview, when to use, getting started | **Always read first** |
+| `api.md` | Runtime API, types, method signatures | Writing code |
+| `configuration.md` | wrangler.toml, bindings, setup | Configuring a project |
+| `patterns.md` | Common patterns, best practices | Implementation guidance |
+| `gotchas.md` | Pitfalls, limitations, edge cases | Debugging, avoiding mistakes |
+
+**Single-file format:** All information consolidated in `README.md`.
+
+### Reading Order
+
+1. Start with `README.md`
+2. Then read additional files relevant to your task (if multi-file format):
+   - Building feature → `api.md` + `patterns.md`
+   - Setting up project → `configuration.md`
+   - Troubleshooting → `gotchas.md`
+
+### Example Paths
+
+```
+./references/workflows/README.md         # Start here for Workflows
+./references/workflows/api.md            # Workflow class, step methods
+./references/durable-objects/gotchas.md  # DO limitations
+./references/workers-ai/README.md        # Single-file - all Workers AI docs
+```
+
+## Quick Decision Trees
+
+### "I need to run code"
+
+```
+Need to run code?
+├─ Serverless functions at the edge → workers/
+├─ Full-stack web app with Git deploys → pages/
+├─ Stateful coordination/real-time → durable-objects/
+├─ Long-running multi-step jobs → workflows/
+├─ Run containers → containers/
+├─ Multi-tenant (customers deploy code) → workers-for-platforms/
+└─ Scheduled tasks (cron) → cron-triggers/
+```
+
+### "I need to store data"
+
+```
+Need storage?
+├─ Key-value (config, sessions, cache) → kv/
+├─ Relational SQL → d1/ (SQLite) or hyperdrive/ (existing Postgres/MySQL)
+├─ Object/file storage (S3-compatible) → r2/
+├─ Message queue (async processing) → queues/
+├─ Vector embeddings (AI/semantic search) → vectorize/
+├─ Strongly-consistent per-entity state → durable-objects/ (DO storage)
+├─ Secrets management → secrets-store/
+└─ Streaming ETL to R2 → pipelines/
+```
+
+### "I need AI/ML"
+
+```
+Need AI?
+├─ Run inference (LLMs, embeddings, images) → workers-ai/
+├─ Vector database for RAG/search → vectorize/
+├─ Build stateful AI agents → agents-sdk/
+├─ Gateway for any AI provider (caching, routing) → ai-gateway/
+└─ AI-powered search widget → ai-search/
+```
+
+### "I need networking/connectivity"
+
+```
+Need networking?
+├─ Expose local service to internet → tunnel/
+├─ TCP/UDP proxy (non-HTTP) → spectrum/
+├─ WebRTC TURN server → turn/
+├─ Private network connectivity → network-interconnect/
+├─ Optimize routing → argo-smart-routing/
+└─ Real-time video/audio → realtimekit/ or realtime-sfu/
+```
+
+### "I need security"
+
+```
+Need security?
+├─ Web Application Firewall → waf/
+├─ DDoS protection → ddos/
+├─ Bot detection/management → bot-management/
+├─ API protection → api-shield/
+├─ CAPTCHA alternative → turnstile/
+└─ Credential leak detection → waf/ (managed ruleset)
+```
+
+### "I need media/content"
+
+```
+Need media?
+├─ Image optimization/transformation → images/
+├─ Video streaming/encoding → stream/
+├─ Browser automation/screenshots → browser-rendering/
+└─ Third-party script management → zaraz/
+```
+
+### "I need infrastructure-as-code"
+
+```
+Need IaC?
+├─ Pulumi → pulumi/
+├─ Terraform → terraform/
+└─ Direct API → api/
+```
+
+## Product Index
+
+### Compute & Runtime
+
+| Product               | Entry File                                     |
+| --------------------- | ---------------------------------------------- |
+| Workers               | `./references/workers/README.md`               |
+| Pages                 | `./references/pages/README.md`                 |
+| Pages Functions       | `./references/pages-functions/README.md`       |
+| Durable Objects       | `./references/durable-objects/README.md`       |
+| Workflows             | `./references/workflows/README.md`             |
+| Containers            | `./references/containers/README.md`            |
+| Workers for Platforms | `./references/workers-for-platforms/README.md` |
+| Cron Triggers         | `./references/cron-triggers/README.md`         |
+| Tail Workers          | `./references/tail-workers/README.md`          |
+| Snippets              | `./references/snippets/README.md`              |
+| Smart Placement       | `./references/smart-placement/README.md`       |
+
+### Storage & Data
+
+| Product         | Entry File                               |
+| --------------- | ---------------------------------------- |
+| KV              | `./references/kv/README.md`              |
+| D1              | `./references/d1/README.md`              |
+| R2              | `./references/r2/README.md`              |
+| Queues          | `./references/queues/README.md`          |
+| Hyperdrive      | `./references/hyperdrive/README.md`      |
+| DO Storage      | `./references/do-storage/README.md`      |
+| Secrets Store   | `./references/secrets-store/README.md`   |
+| Pipelines       | `./references/pipelines/README.md`       |
+| R2 Data Catalog | `./references/r2-data-catalog/README.md` |
+| R2 SQL          | `./references/r2-sql/README.md`          |
+
+### AI & Machine Learning
+
+| Product    | Entry File                          |
+| ---------- | ----------------------------------- |
+| Workers AI | `./references/workers-ai/README.md` |
+| Vectorize  | `./references/vectorize/README.md`  |
+| Agents SDK | `./references/agents-sdk/README.md` |
+| AI Gateway | `./references/ai-gateway/README.md` |
+| AI Search  | `./references/ai-search/README.md`  |
+
+### Networking & Connectivity
+
+| Product              | Entry File                                    |
+| -------------------- | --------------------------------------------- |
+| Tunnel               | `./references/tunnel/README.md`               |
+| Spectrum             | `./references/spectrum/README.md`             |
+| TURN                 | `./references/turn/README.md`                 |
+| Network Interconnect | `./references/network-interconnect/README.md` |
+| Argo Smart Routing   | `./references/argo-smart-routing/README.md`   |
+| Workers VPC          | `./references/workers-vpc/README.md`          |
+
+### Security
+
+| Product         | Entry File                              |
+| --------------- | --------------------------------------- |
+| WAF             | `./references/waf/README.md`            |
+| DDoS Protection | `./references/ddos/README.md`           |
+| Bot Management  | `./references/bot-management/README.md` |
+| API Shield      | `./references/api-shield/README.md`     |
+| Turnstile       | `./references/turnstile/README.md`      |
+
+### Media & Content
+
+| Product           | Entry File                                 |
+| ----------------- | ------------------------------------------ |
+| Images            | `./references/images/README.md`            |
+| Stream            | `./references/stream/README.md`            |
+| Browser Rendering | `./references/browser-rendering/README.md` |
+| Zaraz             | `./references/zaraz/README.md`             |
+
+### Real-Time Communication
+
+| Product      | Entry File                            |
+| ------------ | ------------------------------------- |
+| RealtimeKit  | `./references/realtimekit/README.md`  |
+| Realtime SFU | `./references/realtime-sfu/README.md` |
+
+### Developer Tools
+
+| Product            | Entry File                                  |
+| ------------------ | ------------------------------------------- |
+| Wrangler           | `./references/wrangler/README.md`           |
+| Miniflare          | `./references/miniflare/README.md`          |
+| C3                 | `./references/c3/README.md`                 |
+| Observability      | `./references/observability/README.md`      |
+| Analytics Engine   | `./references/analytics-engine/README.md`   |
+| Web Analytics      | `./references/web-analytics/README.md`      |
+| Sandbox            | `./references/sandbox/README.md`            |
+| Workerd            | `./references/workerd/README.md`            |
+| Workers Playground | `./references/workers-playground/README.md` |
+
+### Infrastructure as Code
+
+| Product   | Entry File                         |
+| --------- | ---------------------------------- |
+| Pulumi    | `./references/pulumi/README.md`    |
+| Terraform | `./references/terraform/README.md` |
+| API       | `./references/api/README.md`       |
+
+### Other Services
+
+| Product       | Entry File                             |
+| ------------- | -------------------------------------- |
+| Email Routing | `./references/email-routing/README.md` |
+| Email Workers | `./references/email-workers/README.md` |
+| Static Assets | `./references/static-assets/README.md` |
+| Bindings      | `./references/bindings/README.md`      |
+| Cache Reserve | `./references/cache-reserve/README.md` |
+
+## Common Rationalizations
+
+| Rationalization | Reality |
+|---|---|
+| "It works locally, it'll work on Cloudflare" | Cloudflare Workers have different runtime constraints (CPU time, memory, subrequest limits). |
+| "I'll hardcode the config for now" | Hardcoded config becomes stale config. Use environment variables and secrets. |
+| "The free tier is enough for launch" | Free tier limits are real. Plan for scale before you need it. |
+| "I'll add caching later" | Caching strategy should be part of the initial architecture, not an afterthought. |
+
+## Red Flags
+
+- Workers deployed without testing in wrangler dev first
+- Hardcoded secrets in wrangler.toml or source code
+- No error handling for Worker CPU timeouts
+- KV/D1/R2 operations without error handling for eventual consistency
+- Caching strategy not defined before launch
+
+## Verification
+
+After deploying to Cloudflare:
+
+- [ ] `wrangler dev` testing passed for all endpoints
+- [ ] Environment variables and secrets are configured in dashboard
+- [ ] Error handling covers Worker-specific failures (CPU timeout, subrequest limit)
+- [ ] Caching strategy is documented and tested
+- [ ] Production deployment verified with actual traffic

package/dist/template/.pi/skills/cloudflare/references/agents-sdk/README.md

@@ -0,0 +1,35 @@
+# Cloudflare Agents SDK
+
+Cloudflare Agents SDK enables building AI-powered agents on Durable Objects with state, WebSockets, SQL, scheduling, and AI integration.
+
+## Core Value
+Build stateful, globally distributed AI agents with persistent memory, real-time connections, scheduled tasks, and async workflows.
+
+## When to Use
+- Persistent state + memory required
+- Real-time WebSocket connections
+- Long-running workflows (minutes/hours)
+- Chat interfaces with AI models
+- Scheduled/recurring tasks with state
+- DB queries with agent state
+
+## Quick Start
+```typescript
+import { Agent } from "agents";
+
+export class MyAgent extends Agent<Env> {
+  onStart() {
+    this.sql`CREATE TABLE IF NOT EXISTS users (id TEXT PRIMARY KEY)`;
+  }
+  
+  async onRequest(request: Request) {
+    return Response.json({ state: this.state });
+  }
+}
+```
+
+## See Also
+- durable-objects - Agent infrastructure
+- d1 - External database integration
+- workers-ai - AI model integration
+- vectorize - Vector search for RAG patterns