@agentskillkit/agent-skills 1.0.1 → 3.2.2

package/.agent/workflows/diagnose.md

@@ -1,5 +1,6 @@
 ---
 description: Root cause detective. Hypothesis-driven debugging with evidence-based verification.
+chain: debug-complex
 ---
 
 # /diagnose - Root Cause Detective
@@ -14,9 +15,31 @@ Systematic debugging using scientific method. **Form hypotheses, gather evidence
 
 ---
 
+## 🤖 Meta-Agents Integration
+
+| Phase | Agent | Action |
+| ----- | ----- | ------ |
+| **Pre-Debug** | `recovery` | Save state before debugging changes |
+| **Hypothesis** | `learner` | Check past bug patterns for similar issues |
+| **Investigation** | `assessor` | Evaluate fix risk before applying |
+| **Post-Fix** | `learner` | Log root cause for future reference |
+| **On Failure** | `recovery` | Restore if debugging makes things worse |
+
+```
+Flow:
+recovery.save() → learner.check(past_bugs)
+       ↓
+hypotheses → test → found? → assessor.evaluate(fix)
+       ↓
+apply fix → learner.log(root_cause, fix)
+```
+
+---
+
 ## 🔴 MANDATORY: 5-Phase Investigation
 
 ### Phase 1: Symptom Collection
+
 ```
 GATHER:
 □ Exact error message (copy/paste)
@@ -28,27 +51,32 @@ GATHER:
 ```
 
 ### Phase 2: Hypothesis Formation
+
 Generate 3+ ranked hypotheses:
 
-| # | Hypothesis | Likelihood | Test Method |
-|---|------------|------------|-------------|
-| 1 | [Most likely cause] | 70% | [How to verify] |
-| 2 | [Second possibility] | 20% | [How to verify] |
-| 3 | [Edge case] | 10% | [How to verify] |
+| #   | Hypothesis           | Likelihood | Test Method     |
+| --- | -------------------- | ---------- | --------------- |
+| 1   | [Most likely cause]  | 70%        | [How to verify] |
+| 2   | [Second possibility] | 20%        | [How to verify] |
+| 3   | [Edge case]          | 10%        | [How to verify] |
 
 ### Phase 3: Evidence Gathering
+
 // turbo
+
 ```bash
 # Run code analysis
-python .agent/scripts/checklist.py .
+node .agent/scripts-js/checklist.js .
+# OR: npm run checklist:js .
 
-# Check for security issues
-python .agent/skills/vulnerability-scanner/scripts/security_scan.py .
+# Check for security issues (Python skill script - still valid)
+python .agent/skills/security-scanner/scripts/security_scan.py .
 ```
 
 ### Phase 4: Systematic Elimination
 
 For each hypothesis:
+
 1. Define the TEST
 2. Predict the OUTCOME if hypothesis is true
 3. Run the test
@@ -59,12 +87,15 @@ For each hypothesis:
 
 ```markdown
 ## Root Cause Confirmed
+
 [Clear explanation]
 
 ## Fix Applied
+
 [Code changes with before/after]
 
 ## Prevention Measures
+
 - [ ] Add test case for this scenario
 - [ ] Add input validation
 - [ ] Update documentation
@@ -75,35 +106,38 @@ For each hypothesis:
 
 ## Output Format
 
-```markdown
+````markdown
 ## 🔍 Diagnosis: [Issue Title]
 
 ### Symptom
+
 > [User's description of the problem]
 
 ### Environment
-| Aspect | Value |
-|--------|-------|
-| File | `src/services/auth.ts` |
-| Line | 42 |
-| Environment | Development |
-| Last Working | 2 commits ago |
+
+| Aspect       | Value                  |
+| ------------ | ---------------------- |
+| File         | `src/services/auth.ts` |
+| Line         | 42                     |
+| Environment  | Development            |
+| Last Working | 2 commits ago          |
 
 ---
 
 ### Hypotheses
 
-| # | Hypothesis | Likelihood | Status |
-|---|------------|------------|--------|
-| 1 | Null reference in user object | 70% | ✅ CONFIRMED |
-| 2 | API timeout | 20% | ❌ Eliminated |
-| 3 | Cache stale data | 10% | ⏳ Not tested |
+| #   | Hypothesis                    | Likelihood | Status        |
+| --- | ----------------------------- | ---------- | ------------- |
+| 1   | Null reference in user object | 70%        | ✅ CONFIRMED  |
+| 2   | API timeout                   | 20%        | ❌ Eliminated |
+| 3   | Cache stale data              | 10%        | ⏳ Not tested |
 
 ---
 
 ### Investigation Log
 
 **Testing H1: Null reference**
+
 - Test: Add console.log before line 42
 - Prediction: user.id will be undefined
 - Result: ✅ user was null when not logged in
@@ -112,6 +146,7 @@ For each hypothesis:
 ---
 
 ### Root Cause
+
 🎯 **user object is null when accessing protected route without auth**
 
 The `getUser()` function returns null for unauthenticated requests, but the code assumes it always returns a user object.
@@ -124,12 +159,13 @@ The `getUser()` function returns null for unauthenticated requests, but the code
 // ❌ Before
 const userId = user.id;
 
-// ✅ After  
+// ✅ After
 if (!user) {
-  throw new AuthError('User not authenticated');
+  throw new AuthError("User not authenticated");
 }
 const userId = user.id;
 ```
+````
 
 ---
 
@@ -143,11 +179,14 @@ const userId = user.id;
 ---
 
 ### Verification
-// turbo
+
 Run tests to confirm fix:
+// turbo
+
 ```bash
 npm test -- --grep "auth"
 ```
+
 ```
 
 ---
@@ -155,12 +194,14 @@ npm test -- --grep "auth"
 ## Examples
 
 ```
+
 /diagnose login returns 401 even with correct credentials
 /diagnose form data not saving to database
 /diagnose page crashes on mobile Safari
 /diagnose API response is 10x slower since yesterday
 /diagnose deployment fails on Vercel
-```
+
+````
 
 ---
 
@@ -193,15 +234,16 @@ graph LR
     A["/diagnose"] --> B["/validate"]
     B --> C["/launch"]
     style A fill:#ef4444
-```
+````
 
-| After /diagnose | Run | Purpose |
-|-----------------|-----|---------|
-| Bug fixed | `/validate` | Verify fix |
-| Need tests | `/validate` | Add test case |
-| Ready | `/launch` | Deploy fix |
+| After /diagnose | Run         | Purpose       |
+| --------------- | ----------- | ------------- |
+| Bug fixed       | `/validate` | Verify fix    |
+| Need tests      | `/validate` | Add test case |
+| Ready           | `/launch`   | Deploy fix    |
 
 **Handoff to /validate:**
+
 ```markdown
 Bug fixed. Run /validate to verify the fix works.
 ```

package/.agent/workflows/diagram.md

@@ -0,0 +1,121 @@
+---
+description: Auto-generate C4, Mermaid, and ER diagrams from codebase. Keep architecture docs in sync with code.
+---
+
+# Architecture Diagram Generation
+
+Create and update architecture diagrams from code.
+
+## 🎯 Purpose
+
+This workflow uses the **system-design** skill to:
+
+- Generate C4 diagrams (Context, Container)
+- Create sequence diagrams
+- Generate ER diagrams from Prisma schema
+- Update diagrams when code changes
+
+## 🤖 Meta-Agents Integration
+
+| Phase | Agent | Action |
+| ----- | ----- | ------ |
+| **Pre-Generate** | `learner` | Recall diagram conventions |
+| **Post-Generate** | `learner` | Log diagram patterns for reuse |
+
+---
+
+## 🔗 Chain: documentation (system-design skill only)
+
+**Skills Loaded (1):**
+
+- `system-design` - C4, Mermaid, ER diagrams
+
+## 📖 Usage
+
+```bash
+/diagram <scope>
+```
+
+### Examples
+
+```bash
+# Generate all diagrams
+/diagram generate
+
+# Update existing diagrams
+/diagram update
+
+# Specific diagram type
+/diagram c4-context
+```
+
+## 🔄 Workflow Steps
+
+1. **Analyze Codebase**
+   - Scan project structure
+   - Detect services and dependencies
+   - Parse Prisma schema
+
+2. **Generate Diagrams**
+   - C4 Context diagram
+   - C4 Container diagram
+   - Sequence diagrams (key flows)
+   - ER diagram from schema
+
+3. **Save to docs/**
+   - `docs/diagrams/context.mmd`
+   - `docs/diagrams/container.mmd`
+   - `docs/diagrams/er.mmd`
+
+## ✅ Success Criteria
+
+✓ **Diagrams Created** - C4, sequence, ER  
+✓ **Auto-update** - Synced with code  
+✓ **Mermaid Format** - Renderable in GitHub/docs
+
+## 📊 Diagram Types
+
+| Diagram      | Purpose             | Auto-detects      |
+| ------------ | ------------------- | ----------------- |
+| C4 Context   | System overview     | External services |
+| C4 Container | Internal components | App structure     |
+| Sequence     | User flows          | API calls         |
+| ER           | Database schema     | Prisma models     |
+
+## 🔍 Related Workflows
+
+- `/chronicle` - Generate all documentation
+- `/build` - Create app first
+- `/api` - Create API then diagram
+
+## 💡 Example Output
+
+```bash
+You: "/diagram update"
+
+Agent: Loading system-design
+       ↓
+
+[1/1] 🏗️ Updating Diagrams
+
+   Scanning codebase...
+   ✅ Detected schema changes (2 new tables)
+   ✅ Updated ER diagram
+   ✅ Updated C4 Container diagram
+   ✅ All diagrams in sync with code
+
+📂 Updated: docs/diagrams/
+   - context.mmd
+   - container.mmd
+   - er.mmd
+   - sequence-auth.mmd
+
+✅ Diagrams updated!
+```
+
+---
+
+**Version:** 1.0.0  
+**Chain:** documentation (system-design)  
+**Added:** v3.6.0 (FAANG upgrade - Phase 3)
+

package/.agent/workflows/flags.md

@@ -0,0 +1,149 @@
+---
+description: Feature flag management for A/B testing and gradual rollouts. Control features without code deploys.
+---
+
+# /flags - Feature Flag Manager
+
+$ARGUMENTS
+
+---
+
+## Purpose
+
+Manage feature flags for A/B testing, gradual rollouts, and kill switches. **Toggle features without redeploying.**
+
+---
+
+## 🤖 Meta-Agents Integration
+
+| Phase | Agent | Action |
+| ----- | ----- | ------ |
+| **Rollout Planning** | `assessor` | Evaluate risk of feature rollout |
+| **State Backup** | `recovery` | Save flag state before changes |
+| **A/B Learning** | `learner` | Learn from rollout success/failure patterns |
+| **On Issues** | `recovery` | Quick rollback via kill switch |
+
+```
+Flow:
+assessor.evaluate(rollout_risk) → safe %?
+       ↓
+recovery.save(flag_state) → enable flag
+       ↓
+monitor → issues? → recovery.restore() → learner.log()
+       ↓
+success → learner.log(pattern)
+```
+
+---
+
+## Commands
+
+| Command                              | Action                        |
+| ------------------------------------ | ----------------------------- |
+| `/flags`                             | Interactive flag manager      |
+| `/flags list`                        | List all flags                |
+| `/flags enable <name>`               | Enable a flag                 |
+| `/flags disable <name>`              | Disable a flag                |
+| `/flags rollout <name> <percentage>` | Set rollout percentage        |
+| `/flags create <name>`               | Create new flag               |
+| `/flags status <name>`               | Show flag details             |
+| `/flags init`                        | Initialize .featureflags.json |
+
+---
+
+## Quick Start
+
+### 1. Initialize
+
+// turbo
+
+```bash
+node .agent/skills/cicd-pipeline/scripts/flag-manager.js init
+```
+
+### 2. List Flags
+
+// turbo
+
+```bash
+node .agent/skills/cicd-pipeline/scripts/flag-manager.js list
+```
+
+### 3. Enable/Disable
+
+```bash
+node .agent/skills/cicd-pipeline/scripts/flag-manager.js enable new-checkout
+node .agent/skills/cicd-pipeline/scripts/flag-manager.js disable maintenance-mode
+```
+
+### 4. Gradual Rollout
+
+```bash
+node .agent/skills/cicd-pipeline/scripts/flag-manager.js set new-feature --percentage 25
+```
+
+---
+
+## Integration
+
+### React
+
+```tsx
+import { useFeatureFlag } from "@/flags";
+
+function App() {
+  const showNew = useFeatureFlag("new-feature");
+  return showNew ? <NewVersion /> : <OldVersion />;
+}
+```
+
+### Node.js/Express
+
+```javascript
+import { isEnabled } from "./flags";
+
+app.get("/api/checkout", (req, res) => {
+  if (isEnabled("new-checkout", { userId: req.user.id })) {
+    return newCheckout(req, res);
+  }
+  return oldCheckout(req, res);
+});
+```
+
+---
+
+## Configuration
+
+File: `.featureflags.json`
+
+```json
+{
+  "flags": {
+    "new-checkout": {
+      "enabled": true,
+      "percentage": 50,
+      "groups": ["beta-users"]
+    }
+  }
+}
+```
+
+---
+
+## Best Practices
+
+1. **Name clearly** - `new-checkout-flow` not `flag1`
+2. **Add descriptions** - Future you will thank you
+3. **Clean up** - Remove flags after 100% rollout
+4. **Test both states** - Ensure code works with flag on/off
+
+---
+
+## 🔗 Related
+
+| Workflow    | Purpose           |
+| ----------- | ----------------- |
+| `/launch`   | Deploy with flags |
+| `/validate` | Test flag states  |
+| `/diagnose` | Debug flag issues |
+

package/.agent/workflows/forge.md

@@ -14,6 +14,16 @@ Create, validate, and package Agent Skills following best practices. **Uses prog
 
 ---
 
+## 🤖 Meta-Agents Integration
+
+| Phase | Agent | Action |
+| ----- | ----- | ------ |
+| **Pre-Create** | `learner` | Analyze existing skill patterns |
+| **Validation** | `assessor` | Evaluate skill quality and completeness |
+| **Post-Create** | `learner` | Log new skill patterns for future reference |
+
+---
+
 ## Sub-commands
 
 ```
@@ -29,7 +39,7 @@ Create, validate, and package Agent Skills following best practices. **Uses prog
 ### 1. Create New Skill
 // turbo
 ```bash
-python .agent/skills/skill-creator/scripts/init_skill.py <skill-name> --path .agent/skills/
+python .agent/skills/skill-forge/scripts/init_skill.py <skill-name> --path .agent/skills/
 ```
 
 This creates:
@@ -54,7 +64,7 @@ This creates:
 ### 3. Validate Skill
 // turbo
 ```bash
-python .agent/skills/skill-creator/scripts/quick_validate.py .agent/skills/<skill-name>
+python .agent/skills/skill-forge/scripts/quick_validate.py .agent/skills/<skill-name>
 ```
 
 Checks:
@@ -66,7 +76,7 @@ Checks:
 ### 4. Package for Distribution
 // turbo
 ```bash
-python .agent/skills/skill-creator/scripts/package_skill.py .agent/skills/<skill-name>
+python .agent/skills/skill-forge/scripts/package_skill.py .agent/skills/<skill-name>
 ```
 
 Creates a distributable zip file.
@@ -99,8 +109,8 @@ graph TD
 
 ## Related Skills
 
-- `skill-creator` - Full skill creation guide
-- `context-engineering` - Context optimization principles
+- `SkillForge` - Full skill creation guide
+- `ContextOptimizer` - Context optimization principles
 
 ---
 

package/.agent/workflows/game.md

@@ -0,0 +1,142 @@
+---
+description: Game development workflow with platform-specific routing. From concept to polished game.
+---
+
+# Game Development Workflow
+
+> **This workflow orchestrates game development with routing to specialized sub-skills.**
+
+## Phase 1: Requirements Clarification
+
+1. **Ask critical questions:**
+   - Platform: Web, Mobile, PC, or VR/AR?
+   - Dimension: 2D or 3D?
+   - Genre: Platformer, puzzle, shooter, RPG, etc.?
+   - Multiplayer: Single-player or multiplayer?
+
+2. **Load game-development orchestrator:**
+   ```
+   Read: .agent/skills/game-development/SKILL.md
+   ```
+
+---
+
+## Phase 2: Platform Routing
+
+3. **Route to platform sub-skill:**
+
+   | Target Platform | Load Sub-skill |
+   |-----------------|----------------|
+   | Web browser | `game-development/web-games` |
+   | Mobile | `game-development/mobile-games` |
+   | PC/Desktop | `game-development/pc-games` |
+   | VR/AR | `game-development/vr-ar` |
+
+4. **Route to dimension sub-skill:**
+
+   | Dimension | Load Sub-skill |
+   |-----------|----------------|
+   | 2D (sprites) | `game-development/2d-games` |
+   | 3D (meshes) | `game-development/3d-games` |
+
+---
+
+## Phase 3: Core Game Loop
+
+5. **Implement game loop pattern:**
+   ```
+   INPUT  → Read player actions
+   UPDATE → Process game logic (fixed timestep)
+   RENDER → Draw the frame (interpolated)
+   ```
+
+6. **Apply performance budget (60 FPS = 16.67ms):**
+   | System | Budget |
+   |--------|--------|
+   | Input | 1ms |
+   | Physics | 3ms |
+   | AI | 2ms |
+   | Game Logic | 4ms |
+   | Rendering | 5ms |
+   | Buffer | 1.67ms |
+
+---
+
+## Phase 4: Specialty Areas
+
+7. **Load specialty sub-skills as needed:**
+
+   | Need | Load Sub-skill |
+   |------|----------------|
+   | Game design, balancing | `game-development/game-design` |
+   | Art, animation | `game-development/game-art` |
+   | Audio, music | `game-development/game-audio` |
+   | Networking | `game-development/multiplayer` |
+
+---
+
+## Phase 5: Pattern Selection
+
+8. **Choose patterns based on complexity:**
+
+   | Pattern | Use When |
+   |---------|----------|
+   | State Machine | 3-5 discrete states |
+   | Object Pooling | Frequent spawn/destroy |
+   | Observer/Events | Cross-system communication |
+   | ECS | Thousands of similar entities |
+   | Command | Undo, replay, networking |
+   | Behavior Tree | Complex AI decisions |
+
+   **Rule:** Start with State Machine. Add ECS only when performance demands.
+
+---
+
+## Phase 6: Input & Collision
+
+9. **Abstract input into actions:**
+   ```
+   "jump"  → Space, Gamepad A, Touch tap
+   "move"  → WASD, Left stick, Virtual joystick
+   ```
+
+10. **Choose collision strategy:**
+    | Type | Best For |
+    |------|----------|
+    | AABB | Rectangles, fast |
+    | Circle | Round objects |
+    | Spatial Hash | Many similar objects |
+    | Quadtree | Large worlds |
+
+---
+
+## Phase 7: Optimization & Testing
+
+11. **Apply optimization priority:**
+    1. Algorithm (O(n²) → O(n log n))
+    2. Batching (reduce draw calls)
+    3. Pooling (avoid GC spikes)
+    4. LOD (detail by distance)
+    5. Culling (skip invisible)
+
+12. **Test checklist:**
+    - [ ] Maintains 60 FPS
+    - [ ] No memory leaks
+    - [ ] Works on target platform
+    - [ ] Input feels responsive
+
+---
+
+## Anti-Patterns to Avoid
+
+| ❌ Don't | ✅ Do |
+|----------|-------|
+| Update everything every frame | Use events, dirty flags |
+| Create objects in hot loops | Object pooling |
+| Cache nothing | Cache references |
+| Optimize without profiling | Profile first |
+| Mix input with logic | Abstract input layer |
+
+---
+
+> **Remember:** Great games come from iteration, not perfection. Prototype fast, then polish.