Add memory

.claude/commands/capture-knowledge.md

@@ -2,6 +2,11 @@
 
 Guide me through creating a structured understanding of a code entry point and saving it to the knowledge docs.
 
+## Memory (use when helpful)
+- If you need clarification or project conventions, query `memory.searchKnowledge` with a brief task description, tags, and scope.
+- If I ask to save reusable guidance, run `/remember` (or call `memory.storeKnowledge`).
+- If MCP tools are unavailable, use `ai-devkit memory search` or `ai-devkit memory store`.
+
 ## Step 1: Gather Context
 - Entry point (file, folder, function, API)
 - Why this entry point matters (feature, bug, investigation)

.claude/commands/check-implementation.md

@@ -1,5 +1,10 @@
 Compare the current implementation with the design in docs/ai/design/ and requirements in docs/ai/requirements/. Please follow this structured review:
 
+## Memory (use when helpful)
+- If you need clarification or project conventions, query `memory.searchKnowledge` with a brief task description, tags, and scope.
+- If I ask to save reusable guidance, run `/remember` (or call `memory.storeKnowledge`).
+- If MCP tools are unavailable, use `ai-devkit memory search` or `ai-devkit memory store`.
+
 1. Ask me for:
    - Feature/branch description
    - List of modified files

.claude/commands/code-review.md

@@ -2,6 +2,11 @@
 
 You are helping me perform a local code review **before** I push changes. Please follow this structured workflow.
 
+## Memory (use when helpful)
+- If you need clarification or project conventions, query `memory.searchKnowledge` with a brief task description, tags, and scope.
+- If I ask to save reusable guidance, run `/remember` (or call `memory.storeKnowledge`).
+- If MCP tools are unavailable, use `ai-devkit memory search` or `ai-devkit memory store`.
+
 ## Step 1: Gather Context
 Ask me for:
 - Brief feature/branch description

.claude/commands/debug.md

@@ -2,6 +2,11 @@
 
 Help me debug an issue by clarifying expectations, identifying gaps, and agreeing on a fix plan before changing code.
 
+## Memory (use when helpful)
+- If you need clarification or project conventions, query `memory.searchKnowledge` with a brief task description, tags, and scope.
+- If I ask to save reusable guidance, run `/remember` (or call `memory.storeKnowledge`).
+- If MCP tools are unavailable, use `ai-devkit memory search` or `ai-devkit memory store`.
+
 ## Step 1: Gather Context
 Ask me for:
 - Brief issue description (what is happening?)

.claude/commands/execute-plan.md

@@ -2,6 +2,11 @@
 
 Help me work through a feature plan one task at a time.
 
+## Memory (use when helpful)
+- If you need clarification or project conventions, query `memory.searchKnowledge` with a brief task description, tags, and scope.
+- If I ask to save reusable guidance, run `/remember` (or call `memory.storeKnowledge`).
+- If MCP tools are unavailable, use `ai-devkit memory search` or `ai-devkit memory store`.
+
 ## Step 1: Gather Context
 Ask me for:
 - Feature name (kebab-case, e.g., `user-authentication`)

.claude/commands/new-requirement.md

@@ -1,5 +1,10 @@
 I want to add a new feature/requirement. Please guide me through the complete development workflow:
 
+## Memory (use when helpful)
+- If you need clarification or project conventions, query `memory.searchKnowledge` with a brief task description, tags, and scope.
+- If I ask to save reusable guidance, run `/remember` (or call `memory.storeKnowledge`).
+- If MCP tools are unavailable, use `ai-devkit memory search` or `ai-devkit memory store`.
+
 ## Step 1: Capture Requirement
 First, ask me:
 - What is the feature name? (e.g., "user-authentication", "payment-integration")

.claude/commands/remember.md

@@ -0,0 +1,22 @@
+When I say "remember this" or want to save a reusable rule, help me store it in the knowledge memory service.
+
+## Step 1: Capture Knowledge
+Ask me for:
+- A short, explicit title (5-12 words)
+- The detailed content (markdown, examples encouraged)
+- Optional tags (keywords like "api", "testing")
+- Optional scope (`global`, `project:<name>`, `repo:<name>`)
+
+If I'm vague, ask follow-ups to make it specific and actionable.
+
+## Step 2: Validate Quality
+- Ensure it is specific and reusable (not generic advice).
+- Avoid storing secrets or sensitive data.
+
+## Step 3: Store
+Call `memory.storeKnowledge` with title, content, tags, scope.
+If MCP tools are unavailable, use `ai-devkit memory store` instead.
+
+## Step 4: Confirm
+Summarize what was saved and offer to store more knowledge if needed.
+

.claude/commands/review-design.md

@@ -1,4 +1,10 @@
 Review the design documentation in docs/ai/design/feature-{name}.md (and the project-level README if relevant). Summarize:
+
+## Memory (use when helpful)
+- If you need clarification or project conventions, query `memory.searchKnowledge` with a brief task description, tags, and scope.
+- If I ask to save reusable guidance, run `/remember` (or call `memory.storeKnowledge`).
+- If MCP tools are unavailable, use `ai-devkit memory search` or `ai-devkit memory store`.
+
 - Architecture overview (ensure mermaid diagram is present and accurate)
 - Key components and their responsibilities
 - Technology choices and rationale

.claude/commands/review-requirements.md

@@ -1,4 +1,10 @@
 Please review `docs/ai/requirements/feature-{name}.md` and the project-level template `docs/ai/requirements/README.md` to ensure structure and content alignment. Summarize:
+
+## Memory (use when helpful)
+- If you need clarification or project conventions, query `memory.searchKnowledge` with a brief task description, tags, and scope.
+- If I ask to save reusable guidance, run `/remember` (or call `memory.storeKnowledge`).
+- If MCP tools are unavailable, use `ai-devkit memory search` or `ai-devkit memory store`.
+
 - Core problem statement and affected users
 - Goals, non-goals, and success criteria
 - Primary user stories & critical flows

.claude/commands/update-planning.md

@@ -2,6 +2,11 @@
 
 Please help me reconcile the current implementation progress with our planning documentation.
 
+## Memory (use when helpful)
+- If you need clarification or project conventions, query `memory.searchKnowledge` with a brief task description, tags, and scope.
+- If I ask to save reusable guidance, run `/remember` (or call `memory.storeKnowledge`).
+- If MCP tools are unavailable, use `ai-devkit memory search` or `ai-devkit memory store`.
+
 ## Step 1: Gather Context
 Ask me for:
 - Feature/branch name and brief status

.claude/commands/writing-test.md

@@ -1,5 +1,10 @@
 Review `docs/ai/testing/feature-{name}.md` and ensure it mirrors the base template before writing tests.
 
+## Memory (use when helpful)
+- If you need clarification or project conventions, query `memory.searchKnowledge` with a brief task description, tags, and scope.
+- If I ask to save reusable guidance, run `/remember` (or call `memory.storeKnowledge`).
+- If MCP tools are unavailable, use `ai-devkit memory search` or `ai-devkit memory store`.
+
 ## Step 1: Gather Context
 Ask me for:
 - Feature name and branch

.cursor/commands/capture-knowledge.md

@@ -2,6 +2,11 @@
 
 Guide me through creating a structured understanding of a code entry point and saving it to the knowledge docs.
 
+## Memory (use when helpful)
+- If you need clarification or project conventions, query `memory.searchKnowledge` with a brief task description, tags, and scope.
+- If I ask to save reusable guidance, run `/remember` (or call `memory.storeKnowledge`).
+- If MCP tools are unavailable, use `ai-devkit memory search` or `ai-devkit memory store`.
+
 ## Step 1: Gather Context
 - Entry point (file, folder, function, API)
 - Why this entry point matters (feature, bug, investigation)

.cursor/commands/check-implementation.md

@@ -3,6 +3,11 @@ description: test
 ---
 Compare the current implementation with the design in docs/ai/design/ and requirements in docs/ai/requirements/. Please follow this structured review:
 
+## Memory (use when helpful)
+- If you need clarification or project conventions, query `memory.searchKnowledge` with a brief task description, tags, and scope.
+- If I ask to save reusable guidance, run `/remember` (or call `memory.storeKnowledge`).
+- If MCP tools are unavailable, use `ai-devkit memory search` or `ai-devkit memory store`.
+
 1. Ask me for:
    - Feature/branch description
    - List of modified files

.cursor/commands/code-review.md

@@ -2,6 +2,11 @@
 
 You are helping me perform a local code review **before** I push changes. Please follow this structured workflow.
 
+## Memory (use when helpful)
+- If you need clarification or project conventions, query `memory.searchKnowledge` with a brief task description, tags, and scope.
+- If I ask to save reusable guidance, run `/remember` (or call `memory.storeKnowledge`).
+- If MCP tools are unavailable, use `ai-devkit memory search` or `ai-devkit memory store`.
+
 ## Step 1: Gather Context
 Ask me for:
 - Brief feature/branch description

.cursor/commands/debug.md

@@ -2,6 +2,11 @@
 
 Help me debug an issue by clarifying expectations, identifying gaps, and agreeing on a fix plan before changing code.
 
+## Memory (use when helpful)
+- If you need clarification or project conventions, query `memory.searchKnowledge` with a brief task description, tags, and scope.
+- If I ask to save reusable guidance, run `/remember` (or call `memory.storeKnowledge`).
+- If MCP tools are unavailable, use `ai-devkit memory search` or `ai-devkit memory store`.
+
 ## Step 1: Gather Context
 Ask me for:
 - Brief issue description (what is happening?)

.cursor/commands/execute-plan.md

@@ -2,6 +2,11 @@
 
 Help me work through a feature plan one task at a time.
 
+## Memory (use when helpful)
+- If you need clarification or project conventions, query `memory.searchKnowledge` with a brief task description, tags, and scope.
+- If I ask to save reusable guidance, run `/remember` (or call `memory.storeKnowledge`).
+- If MCP tools are unavailable, use `ai-devkit memory search` or `ai-devkit memory store`.
+
 ## Step 1: Gather Context
 Ask me for:
 - Feature name (kebab-case, e.g., `user-authentication`)

.cursor/commands/new-requirement.md

@@ -1,5 +1,10 @@
 I want to add a new feature/requirement. Please guide me through the complete development workflow:
 
+## Memory (use when helpful)
+- If you need clarification or project conventions, query `memory.searchKnowledge` with a brief task description, tags, and scope.
+- If I ask to save reusable guidance, run `/remember` (or call `memory.storeKnowledge`).
+- If MCP tools are unavailable, use `ai-devkit memory search` or `ai-devkit memory store`.
+
 ## Step 1: Capture Requirement
 First, ask me:
 - What is the feature name? (e.g., "user-authentication", "payment-integration")

.cursor/commands/remember.md

@@ -0,0 +1,22 @@
+When I say "remember this" or want to save a reusable rule, help me store it in the knowledge memory service.
+
+## Step 1: Capture Knowledge
+Ask me for:
+- A short, explicit title (5-12 words)
+- The detailed content (markdown, examples encouraged)
+- Optional tags (keywords like "api", "testing")
+- Optional scope (`global`, `project:<name>`, `repo:<name>`)
+
+If I'm vague, ask follow-ups to make it specific and actionable.
+
+## Step 2: Validate Quality
+- Ensure it is specific and reusable (not generic advice).
+- Avoid storing secrets or sensitive data.
+
+## Step 3: Store
+Call `memory.storeKnowledge` with title, content, tags, scope.
+If MCP tools are unavailable, use `ai-devkit memory store` instead.
+
+## Step 4: Confirm
+Summarize what was saved and offer to store more knowledge if needed.
+

.cursor/commands/review-design.md

@@ -1,4 +1,10 @@
 Review the design documentation in docs/ai/design/feature-{name}.md (and the project-level README if relevant). Summarize:
+
+## Memory (use when helpful)
+- If you need clarification or project conventions, query `memory.searchKnowledge` with a brief task description, tags, and scope.
+- If I ask to save reusable guidance, run `/remember` (or call `memory.storeKnowledge`).
+- If MCP tools are unavailable, use `ai-devkit memory search` or `ai-devkit memory store`.
+
 - Architecture overview (ensure mermaid diagram is present and accurate)
 - Key components and their responsibilities
 - Technology choices and rationale

.cursor/commands/review-requirements.md

@@ -1,4 +1,10 @@
 Please review `docs/ai/requirements/feature-{name}.md` and the project-level template `docs/ai/requirements/README.md` to ensure structure and content alignment. Summarize:
+
+## Memory (use when helpful)
+- If you need clarification or project conventions, query `memory.searchKnowledge` with a brief task description, tags, and scope.
+- If I ask to save reusable guidance, run `/remember` (or call `memory.storeKnowledge`).
+- If MCP tools are unavailable, use `ai-devkit memory search` or `ai-devkit memory store`.
+
 - Core problem statement and affected users
 - Goals, non-goals, and success criteria
 - Primary user stories & critical flows

.cursor/commands/update-planning.md

@@ -2,6 +2,11 @@
 
 Please help me reconcile the current implementation progress with our planning documentation.
 
+## Memory (use when helpful)
+- If you need clarification or project conventions, query `memory.searchKnowledge` with a brief task description, tags, and scope.
+- If I ask to save reusable guidance, run `/remember` (or call `memory.storeKnowledge`).
+- If MCP tools are unavailable, use `ai-devkit memory search` or `ai-devkit memory store`.
+
 ## Step 1: Gather Context
 Ask me for:
 - Feature/branch name and brief status

.cursor/commands/writing-test.md

@@ -1,5 +1,10 @@
 Review `docs/ai/testing/feature-{name}.md` and ensure it mirrors the base template before writing tests.
 
+## Memory (use when helpful)
+- If you need clarification or project conventions, query `memory.searchKnowledge` with a brief task description, tags, and scope.
+- If I ask to save reusable guidance, run `/remember` (or call `memory.storeKnowledge`).
+- If MCP tools are unavailable, use `ai-devkit memory search` or `ai-devkit memory store`.
+
 ## Step 1: Gather Context
 Ask me for:
 - Feature name and branch

.github/workflows/ci.yml

@@ -0,0 +1,38 @@
+name: CI
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+jobs:
+  test:
+    name: Test (Node 20)
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 20
+          cache: 'npm'
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Lint
+        run: npm run lint
+
+      - name: Build
+        run: npm run build
+
+      - name: Test
+        run: npm run test

.github/workflows/deploy.yml → .github/workflows/deploy-web.yml

@@ -1,9 +1,12 @@
-name: Deploy to GitHub Pages
+name: Deploy Documentation
 
 on:
   push:
     branches:
       - main
+    paths:
+      - 'web/**'
+      - '.github/workflows/deploy-web.yml'
   workflow_dispatch:
 
 permissions:
@@ -17,7 +20,9 @@ concurrency:
 
 jobs:
   build:
+    name: Build Documentation
     runs-on: ubuntu-latest
+
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -30,14 +35,12 @@ jobs:
           cache-dependency-path: web/package-lock.json
 
       - name: Install dependencies
-        run: |
-          cd web
-          npm ci
+        working-directory: ./web
+        run: npm ci
 
       - name: Build website
-        run: |
-          cd web
-          npm run build
+        working-directory: ./web
+        run: npm run build
         env:
           NODE_ENV: production
           NEXT_PUBLIC_SITE_URL: https://ai-devkit.com
@@ -48,13 +51,14 @@ jobs:
           path: web/out
 
   deploy:
+    name: Deploy to GitHub Pages
     environment:
       name: github-pages
       url: ${{ steps.deployment.outputs.page_url }}
     runs-on: ubuntu-latest
     needs: build
+
     steps:
       - name: Deploy to GitHub Pages
         id: deployment
         uses: actions/deploy-pages@v4
-