@su-record/vibe 2.12.3 → 2.12.5

package/skills/spec/references/templates.md

@@ -0,0 +1,189 @@
+# SPEC / Feature Document Templates
+
+> Referenced by `spec` SKILL.md Step 4 (Write SPEC Document) and Step 5 (Create Feature File).
+> Read this file when you reach those steps — copy the matching template verbatim and fill the placeholders.
+
+## Master SPEC (`_index.md`) — Large Scope
+
+```markdown
+# SPEC: {feature-name} (Master)
+
+## Overview
+- Total phases: N
+- Dependencies: [list]
+
+## Sub-SPECs
+
+| Order | SPEC File | Feature File | Status |
+|-------|-----------|--------------|--------|
+| 1 | phase-1-setup.md | phase-1-setup.feature | ⬜ |
+| 2 | phase-2-core.md | phase-2-core.feature | ⬜ |
+
+## Shared Context
+- Tech Stack: [all phases]
+- Constraints: [all phases]
+```
+
+## Master Feature (`_index.feature`) — Large Scope
+
+```markdown
+# Feature: {feature-name} (Master)
+
+**Master SPEC**: `.vibe/specs/{feature-name}/_index.md`
+
+## Sub-Features
+
+| Order | Feature File | SPEC File | Status |
+|-------|--------------|-----------|--------|
+| 1 | phase-1-setup.feature | phase-1-setup.md | ⬜ |
+| 2 | phase-2-core.feature | phase-2-core.md | ⬜ |
+
+## Overall User Story
+**As a** {user}
+**I want** {complete feature}
+**So that** {value}
+```
+
+## Single SPEC (`.vibe/specs/{feature-name}.md`) — Small Scope
+
+```markdown
+---
+status: pending
+currentPhase: 0
+totalPhases: 3
+createdAt: {ISO-timestamp}
+lastUpdated: {ISO-timestamp}
+---
+
+# SPEC: {feature-name}
+
+## Persona
+<role>
+Define AI role and expertise for implementation
+- Senior developer on the project
+- Follow existing code patterns
+- Write testable code
+</role>
+
+## Context
+<context>
+### Background
+- Why this feature is needed
+- Who will use it
+
+### Tech Stack
+- Backend: {technology}
+- Frontend: {technology}
+- Database: {technology}
+
+### Related Code
+- `src/xxx/`: Existing implementation to reference
+- `src/yyy/`: Files to modify
+
+### Design Reference
+- {Reference app/service}
+</context>
+
+## Task
+<task>
+### Phase 1: {phase-name}
+1. [ ] {specific task}
+   - File: `path/to/file`
+   - Verify: `command`
+2. [ ] {specific task}
+
+### Phase 2: {phase-name}
+1. [ ] {specific task}
+2. [ ] {specific task}
+
+### Phase 3: Testing and Verification
+1. [ ] Unit Tests
+2. [ ] Integration Tests
+</task>
+
+## Constraints
+<constraints>
+- Follow existing code patterns
+- Localize error messages
+- Separate configuration via environment variables
+- {other constraints}
+</constraints>
+
+## Output Format
+<output_format>
+### Files to Create
+- `path/to/new/file.ts`
+- `path/to/new/file.test.ts`
+
+### Files to Modify
+- `path/to/existing/file.ts`
+
+### Verification Commands
+- `npm test`
+- `npm run build`
+</output_format>
+
+## Acceptance Criteria
+<acceptance>
+- [ ] {verifiable criterion 1}
+- [ ] {verifiable criterion 2}
+- [ ] All tests pass
+- [ ] Build succeeds
+</acceptance>
+```
+
+## Single Feature (`.vibe/features/{feature-name}.feature`) — Small Scope
+
+```markdown
+# Feature: {feature-name}
+
+**SPEC**: `.vibe/specs/{feature-name}.md`
+
+## User Story
+**As a** {user}
+**I want** {feature}
+**So that** {value}
+
+## Scenarios
+
+### Scenario 1: {Happy Path}
+\`\`\`gherkin
+Scenario: {title}
+  Given {precondition}
+  When {action}
+  Then {result}
+\`\`\`
+**Verification**: SPEC AC #1
+
+### Scenario 2: {Edge Case}
+...
+
+## Coverage
+| Scenario | SPEC AC | Status |
+|----------|---------|--------|
+| 1 | AC-1 | ⬜ |
+```
+
+## Phase Feature (`.vibe/features/{feature-name}/phase-{N}-{name}.feature`) — Large Scope
+
+```markdown
+# Feature: {feature-name} - Phase {N}: {phase-name}
+
+**SPEC**: `.vibe/specs/{feature-name}/phase-{N}-{name}.md`
+**Master Feature**: `.vibe/features/{feature-name}/_index.feature`
+
+## User Story (Phase Scope)
+**As a** {user}
+**I want** {phase-specific feature}
+**So that** {phase-specific value}
+
+## Scenarios
+
+### Scenario 1: {Phase Happy Path}
+...
+
+## Coverage
+| Scenario | SPEC AC | Status |
+|----------|---------|--------|
+| 1 | Phase {N} AC-1 | ⬜ |
+```

package/skills/test/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: test
-description: vibe 자가검진 본체 — 대상 harness(~/.claude/~/.codex)의 모든 command/skill/hook/agent 프로빙 → pass/fail 리포트 → ~/.vibe/test-reports/.
-when_to_use: /vibe.test 진입점에서 체인 호출. 직접 호출 금지.
+description: vibe 자가검진 본체 — 대상 harness(~/.claude/~/.codex)의 모든 entry skill/skill/hook/agent 프로빙 → pass/fail 리포트 → ~/.vibe/test-reports/.
+when_to_use: vibe.test 진입점에서 체인 호출. 직접 호출 금지.
 user-invocable: false
 tier: core
 ---
@@ -12,7 +12,7 @@ Probe every shipped vibe surface in one install dir and emit a pass/fail report.
 
 ## Why this exists
 
-When vibe ships new commands, skills, hooks, or agents, one side (CC or Codex) can end up out of sync with the other, frontmatter can drift, and hook tests can silently break. `/vibe.test` is the single mechanical check: does every surface in the target install actually load and pass its own tests?
+When vibe ships new entry skills, skills, hooks, or agents, one side (CC or Codex) can end up out of sync with the other, frontmatter can drift, and hook tests can silently break. `vibe.test` is the single mechanical check: does every surface in the target install actually load and pass its own tests?
 
 ## Target harness
 
@@ -37,8 +37,8 @@ All probes are **structural or test-based** — no interactive command is ever a
 
 | Category | Source | Check |
 |---|---|---|
-| commands | `<install>/commands/*.md` | file readable · frontmatter parses · `description` present · body references a skill (`Load skill \`...\``) if it delegates |
-| skills | `<install>/skills/*/SKILL.md` | frontmatter parses · required fields (`name`, `description`, `invocation`) · `invocation` ⊆ `{command, auto, chain}` and non-empty · if `invocation` includes `auto` then `triggers` non-empty · if includes `command` then matching `commands/{vibe.X}.md` or `Load skill <name>` reference exists · if includes `chain` then another skill lists it in `chain-next` · body non-empty |
+| entry skills | `<install>/skills/vibe*/SKILL.md` | file readable · frontmatter parses · `name`, `description`, `user-invocable: true` present |
+| skills | `<install>/skills/*/SKILL.md` | frontmatter parses · required fields (`name`, `description`) · body non-empty |
 | hooks | repo `hooks/scripts/*.js` | for each script with a matching `__tests__/<name>.test.js`, run `npx vitest run <test> --reporter=json` and parse pass/fail counts |
 | agents | `<install>/agents/*.md` | file readable · frontmatter parses · required fields (`name`, `description`) |
 
@@ -62,7 +62,7 @@ Written to `~/.vibe/test-reports/<YYYYMMDD-HHmm>-<harness>.{json,md}`. Exact sch
     "failed": 2
   },
   "probes": {
-    "commands": [
+    "entrySkills": [
       { "name": "vibe.spec", "status": "pass" },
       { "name": "vibe.test", "status": "pass" }
     ],
@@ -102,7 +102,7 @@ Written to `~/.vibe/test-reports/<YYYYMMDD-HHmm>-<harness>.{json,md}`. Exact sch
 
 | Category | Pass | Fail |
 |---|---:|---:|
-| commands | 15 | 0 |
+| entry skills | 15 | 0 |
 | skills   | 17 | 1 |
 | hooks    |  6 | 0 |
 | agents   |  3 | 1 |
@@ -136,5 +136,5 @@ If `failed` is empty, replace the Failures section with `_All probes passed._`.
 - [ ] JSON report matches the template above exactly (fields, types, naming)
 - [ ] Markdown summary printed to console after the run
 - [ ] Reports land in `~/.vibe/test-reports/`, never in project-local `.vibe/`
-- [ ] `failed.length > 0` → auto-invokes `/vibe.regress register --from-test`
-- [ ] `invocation` field invariants enforced per skill (`command` / `auto` / `chain` validity)
+- [ ] `failed.length > 0` → auto-invokes `vibe.regress register --from-test`
+- [ ] Entry skills are verified as user-invocable skill surfaces, not deprecated command files

package/skills/ui-ux-pro-max/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: ui-ux-pro-max
+user-invocable: true
 invocation: [command]
 tier: standard
 description: "UI/UX design intelligence with bold aesthetic direction. Searchable database: 50+ styles, 97 color palettes, 57 font pairings, 99 UX guidelines, 25 chart types across 9 stacks (React, Vue, Svelte, Angular, Astro, Next.js, Flutter, Swift, Kotlin). Use when building any UI component, choosing color schemes, selecting typography, applying design patterns, or reviewing UX compliance. Must use this skill when user builds frontend — pages, components, dashboards, or landing pages — to ensure design quality beyond generic AI output."

package/skills/vibe.run/SKILL.md

@@ -606,7 +606,7 @@ At automation levels L3 and L4, checkpoints that do not require confirmation are
 
 - `core/development-philosophy.md` - Surgical precision, modify only requested scope
 - `core/quick-start.md` - Korean, DRY, SRP, YAGNI
-- `standards/complexity-metrics.md` - Functions ≤20 lines, nesting ≤3 levels
+- `standards/complexity-metrics.md` - Functions ≤50 lines, nesting ≤3 levels
 - `quality/checklist.md` - Code quality checklist
 
 **Language guide:** `~/.claude/vibe/languages/{stack}.md` (global reference)
@@ -994,8 +994,8 @@ If implementation requires files outside scope:
 | Context Level | Action |
 |---------------|--------|
 | < 50% | Normal execution |
-| 50-70% | Save checkpoint, trim exploration results |
-| 70%+ | Save checkpoint → `/new` → resume from checkpoint |
+| 50-85% | Save checkpoint, trim exploration results |
+| 85%+ | Save checkpoint → `/new` → resume from checkpoint (`/new` discards KV prefix cache; defer it as long as safe) |
 | Phase boundary | Always save checkpoint regardless of context level |
 
 ### 1-2. SPEC-First Gate (Level 3: Spec = Source of Truth)
@@ -1617,7 +1617,7 @@ After all scenarios complete + Antigravity review, **quality report is auto-gene
 │  │ Build             │ ✅     │ npm run build succeeded     │    │
 │  │ Tests             │ ✅     │ 12/12 passed                │    │
 │  │ Type check        │ ✅     │ 0 errors                    │    │
-│  │ Complexity        │ ✅     │ All functions ≤30 lines     │    │
+│  │ Complexity        │ ✅     │ All functions ≤50 lines     │    │
 │  │ Security          │ ✅     │ 0 vulnerabilities           │    │
 │  │ Race review       │ ✅     │ 3 improvements applied      │    │
 │  └─────────────────────────────────────────────────────────┘    │
@@ -1857,7 +1857,7 @@ Before marking any scenario as complete, ALL items must pass:
 | **Functionality** | All Given/When/Then conditions verified | 20% |
 | **Functionality** | Edge cases handled per scenario | 10% |
 | **Code Quality** | No `any` types in TypeScript | 10% |
-| **Code Quality** | Functions ≤30 lines, nesting ≤3 levels | 10% |
+| **Code Quality** | Functions ≤50 lines, nesting ≤3 levels | 10% |
 | **Code Quality** | No hardcoded values (use constants) | 5% |
 | **Security** | Input validation implemented | 10% |
 | **Security** | Authentication/authorization checked | 5% |

package/skills/vibe.test/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: vibe.test
-description: Self-test vibe — probe every command/skill/hook/agent in the target harness install dir and write a pass/fail report
+description: Self-test vibe — probe every entry skill/skill/hook/agent in the target harness install dir and write a pass/fail report
 argument-hint: "[cc|codex]  (empty = current harness)"
 user-invocable: true
 ---

package/skills/vibe.verify/SKILL.md

@@ -257,7 +257,7 @@ Record the value as `{step_count}` and include it in the report below.
 │  │ Build             │ ✅    │ Success                     │    │
 │  │ Tests             │ ✅    │ 12/12 passed                │    │
 │  │ Type Check        │ ✅    │ 0 errors                    │    │
-│  │ Complexity        │ ✅    │ All functions ≤30 lines     │    │
+│  │ Complexity        │ ✅    │ All functions ≤50 lines     │    │
 │  │ Code Coverage     │ ⚠️    │ 78% (target: 80%)           │    │
 │  └─────────────────────────────────────────────────────────┘    │
 │                                                                 │

package/vibe/rules/standards/complexity-metrics.md

@@ -283,7 +283,7 @@ npm install eslint-plugin-complexity
   "rules": {
     "complexity": ["error", 10],
     "max-depth": ["error", 3],
-    "max-lines-per-function": ["error", 20]
+    "max-lines-per-function": ["error", 50]
   }
 }
 ```
@@ -307,7 +307,7 @@ radon mi app/
 |--------|--------|-------------|
 | Cyclomatic Complexity | ≤ 10 | Independent execution paths |
 | Cognitive Complexity | ≤ 15 | Easy to understand |
-| Function Length | ≤ 20 lines | Short, focused functions |
+| Function Length | ≤ 50 lines | Short, focused functions |
 | Nesting Depth | ≤ 3 levels | Flat structure |
 | Parameters | ≤ 5 | Function parameter limit |
 | Dependencies | ≤ 7 | Module dependency limit |

package/vibe/templates/claudemd-template.md

@@ -64,7 +64,7 @@ Convergence Principle: loop until P1 = 0. Changed files only.
 
 ## Context Management
 
-At 70%+ context: `save_memory` → `/new` → `/vibe.utils --continue`
+At 85%+ context: `save_memory` → `/new` → `/vibe.utils --continue` (raised from 70% — `/new` discards the entire KV prefix cache, so compacting less often preserves cache reuse)
 
 ## Git Commit Rules