@su-record/vibe 2.7.8 → 2.7.9

package/skills/techdebt/SKILL.md

@@ -1,122 +1,122 @@
----
-name: techdebt
-description: "Technical debt cleanup — detect and fix duplicate code, console.log, unused imports, any types, etc. Recommended before session end. Activates on techdebt, cleanup, debt keywords."
-triggers: [techdebt, cleanup, debt, unused imports, console.log, dead code]
-priority: 60
----
-
-# Techdebt — Technical Debt Cleanup
-
-Detect and clean up technical debt in the codebase before session end or periodically.
-
-## Inspection Items
-
-### 1. Duplicate Code
-
-- Check for similar functions/logic across multiple files
-- Identify code extractable into common utilities
-- Method: Detect similar code with `core_analyze_complexity`
-
-### 2. Unused Code
-
-- Unused import statements
-- Unused variables/functions
-- Commented-out code blocks
-
-Detection tools:
-
-```
-# Detect unused imports (using Grep tool)
-Grep: pattern="^import .+ from" → cross-reference usage
-
-# Detect commented-out code blocks
-Grep: pattern="^\\s*//.*\\b(function|const|let|var|class|import)\\b"
-```
-
-### 3. Debug Code
-
-- `console.log` / `console.error` / `console.warn`
-- `debugger` statements
-- Temporary comments: `// TODO`, `// FIXME`, `// HACK`, `// XXX`
-
-Detection tools:
-
-```
-# Detect console statements (using Grep tool)
-Grep: pattern="console\\.(log|error|warn|debug)" glob="*.{ts,tsx}"
-
-# Detect TODO/FIXME
-Grep: pattern="(TODO|FIXME|HACK|XXX)" glob="*.{ts,tsx}"
-
-# Detect debugger statements
-Grep: pattern="\\bdebugger\\b" glob="*.{ts,tsx}"
-```
-
-### 4. Code Quality
-
-- `any` type usage (TypeScript)
-- Hardcoded values (magic numbers/strings)
-- Functions exceeding 50 lines
-- Nesting deeper than 4 levels
-
-Detection tools:
-
-```
-# Detect any types (using Grep tool)
-Grep: pattern=": any\\b|as any\\b" glob="*.{ts,tsx}"
-
-# Analyze complexity with built-in VIBE tools
-core_analyze_complexity: filePath="src/**/*.ts"
-core_validate_code_quality: filePath="src/**/*.ts"
-```
-
-## Output Format
-
-```markdown
-## Technical Debt Report
-
-### Duplicate Code (N items)
-- src/utils.ts:formatDate ↔ src/helpers.ts:formatDateTime
-
-### Unused Imports (N items)
-- src/components/Button.tsx:3 — React (unused)
-
-### Debug Code (N items)
-- src/api/auth.ts:23 — console.log
-
-### Code Quality Issues (N items)
-- src/services/user.ts:45 — any type usage
-- src/utils/calc.ts:10 — magic number (hardcoded 365)
-
-Total: N technical debt items found.
-```
-
-## Auto-fix Scope
-
-### Auto-fixable (Safe)
-
-| Item | Fix Method |
-|------|-----------|
-| Unused imports | Delete the import statement |
-| `console.log` / `debugger` | Delete the line |
-| Trailing whitespace / blank lines | Apply formatter |
-
-### Requires Manual Review (Safety Guard)
-
-| Item | Reason |
-|------|--------|
-| Duplicate code extraction | Need to verify logic equivalence |
-| `any` type fixes | Need proper type design |
-| Magic number extraction | Need to decide constant names and locations |
-| Long function splitting | Need to decide logic separation criteria |
-
-> Always show the scope of changes to the user and get confirmation before auto-fixing.
-
-## VIBE Tool Integration
-
-| Tool | Purpose |
-|------|---------|
-| `core_analyze_complexity` | Measure function complexity (nesting, line count) |
-| `core_validate_code_quality` | Detect code quality rule violations |
-| `core_suggest_improvements` | Generate improvement suggestions |
-| `core_check_coupling_cohesion` | Analyze module coupling/cohesion |
+---
+name: techdebt
+description: "Technical debt cleanup — detect and fix duplicate code, console.log, unused imports, any types, etc. Recommended before session end. Activates on techdebt, cleanup, debt keywords."
+triggers: [techdebt, cleanup, debt, unused imports, console.log, dead code]
+priority: 60
+---
+
+# Techdebt — Technical Debt Cleanup
+
+Detect and clean up technical debt in the codebase before session end or periodically.
+
+## Inspection Items
+
+### 1. Duplicate Code
+
+- Check for similar functions/logic across multiple files
+- Identify code extractable into common utilities
+- Method: Detect similar code with `core_analyze_complexity`
+
+### 2. Unused Code
+
+- Unused import statements
+- Unused variables/functions
+- Commented-out code blocks
+
+Detection tools:
+
+```
+# Detect unused imports (using Grep tool)
+Grep: pattern="^import .+ from" → cross-reference usage
+
+# Detect commented-out code blocks
+Grep: pattern="^\\s*//.*\\b(function|const|let|var|class|import)\\b"
+```
+
+### 3. Debug Code
+
+- `console.log` / `console.error` / `console.warn`
+- `debugger` statements
+- Temporary comments: `// TODO`, `// FIXME`, `// HACK`, `// XXX`
+
+Detection tools:
+
+```
+# Detect console statements (using Grep tool)
+Grep: pattern="console\\.(log|error|warn|debug)" glob="*.{ts,tsx}"
+
+# Detect TODO/FIXME
+Grep: pattern="(TODO|FIXME|HACK|XXX)" glob="*.{ts,tsx}"
+
+# Detect debugger statements
+Grep: pattern="\\bdebugger\\b" glob="*.{ts,tsx}"
+```
+
+### 4. Code Quality
+
+- `any` type usage (TypeScript)
+- Hardcoded values (magic numbers/strings)
+- Functions exceeding 50 lines
+- Nesting deeper than 4 levels
+
+Detection tools:
+
+```
+# Detect any types (using Grep tool)
+Grep: pattern=": any\\b|as any\\b" glob="*.{ts,tsx}"
+
+# Analyze complexity with built-in VIBE tools
+core_analyze_complexity: filePath="src/**/*.ts"
+core_validate_code_quality: filePath="src/**/*.ts"
+```
+
+## Output Format
+
+```markdown
+## Technical Debt Report
+
+### Duplicate Code (N items)
+- src/utils.ts:formatDate ↔ src/helpers.ts:formatDateTime
+
+### Unused Imports (N items)
+- src/components/Button.tsx:3 — React (unused)
+
+### Debug Code (N items)
+- src/api/auth.ts:23 — console.log
+
+### Code Quality Issues (N items)
+- src/services/user.ts:45 — any type usage
+- src/utils/calc.ts:10 — magic number (hardcoded 365)
+
+Total: N technical debt items found.
+```
+
+## Auto-fix Scope
+
+### Auto-fixable (Safe)
+
+| Item | Fix Method |
+|------|-----------|
+| Unused imports | Delete the import statement |
+| `console.log` / `debugger` | Delete the line |
+| Trailing whitespace / blank lines | Apply formatter |
+
+### Requires Manual Review (Safety Guard)
+
+| Item | Reason |
+|------|--------|
+| Duplicate code extraction | Need to verify logic equivalence |
+| `any` type fixes | Need proper type design |
+| Magic number extraction | Need to decide constant names and locations |
+| Long function splitting | Need to decide logic separation criteria |
+
+> Always show the scope of changes to the user and get confirmation before auto-fixing.
+
+## VIBE Tool Integration
+
+| Tool | Purpose |
+|------|---------|
+| `core_analyze_complexity` | Measure function complexity (nesting, line count) |
+| `core_validate_code_quality` | Detect code quality rule violations |
+| `core_suggest_improvements` | Generate improvement suggestions |
+| `core_check_coupling_cohesion` | Analyze module coupling/cohesion |

package/skills/tool-fallback/SKILL.md

@@ -1,193 +1,103 @@
----
-name: tool-fallback
-description: "Tool failure fallback strategies with circuit breaker. Auto-activates on API errors, search failures, timeouts, 429, 5xx, overloaded errors."
-triggers: [API error, search failure, timeout, 429, 5xx, overloaded, fallback, circuit breaker]
-priority: 80
----
-# Tool Fallback Strategies
-
-Guide for finding alternatives when tools fail to continue work.
-
-## Circuit Breaker Pattern
-
-Track tool failures and temporarily disable unreliable tools:
-
-```
-Tool State Machine:
-┌─────────┐   3 failures   ┌─────────┐   30s cooldown   ┌─────────────┐
-│ CLOSED  │ ─────────────→ │  OPEN   │ ───────────────→ │ HALF-OPEN   │
-│ (normal)│                │ (block) │                  │ (test 1 req)│
-└─────────┘                └─────────┘                  └─────────────┘
-     ↑                                                        │
-     │                      success                           │
-     └────────────────────────────────────────────────────────┘
-```
-
-| State | Behavior |
-|-------|----------|
-| **CLOSED** | Normal operation, count failures |
-| **OPEN** | Block all requests, use alternative immediately |
-| **HALF-OPEN** | Allow 1 test request after cooldown |
-
-**Per-tool tracking:**
-```
-GPT hook: failures=2, state=CLOSED
-Gemini hook: failures=0, state=CLOSED
-WebSearch: failures=3, state=OPEN (blocked until 14:32:00)
-context7: failures=1, state=CLOSED
-```
-
-## When Web Search Fails
-
-| Alternative | Method |
-|-------------|--------|
-| context7 plugin | `resolve-library-id` → `get-library-docs` |
-| VibeOrchestrator | `smartWebSearch()` - auto fallback chain |
-| Cached knowledge | Use Claude's built-in knowledge |
-
-```
-Web Search fails (429, 529, timeout)
-    ↓
-Check circuit breaker state
-    ↓
-If OPEN → Skip to alternative immediately
-    ↓
-If CLOSED → Try context7 for library docs
-    ↓
-If still fails: VibeOrchestrator.smartWebSearch()
-    ↓
-Last resort: Claude's built-in knowledge
-```
-
-## API Error Responses
-
-| Error | Cause | Response | Circuit Breaker |
-|-------|-------|----------|-----------------|
-| 429 | Rate Limit | Exponential backoff | +1 failure count |
-| 5xx | Server Error | Switch to alternative | +1 failure count |
-| 529 | Overloaded | Wait and retry | +1 failure count |
-| Timeout | Network | Split request or retry | +1 failure count |
-| 401/403 | Auth Error | Re-auth or alternative | Don't count (auth issue) |
-
-## When File/Code Not Found
-
-```
-Glob fails
-    ↓
-Expand pattern: *.ts → **/*.ts → **/*
-    ↓
-Use Grep for content-based search
-    ↓
-Check git log for history
-```
-
-## When External LLM Fails
-
-**Production (VibeOrchestrator):**
-
-```
-VibeOrchestrator.smartRoute({ type, prompt })
-    ↓
-LLM priority based on task type:
-  - architecture/debugging: GPT → Gemini → Claude
-  - uiux/code-analysis: Gemini → GPT → Claude
-  - code-gen: Claude only
-    ↓
-Auto fallback on primary LLM failure
-    ↓
-Claude handles directly when all fail
-```
-
-**Test/Debug Hooks (development only):**
-
-```
-gpt- or gpt. [question] fails
-    ↓
-Check circuit: If OPEN, skip to next
-    ↓
-Try gemini- or gemini. [question] (similar capability)
-    ↓
-Try context7 (for docs)
-    ↓
-Claude solves alone
-```
-
-> **Note:** `test-gpt`, `test-gemini` prefixes are for hook connectivity testing only.
-> For actual work, use VIBE commands (`/vibe.run`, `/vibe.spec`, etc.) and
-> VibeOrchestrator will automatically select the appropriate LLM.
-
-## Retry Strategy with Circuit Breaker
-
-```
-Request to tool
-    ↓
-Check circuit state
-    ↓
-┌─ OPEN? ──→ Use alternative immediately (no retry)
-│
-└─ CLOSED/HALF-OPEN? ──→ Try request
-                              ↓
-                         Success? ──→ Reset failure count
-                              ↓ No
-                         Retry with backoff:
-                           retry(1): wait 2s
-                           retry(2): wait 4s
-                           retry(3): wait 8s
-                              ↓
-                         All failed? ──→ +1 failure, check threshold
-                              ↓
-                         failures >= 3? ──→ OPEN circuit for 30s
-                              ↓
-                         Use alternative
-```
-
-## VibeOrchestrator Smart Routing
-
-VIBE commands (`/vibe.spec`, `/vibe.run`, etc.) use VibeOrchestrator internally.
-
-### LLM Priority by Task Type
-
-| Task Type       | Primary | Secondary | Fallback |
-|-----------------|---------|-----------|----------|
-| `architecture`  | GPT     | Gemini    | Claude   |
-| `debugging`     | GPT     | Gemini    | Claude   |
-| `uiux`          | Gemini  | GPT       | Claude   |
-| `code-analysis` | Gemini  | GPT       | Claude   |
-| `web-search`    | GPT     | Gemini    | Claude   |
-| `code-gen`      | Claude  | -         | -        |
-| `general`       | Claude  | -         | -        |
-
-### Auto Fallback Logic
-
-```
-smartRoute({ type: 'architecture', prompt })
-    ↓
-1. Try GPT (max 2 retries)
-    ↓ fails (429, 401, 5xx)
-2. Try Gemini (max 2 retries)
-    ↓ fails
-3. Claude handles directly (fallback message)
-```
-
-### Retry vs Immediate Switch
-
-| Error            | Action                 |
-|------------------|------------------------|
-| 429 Rate Limit   | Skip to next LLM       |
-| 401/403 Auth     | Skip to next LLM       |
-| Network Error    | Retry with backoff     |
-| 5xx Server Error | Retry then switch      |
-
-### Availability Cache
-
-- 5-minute TTL for LLM status cache
-- Auto-disable after 3 consecutive failures
-- Failed LLMs are skipped in subsequent requests
-
-## Principles
-
-1. **Never stop** - Always find an alternative
-2. **Before asking user** - Try alternatives first
-3. **Track failures** - Open circuit after 3 consecutive failures
-4. **Auto-recover** - Test after 30s cooldown
-5. **Fail fast** - Skip blocked tools immediately
+---
+name: tool-fallback
+description: "Tool failure fallback strategies with circuit breaker. Auto-activates on API errors, search failures, timeouts, 429, 5xx, overloaded errors."
+triggers: [API error, search failure, timeout, 429, 5xx, overloaded, fallback, circuit breaker]
+priority: 80
+---
+
+# Tool Fallback Strategies
+
+## Pre-check (K1)
+
+> Did a tool just fail? If the error is a simple typo or wrong path, fix the input first. This skill is for persistent failures (429, 5xx, timeouts).
+
+## Circuit Breaker State Machine
+
+```
+┌─────────┐   3 failures   ┌─────────┐   30s cooldown   ┌─────────────┐
+│ CLOSED  │ ─────────────→ │  OPEN   │ ───────────────→ │ HALF-OPEN   │
+│ (normal)│                │ (block) │                  │ (test 1 req)│
+└─────────┘                └─────────┘                  └─────────────┘
+     ↑                                                        │
+     │                      success                           │
+     └────────────────────────────────────────────────────────┘
+```
+
+| State | Behavior |
+|-------|----------|
+| CLOSED | Normal operation, count failures |
+| OPEN | Skip tool immediately, use alternative |
+| HALF-OPEN | Allow 1 test request after cooldown |
+
+## Decision Trees
+
+### Web Search Fails
+
+```
+Web Search fails (429, 529, timeout)
+  → Check circuit state
+  → OPEN? → Skip to alternative immediately
+  → CLOSED? → Try context7 for library docs
+  → Still fails? → Claude's built-in knowledge (last resort)
+```
+
+### External LLM Fails
+
+```
+VibeOrchestrator.smartRoute({ type, prompt })
+  → Primary LLM fails (429, 401, 5xx)
+  → Skip to secondary LLM (no retry on rate limit)
+  → Secondary fails → Claude handles directly
+```
+
+### File/Code Not Found
+
+```
+Glob fails → Expand pattern: *.ts → **/*.ts → **/*
+  → Use Grep for content-based search
+  → Check git log for file history
+```
+
+## Error Response Actions
+
+| Error | Action | Circuit Impact |
+|-------|--------|---------------|
+| 429 Rate Limit | Skip to next alternative (don't retry) | +1 failure |
+| 5xx Server Error | Retry with backoff, then switch | +1 failure |
+| 529 Overloaded | Wait and retry once | +1 failure |
+| Timeout | Split request or retry | +1 failure |
+| 401/403 Auth | Re-auth or switch alternative | Don't count |
+
+## Retry Strategy
+
+```
+Request → Check circuit
+  ├─ OPEN → Use alternative immediately
+  └─ CLOSED/HALF-OPEN → Try request
+       ├─ Success → Reset failure count
+       └─ Fail → Backoff (2s → 4s → 8s)
+            └─ All retries failed → +1 failure
+                 └─ failures ≥ 3 → OPEN circuit (30s)
+                      └─ Use alternative
+```
+
+## LLM Priority by Task Type
+
+| Task Type | Primary → Secondary → Fallback |
+|-----------|-------------------------------|
+| architecture, debugging | GPT → Gemini → Claude |
+| uiux, code-analysis | Gemini → GPT → Claude |
+| code-gen, general | Claude only |
+
+## Principles
+
+1. **Never stop** — always find an alternative
+2. **Try before asking** — exhaust alternatives before asking user
+3. **Fail fast** — skip OPEN-circuit tools immediately
+4. **Auto-recover** — test after 30s cooldown
+
+## Done Criteria (K4)
+
+- [ ] Work continued despite tool failure
+- [ ] Alternative tool/method used successfully
+- [ ] No unnecessary retries on rate-limited tools