@agentskillkit/agent-skills 1.0.1 → 3.2.2

package/.agent/workflows/benchmark.md

@@ -0,0 +1,221 @@
+---
+description: Run k6/Artillery load tests with realistic scenarios. Measure throughput, latency, and error rates.
+---
+
+# Performance Benchmark Workflow
+
+Run load tests to validate application can handle production scale.
+
+## 🎯 Purpose
+
+This workflow uses the **perf-optimizer** skill to:
+
+- Run realistic load tests (k6/Artillery)
+- Measure performance under load
+- Identify bottlenecks at scale
+- Generate performance reports
+
+## 🤖 Meta-Agents Integration
+
+| Phase | Agent | Action |
+| ----- | ----- | ------ |
+| **Pre-Test** | `recovery` | Save current performance baseline |
+| **During Test** | `orchestrator` | Coordinate parallel load scenarios |
+| **Post-Test** | `learner` | Learn bottleneck patterns |
+| **Analysis** | `assessor` | Evaluate production-readiness risk |
+
+```
+Flow:
+recovery.save(baseline) → orchestrator.run(load_test)
+       ↓
+results → learner.log(bottlenecks)
+       ↓
+assessor.evaluate(production_risk) → go/no-go
+```
+
+---
+
+## 🔗 Chain: performance-audit (perf-optimizer skill only)
+
+**Skills Loaded (1):**
+
+- `perf-optimizer` - k6/Artillery load testing, performance benchmarking
+
+## 📖 Usage
+
+```bash
+/benchmark <description>
+```
+
+### Examples
+
+```bash
+# Basic benchmark
+/benchmark my-api
+
+# With specific target
+/benchmark 10,000 concurrent users
+
+# Production validation
+/benchmark production checkout flow
+```
+
+## 🔄 Workflow Steps
+
+This workflow automatically:
+
+1. **Generate Load Test Script**
+   - Realistic user scenarios
+   - Staged ramp-up (100 → 1K → 5K → 10K users)
+   - Performance thresholds
+
+2. **Run Load Test**
+   - Execute k6/Artillery
+   - Monitor observability in real-time
+   - Capture bottlenecks
+
+3. **Analyze Results**
+   - p50, p95, p99 latency
+   - Error rate
+   - Throughput (requests/sec)
+   - Resource usage
+
+4. **Generate Report**
+   - Performance summary
+   - Bottleneck identification
+   - Recommendations
+
+## ✅ Success Criteria
+
+After running `/benchmark`, you will have:
+
+✓ **Load Test Completed** - At target scale
+✓ **observability Captured** - Latency, errors, throughput
+✓ **Bottlenecks Identified** - Database, memory, network
+✓ **Report Generated** - HTML + JSON results
+
+## 📊 Load Test Scenarios
+
+### Spike Test
+
+Rapid increase to validate burst handling
+
+```
+100 users → 10,000 users (1 minute)
+```
+
+### Soak Test
+
+Sustained load to detect memory leaks
+
+```
+1,000 users (3 hours)
+```
+
+### Stress Test
+
+Find breaking point
+
+```
+Incrementally increase until failure
+```
+
+## 🎨 Performance observability
+
+| Metric          | Measured        | Target     |
+| --------------- | --------------- | ---------- |
+| **p95 Latency** | Response time   | <200ms     |
+| **Error Rate**  | Failed requests | <1%        |
+| **Throughput**  | Requests/sec    | 1,000+ rps |
+| **Max Users**   | Concurrent      | 10,000+    |
+
+## 🔍 Related Workflows
+
+- `/optimize` - Auto-optimize before benchmarking
+- `/monitor` - Setup monitoring for production
+- `/launch` - Deploy after validation
+
+## 💡 Tips
+
+**When to use `/benchmark`:**
+
+- Before going to production
+- After optimizations (validate improvements)
+- Regular performance regression testing
+- Capacity planning
+
+**Best practices:**
+
+- Test realistic user scenarios
+- Gradually ramp up load
+- Monitor infrastructure during test
+- Run multiple times for consistency
+
+## 📚 Example Output
+
+```bash
+You: "/benchmark my-api 10K users"
+
+Agent: Loading performance-audit chain (perf-optimizer only)
+       ↓
+
+[1/1] 🧪 Running Load Test...
+
+   Scenario: Ramp to 10,000 concurrent users
+   Duration: 16 minutes
+   Tool: k6
+
+   ✅ Test complete!
+
+📊 Results:
+
+   Requests:
+   ✅ Total: 1,245,000
+   ✅ Success: 1,242,500 (99.8%)
+   ❌ Failed: 2,500 (0.2%)
+
+   Response Time:
+   ✅ p50: 85ms
+   ✅ p95: 180ms
+   ⚠️ p99: 450ms
+   ✅ Max: 1.2s
+
+   Throughput:
+   ✅ 4,150 requests/sec
+   ✅ 15 GB data received
+
+   Errors:
+   ✅ Error rate: 0.2% (target: <1% ✓)
+   ⚠️ Timeout errors: 1,500 (database)
+
+🎯 Bottlenecks Detected:
+   ❌ Database connections maxed (20/20)
+   ⚠️ Memory usage: 90%
+   ✅ CPU usage: 45%
+
+💡 Recommendations:
+   1. Increase DB pool: 20 → 50
+   2. Add horizontal scaling (2 → 4 instances)
+   3. Implement request queuing
+
+✅ Benchmark complete!
+
+   Report: performance-report.html
+   Raw data: results.json
+```
+
+## 🚨 Common Bottlenecks
+
+| Symptom              | Cause                     | Fix                  |
+| -------------------- | ------------------------- | -------------------- |
+| **Timeouts at load** | Connection pool exhausted | Increase pool size   |
+| **Memory spikes**    | Memory leak               | Fix resource cleanup |
+| **High latency**     | Slow queries              | Add indexes          |
+| **500 errors**       | Resource limits           | Scale horizontally   |
+
+---
+
+**Version:** 1.0.0  
+**Chain:** performance-audit (perf-optimizer)  
+**Added:** v3.5.0 (FAANG upgrade - Phase 2)
+

package/.agent/workflows/boost.md

@@ -1,5 +1,6 @@
 ---
 description: Feature enhancer for existing apps. Iterative upgrades with dependency awareness.
+chain: build-web-app
 ---
 
 # /boost - Feature Enhancer
@@ -14,23 +15,53 @@ Add features or upgrades to existing applications. **Analyzes current architectu
 
 ---
 
+## 🤖 Meta-Agents Integration
+
+| Phase | Agent | Action |
+| ----- | ----- | ------ |
+| **Pre-Change** | `assessor` | Evaluate impact and risk level |
+| **Pre-Change** | `recovery` | Save affected files state |
+| **On Conflict** | `critic` | Resolve breaking change decisions |
+| **On Failure** | `recovery` | Restore to pre-boost state |
+| **Post-Boost** | `learner` | Log patterns for future boosts |
+
+```
+Flow:
+assessor → risk level?
+   ↓
+CRITICAL → require approval → recovery.save()
+MEDIUM → recovery.save() → proceed
+LOW → proceed directly
+   ↓
+execute boost → test → success?
+   ↓ NO
+recovery.restore() → learner.log()
+```
+
+---
+
 ## 🔴 MANDATORY: Impact Assessment
 
 Before ANY change:
 
 ### Step 1: Project Analysis
+
 // turbo
+
 ```bash
-python .agent/scripts/session_manager.py info
+npm run session:info
 ```
 
 ### Step 2: Security Check
+
 // turbo
+
 ```bash
-python .agent/skills/vulnerability-scanner/scripts/security_scan.py .
+npm run scan:security
 ```
 
 ### Step 3: Dependency Map
+
 ```
 Identify:
 □ Direct dependencies (what this file imports)
@@ -43,27 +74,27 @@ Identify:
 
 ## Impact Classification
 
-| Change Size | Criteria | Action Required |
-|-------------|----------|-----------------|
-| **Small** | 1-3 files, no deps | Proceed directly |
-| **Medium** | 4-10 files, minor deps | Show plan, get approval |
-| **Large** | 10+ files, breaking changes | Create PLAN.md first |
+| Change Size | Criteria                    | Action Required         |
+| ----------- | --------------------------- | ----------------------- |
+| **Small**   | 1-3 files, no deps          | Proceed directly        |
+| **Medium**  | 4-10 files, minor deps      | Show plan, get approval |
+| **Large**   | 10+ files, breaking changes | Create PLAN.md first    |
 
 ---
 
 ## Output Format
 
-```markdown
+````markdown
 ## 🚀 Boost: [Feature Name]
 
 ### Impact Assessment
 
-| Metric | Value |
-|--------|-------|
-| Files Created | 5 |
-| Files Modified | 3 |
-| Tests Affected | 2 |
-| Breaking Changes | None |
+| Metric           | Value |
+| ---------------- | ----- |
+| Files Created    | 5     |
+| Files Modified   | 3     |
+| Tests Affected   | 2     |
+| Breaking Changes | None  |
 
 ### Dependency Analysis
 
@@ -74,20 +105,23 @@ graph LR
     B --> D[database]
     C --> E[jwt]
 ```
+````
 
 ### Changes Required
 
-| File | Change | Risk |
-|------|--------|------|
-| `src/services/user.ts` | Add method | Low |
-| `src/routes/api.ts` | New endpoint | Low |
-| `prisma/schema.prisma` | Add field | Medium |
+| File                   | Change       | Risk   |
+| ---------------------- | ------------ | ------ |
+| `src/services/user.ts` | Add method   | Low    |
+| `src/routes/api.ts`    | New endpoint | Low    |
+| `prisma/schema.prisma` | Add field    | Medium |
 
 ### Approval Required?
+
 ⚠️ **Medium change** - 8 files affected
 
 Proceed? (y/n)
-```
+
+````
 
 ---
 
@@ -115,7 +149,7 @@ Proceed? (y/n)
 
 ### Preview
 Hot reload applied - refresh to see changes.
-```
+````
 
 ---
 
@@ -151,13 +185,14 @@ graph LR
     style A fill:#f59e0b
 ```
 
-| After /boost | Run | Purpose |
-|--------------|-----|---------|
-| Feature added | `/validate` | Test changes |
-| Ready to deploy | `/launch` | Deploy |
-| Found issues | `/diagnose` | Debug |
+| After /boost    | Run         | Purpose      |
+| --------------- | ----------- | ------------ |
+| Feature added   | `/validate` | Test changes |
+| Ready to deploy | `/launch`   | Deploy       |
+| Found issues    | `/diagnose` | Debug        |
 
 **Handoff to /validate:**
+
 ```markdown
 Feature added. Run /validate to test changes.
 ```

package/.agent/workflows/build.md

@@ -1,5 +1,6 @@
----
-description: Full-stack application factory. From idea to deployed app with multi-agent coordination.
+---
+description: Full-stack application factory. From idea to deployed app with agent-patterns coordination.
+chain: build-web-app
 ---
 
 # /build - Application Factory
@@ -14,11 +15,32 @@ Ship production-ready applications from natural language descriptions. **Coordin
 
 ---
 
-## 🔴 MANDATORY: Build Pipeline
+## 🔴 MANDATORY: Build Pipeline
+
+### Phase 0: Risk Assessment & Safety (NEW)
+
+> **Before building, invoke meta-agents:**
+
+| Step | Agent | Action |
+| ---- | ----- | ------ |
+| 1 | `assessor` | Evaluate risk level of requested changes |
+| 2 | `recovery` | Save current state (if existing project) |
+
+```
+IF risk_level == CRITICAL:
+  → Require explicit user approval
+  → Prepare rollback plan
+ELSE:
+  → Proceed with Phase 1
+```
 
 ### Phase 1: Requirements Discovery
-// turbo
+
+
 Ask these questions if not answered:
+
+// turbo
+
 ```
 1. What TYPE of app? (web/mobile/api/cli)
 2. Who are the USERS? (consumers/business/developers)
@@ -31,22 +53,24 @@ Ask these questions if not answered:
 
 **AI-Powered Stack Recommendation:**
 
-| App Type | Recommended Stack | Agents Invoked |
-|----------|-------------------|----------------|
-| **Web SaaS** | Next.js + Prisma + PostgreSQL | frontend, backend, database |
-| **E-commerce** | Next.js + Stripe + Supabase | frontend, backend, security |
-| **Mobile** | React Native + Expo + Firebase | mobile, backend, test |
-| **API** | Hono + Prisma + Railway | backend, database, devops |
-| **Dashboard** | Next.js + Tremor + Chart.js | frontend, backend |
+| App Type       | Recommended Stack              | Agents Invoked              |
+| -------------- | ------------------------------ | --------------------------- |
+| **Web SaaS**   | Next.js + Prisma + PostgreSQL  | frontend, backend, database |
+| **E-commerce** | Next.js + Stripe + Supabase    | frontend, backend, security |
+| **Mobile**     | React Native + Expo + Firebase | mobile, backend, test       |
+| **API**        | Hono + Prisma + Railway        | backend, database, devops   |
+| **Dashboard**  | Next.js + Tremor + Chart.js    | frontend, backend           |
 
 ### Phase 3: Project Scaffolding
+
 // turbo
+
 ```bash
 # Auto-detect and scaffold
-python .agent/scripts/session_manager.py create --name "$PROJECT_NAME" --stack "$STACK"
+npm run session:status
 ```
 
-### Phase 4: Multi-Agent Build
+### Phase 4: agent-patterns Build
 
 ```mermaid
 graph TD
@@ -69,9 +93,11 @@ graph TD
 ```
 
 ### Phase 5: Preview & Iterate
+
 // turbo
+
 ```bash
-python .agent/scripts/auto_preview.py start
+npm run preview:start
 ```
 
 ---
@@ -79,43 +105,46 @@ python .agent/scripts/auto_preview.py start
 ## Output Format
 
 ```markdown
-## 🏗️ Building: [App Name]
+## 🏗️ Building: [App Name]
 
 ### Stack Decision
-| Layer | Choice | Reason |
-|-------|--------|--------|
-| Frontend | Next.js 15 | SSR, App Router, Vercel deploy |
-| Backend | Hono + Prisma | Type-safe, edge-ready |
-| Database | PostgreSQL | Relational, Supabase hosting |
-| Auth | Clerk | Fast integration, social login |
-| Styling | Tailwind + shadcn/ui | Rapid UI development |
+
+| Layer    | Choice               | Reason                         |
+| -------- | -------------------- | ------------------------------ |
+| Frontend | Next.js 15           | SSR, App Router, Vercel deploy |
+| Backend  | Hono + Prisma        | Type-safe, edge-ready          |
+| Database | PostgreSQL           | Relational, Supabase hosting   |
+| Auth     | Clerk                | Fast integration, social login |
+| Styling  | Tailwind + shadcn/ui | Rapid UI development           |
 
 ### Agent Coordination
 
-| Agent | Task | Status |
-|-------|------|--------|
-| `database-architect` | Schema design | ✅ Complete |
-| `backend-specialist` | API routes | 🔄 In progress |
-| `frontend-specialist` | UI components | ⏳ Waiting |
-| `test-engineer` | E2E tests | ⏳ Waiting |
+| Agent                 | Task          | Status         |
+| --------------------- | ------------- | -------------- |
+| `database-architect`  | Schema design | ✅ Complete    |
+| `backend-specialist`  | API routes    | 🔄 In progress |
+| `frontend-specialist` | UI components | ⏳ Waiting     |
+| `test-engineer`       | E2E tests     | ⏳ Waiting     |
 
 ### Files Created
 ```
+
 src/
-├── app/
-│   ├── page.tsx
-│   ├── layout.tsx
-│   └── api/
-├── components/
-├── lib/
-├── prisma/
-│   └── schema.prisma
-└── tests/
+├── app/
+│ ├── page.tsx
+│ ├── layout.tsx
+│ └── api/
+├── components/
+├── lib/
+├── prisma/
+│ └── schema.prisma
+└── tests/
+
 ```
 
 ### Preview
-🌐 **URL:** http://localhost:3000
-📊 **Status:** Running
+🌐 **URL:** http://localhost:3000
+📊 **Status:** Running
 
 ### Next Steps
 - [ ] Review the code
@@ -142,14 +171,42 @@ src/
 
 If user doesn't specify, use these:
 
-| Aspect | Default |
-|--------|---------|
-| Framework | Next.js 15 |
-| Styling | Tailwind + shadcn/ui |
-| Database | PostgreSQL (Supabase) |
-| Auth | Clerk |
-| Deployment | Vercel |
-| Testing | Vitest + Playwright |
+| Aspect     | Default               |
+| ---------- | --------------------- |
+| Framework  | Next.js 15            |
+| Styling    | Tailwind + shadcn/ui  |
+| Database   | PostgreSQL (Supabase) |
+| Auth       | Clerk                 |
+| Deployment | Vercel                |
+| Testing    | Vitest + Playwright   |
+
+---
+
+## â›” MANDATORY: Problem Verification Before Completion
+
+> **CRITICAL:** This check MUST be performed before any `notify_user` or task completion.
+
+### Check @[current_problems]
+
+```
+1. Read @[current_problems] from IDE
+2. If errors/warnings > 0:
+   a. Auto-fix: imports, types, lint errors
+   b. Re-check @[current_problems]
+   c. If still > 0 → STOP → Notify user
+3. If count = 0 → Proceed to Quality Gates
+```
+
+### Auto-Fixable
+
+| Type            | Fix                  |
+| --------------- | -------------------- |
+| Missing import  | Add import statement |
+| JSX namespace   | Import from 'react'  |
+| Unused variable | Remove or prefix `_` |
+| Lint errors     | Run eslint --fix     |
+
+> **Rule:** Never mark complete with errors in `@[current_problems]`.
 
 ---
 
@@ -157,6 +214,7 @@ If user doesn't specify, use these:
 
 Before marking complete, verify:
 
+- [ ] `@[current_problems]` shows 0 errors ← **CHECK THIS FIRST**
 - [ ] All files compile without errors
 - [ ] Database schema is valid
 - [ ] API endpoints respond correctly
@@ -168,7 +226,7 @@ Before marking complete, verify:
 
 ---
 
-## 🔗 Workflow Chain
+## 🔗 Workflow Chain
 
 ```mermaid
 graph LR
@@ -178,15 +236,17 @@ graph LR
     style B fill:#10b981
 ```
 
-| After /build | Run | Purpose |
-|--------------|-----|---------|
-| Build complete | `/validate` | Run tests |
-| Needs testing | `/stage` | Start preview server |
-| Ready to deploy | `/launch` | Deploy to production |
-| Found bugs | `/diagnose` | Debug issues |
+| After /build    | Run         | Purpose              |
+| --------------- | ----------- | -------------------- |
+| Build complete  | `/validate` | Run tests            |
+| Needs testing   | `/stage`    | Start preview server |
+| Ready to deploy | `/launch`   | Deploy to production |
+| Found bugs      | `/diagnose` | Debug issues         |
 
 **Handoff to /validate:**
+
 ```markdown
 Build complete. Preview running at http://localhost:3000
 Run /validate to generate and execute tests.
 ```
+

package/.agent/workflows/chronicle.md

@@ -14,6 +14,25 @@ Generate comprehensive documentation automatically. **Analyzes code structure an
 
 ---
 
+## 🤖 Meta-Agents Integration
+
+| Phase | Agent | Action |
+| ----- | ----- | ------ |
+| **Pre-Generation** | `assessor` | Evaluate documentation scope |
+| **Pattern Learning** | `learner` | Learn from existing doc patterns |
+| **Post-Generation** | `learner` | Log documentation templates for reuse |
+
+```
+Flow:
+assessor.evaluate(scope) → file count, complexity
+       ↓
+learner.analyze(existing_docs) → patterns
+       ↓
+generate → learner.log(templates)
+```
+
+---
+
 ## Sub-commands
 
 ```