@kennethsolomon/shipkit 3.15.2 → 3.16.1

package/skills/sk:setup-claude/templates/.claude/rules/react.md.template

@@ -1,7 +1,12 @@
-<!-- Generated by /setup-claude -->
-# React Standards
+---
+paths:
+  - "**/*.tsx"
+  - "**/*.jsx"
+  - "src/**/*.ts"
+  - "resources/js/**"
+---
 
-Applies to: `src/components/`, `src/hooks/`, `src/pages/`, `app/components/`
+# React Standards
 
 ## Conventions
 

package/skills/sk:setup-claude/templates/.claude/rules/tests.md.template

@@ -1,7 +1,16 @@
-<!-- Generated by /setup-claude -->
-# Testing Standards
+---
+paths:
+  - "tests/**"
+  - "test/**"
+  - "__tests__/**"
+  - "**/*.test.ts"
+  - "**/*.test.js"
+  - "**/*.spec.ts"
+  - "**/*.spec.js"
+  - "**/*.test.php"
+---
 
-Applies to: `tests/`, `test/`, `__tests__/`, `spec/`
+# Testing Standards
 
 ## Conventions
 

package/skills/sk:setup-claude/templates/.claude/rules/vue.md.template

@@ -0,0 +1,22 @@
+---
+paths:
+  - "**/*.vue"
+  - "resources/js/**/*.ts"
+---
+
+# Vue 3 Standards
+
+## Conventions
+
+- Composition API only — no Options API in new code
+- Prefer `<script setup>` syntax for SFCs
+- `defineProps` with TypeScript types — always validate prop types
+- Always declare emits with typed `defineEmits` interface
+- Composables: prefix with `use` (`useAuth`, `useCart`) — one concern per composable
+- `ref` for primitives, `reactive` for objects — be consistent within a file
+- `computed`: no side effects — read-only getters only
+- Prefer `watchEffect` when dependencies are obvious; use `watch` for explicit control
+- All `v-for` must have `:key` — stable IDs, never array index
+- No logic in templates beyond simple ternaries — extract to computed
+- Pinia stores: one store per domain; actions for mutations, getters for derived state
+- `nextTick`: use sparingly — frequent use usually indicates a design issue

package/skills/sk:setup-optimizer/SKILL.md

@@ -45,7 +45,10 @@ Before making any changes, runs a diagnostic pass on the existing CLAUDE.md:
 - **Inconsistencies** — compares documented vs actual project state (directories, scripts, workflows)
 - **Section completeness** — flags sections that exist but are empty or have only placeholder text
 - **Outdated workflow** — checks if the workflow matches the current 8-step flow with `/sk:gates` as single gate step
-- **Missing commands** — checks for `sk:start`, `sk:autopilot`, `sk:team`, `sk:learn`, `sk:context-budget`, `sk:health`, `sk:save-session`, `sk:resume-session`, `sk:safety-guard`, `sk:eval` in the Commands table
+- **Missing commands** — checks for `sk:start`, `sk:autopilot`, `sk:team`, `sk:learn`, `sk:context-budget`, `sk:health`, `sk:save-session`, `sk:resume-session`, `sk:safety-guard`, `sk:eval`, `sk:ci`, `sk:plugin` in the Commands table
+- **Missing agents** — checks if `.claude/agents/` exists and contains the 13 core agents: `backend-dev`, `frontend-dev`, `mobile-dev`, `qa-engineer`, `code-reviewer`, `security-reviewer`, `performance-optimizer`, `architect`, `database-architect`, `devops-engineer`, `debugger`, `refactor-specialist`, `tech-writer`
+- **Missing rules** — checks if `.claude/rules/` exists and contains the project-relevant rule files based on detected stack (laravel.md, react.md, vue.md, tests.md, api.md, migrations.md)
+- **Stale agent frontmatter** — checks that existing agent files use the new `memory`, `model`, and `tools` frontmatter fields (agents without `memory` are degraded)
 - **Auto-skip rules** — checks for auto-skip detection rules in the workflow section
 - **Stale tracker references** — checks for `tasks/workflow-status.md` references (removed — progress tracked via git branch + todo.md checkboxes)
 - **Missing hooks** — checks if `.claude/hooks/` exists and contains both core and enhanced hooks
@@ -191,10 +194,66 @@ After LSP check, verify the three recommended tools are configured:
 - Context7: add `context7@claude-plugins-official: true` to `~/.claude/settings.json` enabledPlugins
 - ccstatusline: run `npx ccstatusline@latest`
 
-**If no:** skip, continue to Step 2.
+**If no:** skip, continue to Step 1.8.
 
 **Idempotency:** Never overwrite existing MCP entries, plugin flags, or statusline config — additive merge only.
 
+### Step 1.8: Agents & Rules Check
+
+After MCP check, verify the project has formal agent definitions and path-scoped rules:
+
+**Agents check:**
+
+1. Check if `.claude/agents/` directory exists
+2. Check for the 13 core agents:
+   - **Implementation:** `backend-dev.md`, `frontend-dev.md`, `mobile-dev.md`
+   - **Quality:** `qa-engineer.md`, `code-reviewer.md`, `security-reviewer.md`, `performance-optimizer.md`
+   - **Design:** `architect.md`, `database-architect.md`
+   - **Operations:** `devops-engineer.md`
+   - **Maintenance:** `debugger.md`, `refactor-specialist.md`, `tech-writer.md`
+3. For each existing agent, check if it has `memory:` and `model:` in frontmatter (older agents may be missing these)
+
+**Rules check:**
+
+1. Check if `.claude/rules/` directory exists
+2. Detect project stack from `CLAUDE.md`, `package.json`, `composer.json`
+3. Check for relevant rule files based on detected stack:
+   - Laravel/PHP detected → check for `laravel.md`, `api.md`, `migrations.md`
+   - React/Next.js detected → check for `react.md`, `tests.md`, `api.md`
+   - Vue/Nuxt detected → check for `vue.md`, `tests.md`, `api.md`
+   - Any stack → check for `tests.md`
+
+**Report status and prompt:**
+
+> "Agents: [X/13] core agents found
+>   backend-dev:           [✓ / ✗ missing]
+>   frontend-dev:          [✓ / ✗ missing]
+>   mobile-dev:            [✓ / ✗ missing]
+>   qa-engineer:           [✓ / ✗ missing]
+>   code-reviewer:         [✓ / ✗ missing]
+>   security-reviewer:     [✓ / ✗ missing]
+>   performance-optimizer: [✓ / ✗ missing]
+>   architect:             [✓ / ✗ missing]
+>   database-architect:    [✓ / ✗ missing]
+>   devops-engineer:       [✓ / ✗ missing]
+>   debugger:              [✓ / ✗ missing]
+>   refactor-specialist:   [✓ / ✗ missing]
+>   tech-writer:           [✓ / ✗ missing]
+>
+> Rules: [X/N] stack-relevant rules found
+>   [list relevant rules with ✓/✗]
+>
+> Deploy missing agents and rules? [y/n]"
+
+**If yes:**
+- Copy missing agent files from `~/.claude/skills/sk:setup-claude/templates/.claude/agents/`
+- Copy missing rule files from `~/.claude/skills/sk:setup-claude/templates/.claude/rules/`
+- Only deploy agents/rules that don't exist yet — never overwrite existing customized files
+
+**If no:** skip, continue to Step 2.
+
+**Idempotency:** Never overwrite existing agent or rule files.
+
 ### Step 2: Scan & Enrich
 
 After workflow update, proceeds with codebase discovery and enrichment:

package/skills/sk:smart-commit/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: sk:smart-commit
 description: "Analyze staged changes, auto-detect commit type, and generate conventional commit messages with approval workflow."
+disable-model-invocation: true
 ---
 
 # Smart Conventional Commits

package/skills/sk:start/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: sk:start
 description: Smart entry point — classifies your task, detects scope, and routes to the optimal flow (feature/debug/hotfix/fast-track), mode (manual/autopilot), and agent strategy (solo/team).
-allowed_tools: Read, Write, Bash, Glob, Grep, Agent, Skill
+allowed-tools: Read, Write, Bash, Glob, Grep, Agent, Skill
 ---
 
 # Smart Start

package/skills/sk:team/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: sk:team
 description: Parallel domain agents for full-stack implementation — spawns Backend, Frontend, and QA agents in isolated worktrees.
-allowed_tools: Read, Write, Bash, Glob, Grep, Agent
+allowed-tools: Read, Write, Bash, Glob, Grep, Agent
 ---
 
 # Team Mode

package/skills/sk:website/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: sk:website
 description: Build a complete, client-deliverable multi-page marketing website from a brief, URL, or one sentence. NOT a prototype — a real site you hand to a client. Auto-builds from intake to handoff package. Use --revise for change iterations after initial build.
+argument-hint: "[--revise] [URL or brief]"
 ---
 
 # /sk:website — Client Website Builder

package/commands/sk/autopilot.md

@@ -1,22 +0,0 @@
----
-description: "Hands-free workflow — all 8 steps, auto-skip, auto-advance, auto-commit. Stops only for direction approval and PR push."
----
-
-# /sk:autopilot
-
-Run the full ShipIt workflow in hands-free mode.
-
-Usage: `/sk:autopilot <task description>`
-
-Executes all 8 workflow steps with:
-- **Auto-skip** — optional steps skipped when clearly not needed
-- **Auto-advance** — no manual step transitions
-- **Auto-commit** — conventional format, no approval prompt
-- **Same quality gates** — all gates enforced, same fix loops
-
-Stops only for:
-1. Direction approval (after brainstorm)
-2. 3-strike failures
-3. PR push confirmation
-
-See `skills/sk:autopilot/SKILL.md` for full details.

package/commands/sk/context-budget.md

@@ -1,5 +0,0 @@
----
-description: "Audit context window token consumption and find optimization opportunities."
----
-
-Use the `sk:context-budget` skill to inventory all components consuming context tokens (agents, skills, rules, MCP tools, CLAUDE.md), classify usage frequency, detect bloat, and recommend top 3 optimizations with estimated token savings.

package/commands/sk/eval.md

@@ -1,5 +0,0 @@
----
-description: "Define, run, and report on evaluations for agent reliability and code quality."
----
-
-Use the `sk:eval` skill to define eval criteria before coding (`define`), verify during implementation (`check`), and summarize results after shipping (`report`). Supports code-based, model-based, and human graders with pass@k and pass^k metrics.

package/commands/sk/health.md

@@ -1,5 +0,0 @@
----
-description: "Run harness self-audit and produce a health scorecard."
----
-
-Use the `sk:health` skill to score your ShipKit setup across 7 categories (Tool Coverage, Context Efficiency, Quality Gates, Memory Persistence, Eval Coverage, Security Guardrails, Cost Efficiency). Produces a 0-70 scorecard with concrete findings and top 3 actions.

package/commands/sk/learn.md

@@ -1,5 +0,0 @@
----
-description: "Extract reusable patterns from the current session into learned instincts."
----
-
-Use the `sk:learn` skill to analyze the current session for extractable patterns (error resolutions, debugging techniques, workarounds, project conventions). Patterns are saved with confidence scoring and can be promoted from project-scoped to global.

package/commands/sk/resume-session.md

@@ -1,5 +0,0 @@
----
-description: "Resume a previously saved session with full context restoration."
----
-
-Use the `sk:resume-session` skill to list available saved sessions from `.claude/sessions/`, select one, and restore its context (branch, task state, progress, open questions, next steps) into the current conversation.

package/commands/sk/safety-guard.md

@@ -1,5 +0,0 @@
----
-description: "Protect against destructive operations with careful, freeze, and guard modes."
----
-
-Use the `sk:safety-guard` skill to activate protection modes: `careful` (block destructive commands), `freeze --dir <path>` (lock edits to a directory), `guard --dir <path>` (both), `off` (disable), or `status` (show current mode).

package/commands/sk/save-session.md

@@ -1,5 +0,0 @@
----
-description: "Save current session state for cross-session continuity."
----
-
-Use the `sk:save-session` skill to persist the current session state (branch, task, progress, findings, open questions) to `.claude/sessions/` for resumption in a future conversation. Essential for EPIC-scope multi-session workflows.

package/commands/sk/start.md

@@ -1,30 +0,0 @@
----
-description: "Smart entry point — classifies your task and routes to the optimal flow, mode, and agent strategy."
----
-
-# /sk:start
-
-Smart entry point for all ShipIt work. Classifies your task and recommends the best workflow configuration.
-
-Usage: `/sk:start <task description>`
-
-Examples:
-```
-/sk:start add user profile page with avatar upload
-/sk:start fix login redirect loop
-/sk:start urgent: payments failing in production
-/sk:start bump lodash to latest version
-```
-
-**What it does:**
-1. **Classifies** — detects if it's a feature, bug, hotfix, or small change
-2. **Detects scope** — full-stack, frontend-only, or backend-only
-3. **Recommends** — optimal flow + mode (autopilot/manual) + agents (team/solo)
-4. **Routes** — enters the chosen workflow after your confirmation
-
-**Override flags:**
-- `--manual` — force step-by-step mode
-- `--team` / `--no-team` — force team or solo agents
-- `--debug` / `--hotfix` / `--fast-track` — force a specific flow
-
-See `skills/sk:start/SKILL.md` for full details.

package/commands/sk/team.md

@@ -1,23 +0,0 @@
----
-description: "Parallel domain agents — spawns Backend, Frontend, and QA agents for full-stack implementation."
----
-
-# /sk:team
-
-Split implementation across parallel domain agents.
-
-Usage: `/sk:team`
-
-Spawns 3 specialized agents in parallel:
-- **Backend Agent** (worktree) — backend tests + implementation
-- **Frontend Agent** (worktree) — frontend tests + implementation
-- **QA Agent** (background) — E2E test scenarios
-
-**Prerequisite:** Plan must contain an explicit API contract section.
-
-Falls back to single-agent mode if:
-- No API contract in plan
-- Backend-only or frontend-only task
-- Worktree creation fails
-
-See `skills/sk:team/SKILL.md` for full details.

package/commands/sk/website.md

@@ -1,11 +0,0 @@
----
-description: Build a complete, client-deliverable multi-page marketing website from a brief, URL, or one sentence. Auto-builds from intake to handoff. Supports Next.js (default), Nuxt 3, and Laravel. Use --revise for client feedback iterations.
----
-
-# /sk:website
-
-Build a production-ready multi-page marketing website for delivery to a client.
-
-Usage: `/sk:website [--stack nuxt|laravel] [--deploy] [--revise]`
-
-See `skills/sk:website/SKILL.md` for full details.