aigroup-workflow 2.1.2 → 2.2.0

package/skills/quality/chaos-engineer/references/kubernetes-chaos.md

@@ -0,0 +1,432 @@
+# Kubernetes Chaos Engineering
+
+## Litmus Chaos - ChaosEngine
+
+```yaml
+apiVersion: litmuschaos.io/v1alpha1
+kind: ChaosEngine
+metadata:
+  name: nginx-chaos
+  namespace: default
+spec:
+  # Application information
+  appinfo:
+    appns: 'default'
+    applabel: 'app=nginx'
+    appkind: 'deployment'
+
+  # Chaos service account
+  chaosServiceAccount: litmus-admin
+
+  # Experiments to run
+  experiments:
+    - name: pod-delete
+      spec:
+        components:
+          env:
+            # Total chaos duration
+            - name: TOTAL_CHAOS_DURATION
+              value: '60'
+
+            # Chaos interval (delete pod every X seconds)
+            - name: CHAOS_INTERVAL
+              value: '10'
+
+            # Force delete pods
+            - name: FORCE
+              value: 'true'
+
+            # Number of pods to delete
+            - name: PODS_AFFECTED_PERC
+              value: '50'
+
+    - name: pod-network-latency
+      spec:
+        components:
+          env:
+            - name: TOTAL_CHAOS_DURATION
+              value: '60'
+            - name: NETWORK_LATENCY
+              value: '2000'  # 2 second latency
+            - name: JITTER
+              value: '200'   # 200ms jitter
+            - name: CONTAINER_RUNTIME
+              value: 'containerd'
+
+    - name: pod-cpu-hog
+      spec:
+        components:
+          env:
+            - name: TOTAL_CHAOS_DURATION
+              value: '60'
+            - name: CPU_CORES
+              value: '2'
+            - name: PODS_AFFECTED_PERC
+              value: '50'
+
+  # Monitor application during chaos
+  monitoring: true
+
+  # Job cleanup policy
+  jobCleanUpPolicy: 'delete'
+```
+
+## Chaos Mesh Experiments
+
+```yaml
+# Network partition between services
+apiVersion: chaos-mesh.org/v1alpha1
+kind: NetworkChaos
+metadata:
+  name: partition-frontend-backend
+  namespace: chaos-testing
+spec:
+  action: partition
+  mode: all
+  selector:
+    namespaces:
+      - production
+    labelSelectors:
+      'app': 'frontend'
+  direction: to
+  target:
+    mode: all
+    selector:
+      namespaces:
+        - production
+      labelSelectors:
+        'app': 'backend'
+  duration: '5m'
+
+---
+# Pod failure - kill random pods
+apiVersion: chaos-mesh.org/v1alpha1
+kind: PodChaos
+metadata:
+  name: pod-failure
+  namespace: chaos-testing
+spec:
+  action: pod-failure
+  mode: one  # one, all, fixed, fixed-percent, random-max-percent
+  duration: '30s'
+  selector:
+    namespaces:
+      - production
+    labelSelectors:
+      'app': 'payment-service'
+  scheduler:
+    cron: '@every 10m'  # Run every 10 minutes
+
+---
+# Network bandwidth limitation
+apiVersion: chaos-mesh.org/v1alpha1
+kind: NetworkChaos
+metadata:
+  name: bandwidth-limit
+spec:
+  action: bandwidth
+  mode: all
+  selector:
+    namespaces:
+      - production
+    labelSelectors:
+      'tier': 'backend'
+  bandwidth:
+    rate: '1mbps'
+    limit: 20000
+    buffer: 10000
+  duration: '5m'
+
+---
+# Disk I/O stress
+apiVersion: chaos-mesh.org/v1alpha1
+kind: IOChaos
+metadata:
+  name: io-latency
+spec:
+  action: latency
+  mode: one
+  selector:
+    namespaces:
+      - production
+    labelSelectors:
+      'app': 'database'
+  volumePath: /var/lib/postgresql/data
+  path: /var/lib/postgresql/data/**/*
+  delay: '100ms'
+  percent: 50  # 50% of I/O operations affected
+  duration: '5m'
+
+---
+# DNS chaos - random DNS errors
+apiVersion: chaos-mesh.org/v1alpha1
+kind: DNSChaos
+metadata:
+  name: dns-random-error
+spec:
+  action: random
+  mode: all
+  selector:
+    namespaces:
+      - production
+    labelSelectors:
+      'app': 'api-gateway'
+  patterns:
+    - external-api.example.com
+    - *.third-party-service.com
+  duration: '3m'
+```
+
+## Node Drain Simulation
+
+```python
+from kubernetes import client, config
+from kubernetes.client.rest import ApiException
+import time
+
+class K8sNodeChaos:
+    def __init__(self):
+        config.load_kube_config()
+        self.core_v1 = client.CoreV1Api()
+        self.apps_v1 = client.AppsV1Api()
+
+    def cordon_node(self, node_name: str):
+        """Mark node as unschedulable."""
+        body = {
+            "spec": {
+                "unschedulable": True
+            }
+        }
+        try:
+            self.core_v1.patch_node(node_name, body)
+            print(f"Node {node_name} cordoned")
+        except ApiException as e:
+            print(f"Failed to cordon node: {e}")
+
+    def drain_node(
+        self,
+        node_name: str,
+        grace_period_seconds: int = 30,
+        delete_local_data: bool = True
+    ):
+        """
+        Drain node by evicting all pods.
+        Simulates node failure or maintenance.
+        """
+        # First, cordon the node
+        self.cordon_node(node_name)
+
+        # Get all pods on the node
+        field_selector = f"spec.nodeName={node_name}"
+        pods = self.core_v1.list_pod_for_all_namespaces(
+            field_selector=field_selector
+        )
+
+        # Evict each pod
+        for pod in pods.items:
+            # Skip DaemonSet pods and mirror pods
+            if pod.metadata.owner_references:
+                for owner in pod.metadata.owner_references:
+                    if owner.kind in ['DaemonSet', 'Node']:
+                        continue
+
+            # Create eviction
+            eviction = client.V1Eviction(
+                metadata=client.V1ObjectMeta(
+                    name=pod.metadata.name,
+                    namespace=pod.metadata.namespace
+                ),
+                delete_options=client.V1DeleteOptions(
+                    grace_period_seconds=grace_period_seconds
+                )
+            )
+
+            try:
+                self.core_v1.create_namespaced_pod_eviction(
+                    name=pod.metadata.name,
+                    namespace=pod.metadata.namespace,
+                    body=eviction
+                )
+                print(f"Evicted pod {pod.metadata.name}")
+            except ApiException as e:
+                if e.status == 429:  # Too many requests
+                    print(f"Pod {pod.metadata.name} protected by PDB")
+                else:
+                    print(f"Failed to evict {pod.metadata.name}: {e}")
+
+        return {"node": node_name, "status": "drained"}
+
+    def uncordon_node(self, node_name: str):
+        """Mark node as schedulable again."""
+        body = {
+            "spec": {
+                "unschedulable": False
+            }
+        }
+        self.core_v1.patch_node(node_name, body)
+        print(f"Node {node_name} uncordoned")
+
+    def simulate_node_failure(
+        self,
+        node_name: str,
+        duration_seconds: int = 300
+    ):
+        """
+        Simulate complete node failure.
+        Drain node, wait, then restore.
+        """
+        print(f"Simulating failure of node {node_name}")
+
+        # Drain the node
+        self.drain_node(node_name)
+
+        # Wait for duration
+        print(f"Node failed for {duration_seconds} seconds")
+        time.sleep(duration_seconds)
+
+        # Restore node
+        self.uncordon_node(node_name)
+        print("Node restored")
+```
+
+## Pod Autoscaling Chaos
+
+```yaml
+# Test HPA behavior under load
+apiVersion: chaos-mesh.org/v1alpha1
+kind: StressChaos
+metadata:
+  name: stress-hpa-trigger
+spec:
+  mode: all
+  selector:
+    namespaces:
+      - production
+    labelSelectors:
+      'app': 'web-server'
+  stressors:
+    cpu:
+      workers: 2
+      load: 80  # 80% CPU load
+  duration: '10m'
+
+---
+# Verify HPA scaling response
+apiVersion: v1
+kind: Pod
+metadata:
+  name: chaos-verification
+spec:
+  containers:
+  - name: verifier
+    image: bitnami/kubectl:latest
+    command:
+      - /bin/bash
+      - -c
+      - |
+        # Monitor HPA scaling
+        while true; do
+          echo "=== HPA Status ==="
+          kubectl get hpa web-server -o json | \
+            jq '.status | {current: .currentReplicas, desired: .desiredReplicas, cpu: .currentCPUUtilizationPercentage}'
+
+          echo "=== Pod Count ==="
+          kubectl get pods -l app=web-server --no-headers | wc -l
+
+          sleep 10
+        done
+```
+
+## Custom Resource Chaos
+
+```python
+# Python script to test custom CRD resilience
+from kubernetes import client, config
+from kubernetes.client.rest import ApiException
+import random
+import time
+
+def chaos_delete_custom_resources(
+    group: str,
+    version: str,
+    plural: str,
+    namespace: str,
+    percentage: int = 30
+):
+    """
+    Randomly delete custom resources to test operator resilience.
+
+    Args:
+        group: API group (e.g., 'app.example.com')
+        version: API version (e.g., 'v1')
+        plural: Resource plural name (e.g., 'myapps')
+        namespace: Namespace to target
+        percentage: Percentage of resources to delete (0-100)
+    """
+    config.load_kube_config()
+    custom_api = client.CustomObjectsApi()
+
+    try:
+        # List all custom resources
+        resources = custom_api.list_namespaced_custom_object(
+            group=group,
+            version=version,
+            namespace=namespace,
+            plural=plural
+        )
+
+        items = resources.get('items', [])
+        if not items:
+            print("No resources found")
+            return
+
+        # Calculate number to delete
+        count_to_delete = max(1, int(len(items) * percentage / 100))
+
+        # Randomly select resources
+        to_delete = random.sample(items, count_to_delete)
+
+        print(f"Deleting {count_to_delete} of {len(items)} {plural}")
+
+        # Delete selected resources
+        for resource in to_delete:
+            name = resource['metadata']['name']
+            try:
+                custom_api.delete_namespaced_custom_object(
+                    group=group,
+                    version=version,
+                    namespace=namespace,
+                    plural=plural,
+                    name=name,
+                    body=client.V1DeleteOptions()
+                )
+                print(f"Deleted {plural}/{name}")
+                time.sleep(1)  # Rate limit deletions
+            except ApiException as e:
+                print(f"Failed to delete {name}: {e}")
+
+    except ApiException as e:
+        print(f"Error listing resources: {e}")
+
+# Example: Delete 30% of MyApp custom resources
+chaos_delete_custom_resources(
+    group='app.example.com',
+    version='v1',
+    plural='myapps',
+    namespace='production',
+    percentage=30
+)
+```
+
+## Quick Reference
+
+| Chaos Type | Tool | YAML/Command |
+|------------|------|--------------|
+| Pod delete | Litmus | `pod-delete` experiment |
+| Network latency | Chaos Mesh | `NetworkChaos` with action: delay |
+| Node drain | kubectl/API | `kubectl drain <node>` |
+| CPU stress | Chaos Mesh | `StressChaos` with cpu stressor |
+| DNS failure | Chaos Mesh | `DNSChaos` random/error action |
+| I/O latency | Chaos Mesh | `IOChaos` with latency action |
+| Network partition | Chaos Mesh | `NetworkChaos` partition |
+| Pod failure | Chaos Mesh | `PodChaos` pod-failure |

package/skills/quality/code-reviewer/SKILL.md

@@ -0,0 +1,119 @@
+---
+name: code-reviewer
+description: Analyzes code diffs and files to identify bugs, security vulnerabilities (SQL injection, XSS, insecure deserialization), code smells, N+1 queries, naming issues, and architectural concerns, then produces a structured review report with prioritized, actionable feedback. Use when reviewing pull requests, conducting code quality audits, identifying refactoring opportunities, or checking for security issues. Invoke for PR reviews, code quality checks, refactoring suggestions, review code, code quality. Complements specialized skills (security-reviewer, test-master) by providing broad-scope review across correctness, performance, maintainability, and test coverage in a single pass.
+license: MIT
+allowed-tools: Read, Grep, Glob
+metadata:
+  author: https://github.com/Jeffallan
+  version: "1.1.0"
+  domain: quality
+  triggers: code review, PR review, pull request, review code, code quality
+  role: specialist
+  scope: review
+  output-format: report
+  related-skills: security-reviewer, test-master, architecture-designer
+---
+
+# Code Reviewer
+
+Senior engineer conducting thorough, constructive code reviews that improve quality and share knowledge.
+
+## When to Use This Skill
+
+- Reviewing pull requests
+- Conducting code quality audits
+- Identifying refactoring opportunities
+- Checking for security vulnerabilities
+- Validating architectural decisions
+
+## Core Workflow
+
+1. **Context** — Read PR description, understand the problem being solved. **Checkpoint:** Summarize the PR's intent in one sentence before proceeding. If you cannot, ask the author to clarify.
+2. **Structure** — Review architecture and design decisions. Ask: Does this follow existing patterns in the codebase? Are new abstractions justified?
+3. **Details** — Check code quality, security, and performance. Apply the checks in the Reference Guide below. Ask: Are there N+1 queries, hardcoded secrets, or injection risks?
+4. **Tests** — Validate test coverage and quality. Ask: Are edge cases covered? Do tests assert behavior, not implementation?
+5. **Feedback** — Produce a categorized report using the Output Template. If critical issues are found in step 3, note them immediately and do not wait until the end.
+
+> **Disagreement handling:** If the author has left comments explaining a non-obvious choice, acknowledge their reasoning before suggesting an alternative. Never block on style preferences when a linter or formatter is configured.
+
+## Reference Guide
+
+Load detailed guidance based on context:
+
+<!-- Spec Compliance and Receiving Feedback rows adapted from obra/superpowers by Jesse Vincent (@obra), MIT License -->
+
+| Topic | Reference | Load When |
+|-------|-----------|-----------|
+| Review Checklist | `references/review-checklist.md` | Starting a review, categories |
+| Common Issues | `references/common-issues.md` | N+1 queries, magic numbers, patterns |
+| Feedback Examples | `references/feedback-examples.md` | Writing good feedback |
+| Report Template | `references/report-template.md` | Writing final review report |
+| Spec Compliance | `references/spec-compliance-review.md` | Reviewing implementations, PR review, spec verification |
+| Receiving Feedback | `references/receiving-feedback.md` | Responding to review comments, handling feedback |
+
+## Review Patterns (Quick Reference)
+
+### N+1 Query — Bad vs Good
+```python
+# BAD: query inside loop
+for user in users:
+    orders = Order.objects.filter(user=user)  # N+1
+
+# GOOD: prefetch in bulk
+users = User.objects.prefetch_related('orders').all()
+```
+
+### Magic Number — Bad vs Good
+```python
+# BAD
+if status == 3:
+    ...
+
+# GOOD
+ORDER_STATUS_SHIPPED = 3
+if status == ORDER_STATUS_SHIPPED:
+    ...
+```
+
+### Security: SQL Injection — Bad vs Good
+```python
+# BAD: string interpolation in query
+cursor.execute(f"SELECT * FROM users WHERE id = {user_id}")
+
+# GOOD: parameterized query
+cursor.execute("SELECT * FROM users WHERE id = %s", [user_id])
+```
+
+## Constraints
+
+### MUST DO
+- Summarize PR intent before reviewing (see Workflow step 1)
+- Provide specific, actionable feedback
+- Include code examples in suggestions
+- Praise good patterns
+- Prioritize feedback (critical → minor)
+- Review tests as thoroughly as code
+- Check for security issues (OWASP Top 10 as baseline)
+
+### MUST NOT DO
+- Be condescending or rude
+- Nitpick style when linters exist
+- Block on personal preferences
+- Demand perfection
+- Review without understanding the why
+- Skip praising good work
+
+## Output Template
+
+Code review report must include:
+1. **Summary** — One-sentence intent recap + overall assessment
+2. **Critical issues** — Must fix before merge (bugs, security, data loss)
+3. **Major issues** — Should fix (performance, design, maintainability)
+4. **Minor issues** — Nice to have (naming, readability)
+5. **Positive feedback** — Specific patterns done well
+6. **Questions for author** — Clarifications needed
+7. **Verdict** — Approve / Request Changes / Comment
+
+## Knowledge Reference
+
+SOLID, DRY, KISS, YAGNI, design patterns, OWASP Top 10, language idioms, testing patterns

package/skills/quality/code-reviewer/references/common-issues.md

@@ -0,0 +1,142 @@
+# Common Issues
+
+## N+1 Query Problem
+
+```typescript
+// N+1 queries - BAD
+const posts = await Post.findAll();
+for (const post of posts) {
+  post.author = await User.findById(post.authorId); // N queries!
+}
+
+// Single query with join - GOOD
+const posts = await Post.findAll({ include: [User] });
+
+// Or batch load
+const posts = await Post.findAll();
+const authorIds = posts.map(p => p.authorId);
+const authors = await User.findByIds(authorIds);
+```
+
+## Missing Error Handling
+
+```typescript
+// Unhandled rejection - BAD
+const data = await fetch('/api/data').then(r => r.json());
+
+// Proper error handling - GOOD
+try {
+  const response = await fetch('/api/data');
+  if (!response.ok) {
+    throw new Error(`HTTP ${response.status}`);
+  }
+  const data = await response.json();
+} catch (error) {
+  logger.error('Failed to fetch data', { error });
+  throw new DataFetchError('Could not load data');
+}
+```
+
+## Magic Numbers/Strings
+
+```typescript
+// Magic number - BAD
+if (user.age >= 18) { ... }
+setTimeout(fn, 86400000);
+
+// Named constant - GOOD
+const MINIMUM_AGE = 18;
+const ONE_DAY_MS = 24 * 60 * 60 * 1000;
+
+if (user.age >= MINIMUM_AGE) { ... }
+setTimeout(fn, ONE_DAY_MS);
+```
+
+## Deep Nesting
+
+```typescript
+// Deep nesting - BAD
+if (user) {
+  if (user.isActive) {
+    if (user.hasPermission) {
+      doSomething();
+    }
+  }
+}
+
+// Early returns - GOOD
+if (!user || !user.isActive || !user.hasPermission) {
+  return;
+}
+doSomething();
+```
+
+## God Functions
+
+```typescript
+// Does too much - BAD
+async function processOrder(order) {
+  // validate
+  // check inventory
+  // process payment
+  // send email
+  // update database
+  // log analytics
+}
+
+// Single responsibility - GOOD
+async function processOrder(order) {
+  await validateOrder(order);
+  await reserveInventory(order);
+  await chargePayment(order);
+  await sendConfirmation(order);
+}
+```
+
+## Mutable Shared State
+
+```typescript
+// Shared mutable - BAD
+const config = { debug: false };
+function enableDebug() {
+  config.debug = true;
+}
+
+// Immutable pattern - GOOD
+function createConfig(overrides = {}) {
+  return Object.freeze({ debug: false, ...overrides });
+}
+```
+
+## Missing Null Checks
+
+```typescript
+// Unsafe access - BAD
+const name = user.profile.name;
+
+// Safe access - GOOD
+const name = user?.profile?.name ?? 'Unknown';
+```
+
+## Synchronous File Operations
+
+```typescript
+// Blocks event loop - BAD
+const data = fs.readFileSync('file.txt');
+
+// Non-blocking - GOOD
+const data = await fs.promises.readFile('file.txt');
+```
+
+## Quick Reference
+
+| Issue | Impact | Fix |
+|-------|--------|-----|
+| N+1 queries | Performance | Eager load or batch |
+| Missing error handling | Reliability | Try/catch + logging |
+| Magic numbers | Maintainability | Named constants |
+| Deep nesting | Readability | Early returns |
+| God functions | Testability | Single responsibility |
+| Mutable shared state | Bugs | Immutable patterns |
+| Missing null checks | Crashes | Optional chaining |
+| Sync file operations | Performance | Async operations |