[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M736FPV3F5JA6T98ZTY2AZ4S":3,"skill-same:01M736FPV3F5JA6T98ZTY2AZ4S":70},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M736FPV3F5JA6T98ZTY2AZ4S","content-driven-development",null,"Apply a Content Driven Development process to AEM Edge Delivery Services development. Use for ALL code changes - new blocks, block modifications, CSS styling, bug fixes, core functionality (scripts.js, styles, etc.), or any JavaScript\u002FCSS work that needs validation.","kalash33\u002Fkstack","kalash33","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F90259149?v=4","01M7365X8Q0B73NYHA730SMZWN","Kalash Poddar","01M7365X9D0JK47C3Q0YCCK9Z2",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fadobe-content-driven-development\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: content-driven-development\ndescription: Apply a Content Driven Development process to AEM Edge Delivery Services development. Use for ALL code changes - new blocks, block modifications, CSS styling, bug fixes, core functionality (scripts.js, styles, etc.), or any JavaScript\u002FCSS work that needs validation.\nlicense: Apache-2.0\nmetadata:\n  version: \"1.1.0\"\n---\n\n# Content Driven Development (CDD)\n\nYou are an orchestrator of the Content Driven Development workflow for AEM Edge Delivery Services. This workflow ensures code is built against real content with author-friendly content models.\n\n**CRITICAL: Never start writing or modifying code without first identifying or creating the content you will use to test your changes.**\n\n## When to Use This Skill\n\nUse CDD for ALL AEM development tasks:\n- ✅ Creating new blocks\n- ✅ Modifying existing blocks (structural or functional changes)\n- ✅ Changes to core decoration functionality\n- ✅ Bug fixes that require validation\n- ✅ Any code that affects how authors create or structure content\n\nDo NOT use for:\n- Documentation-only changes\n- Configuration changes that don't affect authoring\n- Research tasks that don't require making any code changes yet\n\n## Philosophy\n\nContent Driven Development prioritizes creating or identifying test content before writing code. This ensures:\n- Code is built against real content\n- Author-friendly content models\n- Validation throughout development\n\n**Optional: Understanding CDD Principles**\n\nRead `resources\u002Fcdd-philosophy.md` if:\n- User asks \"why\" questions about content-first approach\n- You need to understand reasoning behind CDD decisions\n- You're unsure whether to prioritize author vs developer experience\n\nOtherwise: Follow the workflow steps below\n\n## Step 0: Create TodoList\n\n**FIRST STEP:** Use the TodoWrite tool to create a todo list with the following 8 tasks:\n\n1. **Start dev server** (if not running)\n   - Success: Dev server running, can access http:\u002F\u002Flocalhost:3000\n\n2. **Analyze & plan**\n   - Success: Clear understanding documented + acceptance criteria defined\n\n3. **Design content model**\n   - Success: Content structure documented and validated\n\n4. **Identify\u002Fcreate test content**\n   - Success: Test content accessible covering all scenarios\n\n5. **Implement**\n   - Success: Functionality works across all viewports\n\n6. **Lint & test**\n   - Success: All checks pass\n\n7. **Final validation**\n   - Success: All acceptance criteria met, everything works\n\n8. **Ship it**\n   - Success: PR created with preview link for validation\n\n**Mark todo complete when:** Todo list created with all 8 tasks\n\n---\n\n## Step 1: Start Dev Server\n\n**Check if dev server is running:**\n\n```bash\ncurl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" http:\u002F\u002Flocalhost:3000\n```\n\nExpected: `200` (server running) or connection error (server not running)\n\n**If not running, start it:**\n\n```bash\naem up --no-open --forward-browser-logs\n```\n\n**Notes:**\n- Run in background if possible (dev server needs to stay running)\n- Requires AEM CLI installed globally: `npm install -g @adobe\u002Faem-cli`\n- Alternative: `npx -y @adobe\u002Faem-cli up --no-open --forward-browser-logs`\n\n**IMPORTANT:** Check the command output for errors. Common issues:\n- Port 3000 already in use\n- AEM CLI not installed\n- Configuration errors\n\n**After starting, verify it's running:**\n\n```bash\ncurl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" http:\u002F\u002Flocalhost:3000\n```\n\nExpected: `200`\n\n**Success criteria:**\n- ✅ Dev server running\n- ✅ http:\u002F\u002Flocalhost:3000 returns 200\n- ✅ No errors in server startup output\n\n**Mark todo complete when:** Dev server confirmed running and accessible\n\n---\n\n## Step 2: Analyze & Plan\n\n**Invoke:** analyze-and-plan skill\n\n**Provide:**\n- Task description from user\n- Screenshots, design files, or existing URLs to match design from (if available)\n\n**The analyze-and-plan skill will:**\n- Guide you through task-specific analysis\n- Help define acceptance criteria\n- Optionally analyze visual designs\u002Fmockups if provided\n- Create documented analysis for reference\n\n**Success criteria:**\n- ✅ Requirements analyzed\n- ✅ Acceptance criteria defined\n- ✅ Analysis documented to file for later steps\n\n**Mark todo complete when:** Analysis documented and acceptance criteria defined\n\n---\n\n## Step 3: Design Content Model\n\n**Skip if:** CSS-only changes that don't affect content structure\n\n**Invoke:** content-modeling skill\n\n**Provide:**\n- Analysis from Step 2 (content requirements, author inputs)\n- Block name and purpose\n\n**The content-modeling skill will:**\n- Design table structure (rows, columns, semantic formatting)\n- Validate against best practices (4 cells\u002Frow, semantic formatting)\n- Document content model for authors\n\n**Success criteria:**\n- ✅ Content model designed (table structure defined)\n- ✅ Validated against best practices\n- ✅ Content model documented\n\n**Mark todo complete when:** Content model designed and documented\n\n---\n\n## Step 4: Identify\u002FCreate Test Content\n\n**Goal:** End this step with accessible test content URL(s) covering all test scenarios\n\n**Choose the best path based on your situation:**\n\n---\n\n### Option A: User Provided Test URL(s)\n\n**When to use:** User already has content and provided URL(s)\n\n**What to do:**\n1. Validate URL loads: `curl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" http:\u002F\u002Flocalhost:3000\u002Fpath`\n2. Expected: `200` status\n3. Document URL(s)\n4. Mark complete\n\n---\n\n### Option B: New Block (No Existing Content)\n\n**When to use:** Building a brand new block that doesn't exist yet\n\n**What to do:**\n1. Skip search (nothing exists yet to find)\n2. Create test content using one of these approaches:\n\n**Approach 1: CMS Content (Recommended)**\n1. Ask user to create content in their CMS (Google Drive\u002FSharePoint\u002FDA\u002FUniversal Editor)\n2. Provide content model from Step 3 as reference\n3. Wait for user to provide URL(s)\n4. Validate: `curl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" http:\u002F\u002Flocalhost:3000\u002Fpath`\n5. Expected: `200` status\n\n> **Using DA:** If you need to push HTML content programmatically to DA (rather than asking the user to author it), invoke the **da-auth** skill first to obtain a valid `DA_TOKEN`, then use the DA Admin API (`POST https:\u002F\u002Fadmin.da.live\u002Fsource\u002F{org}\u002F{repo}\u002F{path}`) to push the content and trigger a preview.\n\n**Approach 2: Local HTML (Temporary)**\n1. Create HTML file in `drafts\u002Ftmp\u002F{block-name}.plain.html`\n2. Follow structure from Step 3 content model\n3. Read `resources\u002Fhtml-structure.md` for local HTML file format guidance\n4. Restart dev server: `aem up --html-folder drafts --no-open --forward-browser-logs`\n5. Validate: `curl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" http:\u002F\u002Flocalhost:3000\u002Fdrafts\u002Ftmp\u002F{block-name}`\n6. Expected: `200` status\n7. **Note:** User must create CMS content before PR (required for preview link)\n\n---\n\n### Option C: Existing Block\n\n**When to use:** Modifying, fixing, or styling an existing block\n\n**What to do:**\n\n**First: Search for existing content**\n1. Invoke find-test-content skill\n2. Provide: block name, dev server URL (optional, defaults to localhost:3000)\n\n**What find-test-content will do:**\n- Search for existing content pages containing the block\n- Automatically detect and report all variants found\n- Report: URLs with instance counts and variant info\n\n**Then: Assess search results**\n\n**If sufficient content found:**\n1. Document URL(s)\n2. Validate URLs load: `curl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" http:\u002F\u002Flocalhost:3000\u002Fpath`\n3. Expected: `200` status\n4. Mark complete\n\n**If no content found OR insufficient coverage:**\n1. Create additional test content using approaches from Option B\n2. Validate URLs load\n3. Mark complete\n\n---\n\n**Success criteria:**\n- ✅ Test content accessible at known URL(s)\n- ✅ Content covers all test scenarios (variants, edge cases)\n- ✅ URLs validated (return 200)\n\n**Mark todo complete when:** Test content identified\u002Fcreated and validated\n\n---\n\n## Step 5: Implement\n\n**Invoke:** building-blocks skill\n\n**Provide:**\n- Content model from Step 3 (if applicable)\n- Test content URL(s) from Step 4\n- Analysis\u002Frequirements from Step 2\n- Type of changes: new block, existing block modification, CSS-only, etc.\n\n**The building-blocks skill will:**\n- Guide implementation approach based on change type\n- Handle JavaScript decoration (if needed)\n- Handle CSS styling (mobile-first, responsive)\n- Ensure iterative testing in browser throughout development\n\n**Success criteria:**\n- ✅ Code implementation complete\n- ✅ Functionality works across all viewports (mobile, tablet, desktop)\n- ✅ No console errors\n\n**Mark todo complete when:** building-blocks skill reports implementation complete and working across viewports\n\n---\n\n## Step 6: Lint & Test\n\n**What to do:**\n\n```bash\nnpm run lint\n```\n\n**If lint errors:**\n1. Fix issues (use `npm run lint:fix` for auto-fixable problems)\n2. Re-run lint until clean\n\n**Run existing tests:**\n```bash\nnpm test\n```\n\n**Note:** Unit tests are optional and only needed for logic-heavy utilities. The testing-blocks skill (invoked by building-blocks in Step 5) handles browser testing. This step catches any remaining lint issues and runs the project's test suite.\n\n**Success criteria:**\n- ✅ `npm run lint` passes with no errors\n- ✅ `npm test` passes (if tests exist)\n\n**Mark todo complete when:** All lint and test checks pass\n\n---\n\n## Step 7: Final Validation\n\n**What to do:**\n\n1. **Review acceptance criteria from Step 2**\n   - Read the analysis document created in Step 2\n   - Check each acceptance criterion is met\n\n2. **Final browser sanity check**\n   - Load test content URL(s) in browser\n   - Check mobile, tablet, and desktop viewports\n   - Verify no console errors\n   - Confirm no visual regressions\n\n3. **Verify no regressions**\n   - If modifying existing block: test existing variants still work\n   - If modifying core functionality: spot-check a few pages\n\n**Success criteria:**\n- ✅ All acceptance criteria from Step 2 met\n- ✅ Works across all viewports\n- ✅ No console errors\n- ✅ No regressions on existing functionality\n\n**Mark todo complete when:** All acceptance criteria verified and no regressions found\n\n---\n\n## Step 8: Ship It\n\n**What to do:**\n\n1. **Create feature branch (if not already on one):**\n   ```bash\n   git checkout -b block-name\n   ```\n\n2. **Stage specific files only:**\n   ```bash\n   git add blocks\u002F{block-name}\u002F{block-name}.js blocks\u002F{block-name}\u002F{block-name}.css\n   # Add only files you worked on - NEVER use `git add .`\n   ```\n\n3. **Commit with conventional commit format:**\n   ```bash\n   git commit -m \"feat(block-name): add new block\"\n   ```\n   Include relevant details in commit message and agent attribution in footer (agent adds `Co-authored-by: cursor \u003Cnoreply@cursor.com>`)\n\n4. **Push to feature branch:**\n   ```bash\n   git push origin HEAD\n   ```\n\n5. **Create PR with preview link:**\n   - Branch preview URL format: `https:\u002F\u002F{branch}--{repo}--{owner}.aem.page\u002F{path}`\n   - Example: `https:\u002F\u002Fcarousel--aem-skills-demo--shsteimer.aem.page\u002F`\n   - **REQUIRED:** Include preview link in PR description (used for automated PSI checks)\n   - Add multiple preview links if needed (e.g., different variants, edge cases)\n\n   **Determining if you need a draft PR:**\n\n   Create a **draft PR** when:\n   - ✅ Only local test content exists for NEW functionality\u002Fvariants\n   - ✅ Test content demonstrates new features not yet in CMS\n   - ✅ You need user to create CMS content before final validation\n\n   Create a **regular PR** when:\n   - ✅ All test content exists in CMS and is previewable\n   - ✅ Changes only affect existing content (regressions can be tested with existing CMS content)\n\n   **Workflow for draft PRs:**\n   1. Create the PR as a draft using `gh pr create --draft`\n   2. Include existing content preview links (for regression testing if applicable)\n   3. Include next steps in PR description (see template below):\n      - Describe the test content used locally and what scenarios it covered\n      - Suggest that same\u002Fsimilar content be created and previewed, and links added to PR\n      - Keep steps brief but actionable for any reviewer\n   4. Instruct the user to create CMS content following the steps:\n      - Open local test content in browser: `http:\u002F\u002Flocalhost:3000\u002Fdrafts\u002Ftmp\u002F[test-file]`\n      - Right-click AEM Sidekick extension\n      - Click \"View document source\" option\n      - Use the copy button to copy the document content\n      - Paste into Word\u002FGoogle Docs\u002FDocument Authoring (for UE: use as guide, copy\u002Fpaste won't work directly)\n      - Preview the CMS content\n   5. User adds preview URL(s) to PR description and marks PR ready for review (or agent does with user's input)\n\n**PR Description Template:**\n\nUse this template for all PRs, including all relevant preview links and adapting as needed:\n\n```markdown\n## Description\nBrief description of changes\n\n[If an issue exists]\nFix #\u003Cgh-issue-id>\n\nTest URLs:\n\n[Repeat for all relevant test urls]\n- Before: https:\u002F\u002Fmain--{repo}--{owner}.aem.page\u002F{path}\n- After: https:\u002F\u002F{branch}--{repo}--{owner}.aem.page\u002F{path} \n\n[If only local test content (draft PR):]\n\nThis PR is currently a **draft** pending creation of CMS test content.\n\n### Next Steps to Complete PR:\n\n[add relevant steps here]\n```\n\n**Success criteria:**\n- ✅ Changes committed with proper message format and attribution\n- ✅ Pushed to feature branch (not main)\n- ✅ PR created with preview link in description\n\n**Mark todo complete when:** PR created and ready for review\n\n---\n\n## Related Skills\n\n- **analyze-and-plan**: Invoked in Step 2 for requirements analysis and acceptance criteria\n- **content-modeling**: Invoked in Step 3 for designing content models\n- **da-auth**: Obtain a valid Adobe IMS token before pushing content to DA or triggering DA previews programmatically — invoke at the start of Step 4 when using DA\n- **find-test-content**: Invoked in Step 4, Option C for finding existing content\n- **building-blocks**: Invoked in Step 5 for implementation\n- **testing-blocks**: Invoked by building-blocks for browser testing\n- **block-collection-and-party**: Used to find similar blocks and reference implementations\n\n## Anti-Patterns to Avoid\n\nCommon mistakes that violate CDD principles:\n- ❌ Starting with code before understanding the content model\n- ❌ Making assumptions about content structure without seeing real examples\n- ❌ Creating developer-friendly but author-hostile content models\n- ❌ Skipping content creation \"to save time\" (costs more time later)\n\n## Resources\n\n- **Philosophy:** `resources\u002Fcdd-philosophy.md` - Why content-first matters\n- **HTML Structure:** `resources\u002Fhtml-structure.md` - Guide for creating local HTML test files\n","# Content Driven Development (CDD)\n\nYou are an orchestrator of the Content Driven Development workflow for AEM Edge Delivery Services. This workflow ensures code is built against real content with author-friendly content models.\n\n**CRITICAL: Never start writing or modifying code without first identifying or creating the content you will use to test your changes.**\n\n## When to Use This Skill\n\nUse CDD for ALL AEM development tasks:\n- ✅ Creating new blocks\n- ✅ Modifying existing blocks (structural or functional changes)\n- ✅ Changes to core decoration functionality\n- ✅ Bug fixes that require validation\n- ✅ Any code that affects how authors create or structure content\n\nDo NOT use for:\n- Documentation-only changes\n- Configuration changes that don't affect authoring\n- Research tasks that don't require making any code changes yet\n\n## Philosophy\n\nContent Driven Development prioritizes creating or identifying test content before writing code. This ensures:\n- Code is built against real content\n- Author-friendly content models\n- Validation throughout development\n\n**Optional: Understanding CDD Principles**\n\nRead `resources\u002Fcdd-philosophy.md` if:\n- User asks \"why\" questions about content-first approach\n- You need to understand reasoning behind CDD decisions\n- You're unsure whether to prioritize author vs developer experience\n\nOtherwise: Follow the workflow steps below\n\n## Step 0: Create TodoList\n\n**FIRST STEP:** Use the TodoWrite tool to create a todo list with the following 8 tasks:\n\n1. **Start dev server** (if not running)\n   - Success: Dev server running, can access http:\u002F\u002Flocalhost:3000\n\n2. **Analyze & plan**\n   - Success: Clear understanding documented + acceptance criteria defined\n\n3. **Design content model**\n   - Success: Content structure documented and validated\n\n4. **Identify\u002Fcreate test content**\n   - Success: Test content accessible covering all scenarios\n\n5. **Implement**\n   - Success: Functionality works across all viewports\n\n6. **Lint & test**\n   - Success: All checks pass\n\n7. **Final validation**\n   - Success: All acceptance criteria met, everything works\n\n8. **Ship it**\n   - Success: PR created with preview link for validation\n\n**Mark todo complete when:** Todo list created with all 8 tasks\n\n---\n\n## Step 1: Start Dev Server\n\n**Check if dev server is running:**\n\n```bash\ncurl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" http:\u002F\u002Flocalhost:3000\n```\n\nExpected: `200` (server running) or connection error (server not running)\n\n**If not running, start it:**\n\n```bash\naem up --no-open --forward-browser-logs\n```\n\n**Notes:**\n- Run in background if possible (dev server needs to stay running)\n- Requires AEM CLI installed globally: `npm install -g @adobe\u002Faem-cli`\n- Alternative: `npx -y @adobe\u002Faem-cli up --no-open --forward-browser-logs`\n\n**IMPORTANT:** Check the command output for errors. Common issues:\n- Port 3000 already in use\n- AEM CLI not installed\n- Configuration errors\n\n**After starting, verify it's running:**\n\n```bash\ncurl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" http:\u002F\u002Flocalhost:3000\n```\n\nExpected: `200`\n\n**Success criteria:**\n- ✅ Dev server running\n- ✅ http:\u002F\u002Flocalhost:3000 returns 200\n- ✅ No errors in server startup output\n\n**Mark todo complete when:** Dev server confirmed running and accessible\n\n---\n\n## Step 2: Analyze & Plan\n\n**Invoke:** analyze-and-plan skill\n\n**Provide:**\n- Task description from user\n- Screenshots, design files, or existing URLs to match design from (if available)\n\n**The analyze-and-plan skill will:**\n- Guide you through task-specific analysis\n- Help define acceptance criteria\n- Optionally analyze visual designs\u002Fmockups if provided\n- Create documented analysis for reference\n\n**Success criteria:**\n- ✅ Requirements analyzed\n- ✅ Acceptance criteria defined\n- ✅ Analysis documented to file for later steps\n\n**Mark todo complete when:** Analysis documented and acceptance criteria defined\n\n---\n\n## Step 3: Design Content Model\n\n**Skip if:** CSS-only changes that don't affect content structure\n\n**Invoke:** content-modeling skill\n\n**Provide:**\n- Analysis from Step 2 (content requirements, author inputs)\n- Block name and purpose\n\n**The content-modeling skill will:**\n- Design table structure (rows, columns, semantic formatting)\n- Validate against best practices (4 cells\u002Frow, semantic formatting)\n- Document content model for authors\n\n**Success criteria:**\n- ✅ Content model designed (table structure defined)\n- ✅ Validated against best practices\n- ✅ Content model documented\n\n**Mark todo complete when:** Content model designed and documented\n\n---\n\n## Step 4: Identify\u002FCreate Test Content\n\n**Goal:** End this step with accessible test content URL(s) covering all test scenarios\n\n**Choose the best path based on your situation:**\n\n---\n\n### Option A: User Provided Test URL(s)\n\n**When to use:** User already has content and provided URL(s)\n\n**What to do:**\n1. Validate URL loads: `curl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" http:\u002F\u002Flocalhost:3000\u002Fpath`\n2. Expected: `200` status\n3. Document URL(s)\n4. Mark complete\n\n---\n\n### Option B: New Block (No Existing Content)\n\n**When to use:** Building a brand new block that doesn't exist yet\n\n**What to do:**\n1. Skip search (nothing exists yet to find)\n2. Create test content using one of these approaches:\n\n**Approach 1: CMS Content (Recommended)**\n1. Ask user to create content in their CMS (Google Drive\u002FSharePoint\u002FDA\u002FUniversal Editor)\n2. Provide content model from Step 3 as reference\n3. Wait for user to provide URL(s)\n4. Validate: `curl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" http:\u002F\u002Flocalhost:3000\u002Fpath`\n5. Expected: `200` status\n\n> **Using DA:** If you need to push HTML content programmatically to DA (rather than asking the user to author it), invoke the **da-auth** skill first to obtain a valid `DA_TOKEN`, then use the DA Admin API (`POST https:\u002F\u002Fadmin.da.live\u002Fsource\u002F{org}\u002F{repo}\u002F{path}`) to push the content and trigger a preview.\n\n**Approach 2: Local HTML (Temporary)**\n1. Create HTML file in `drafts\u002Ftmp\u002F{block-name}.plain.html`\n2. Follow structure from Step 3 content model\n3. Read `resources\u002Fhtml-structure.md` for local HTML file format guidance\n4. Restart dev server: `aem up --html-folder drafts --no-open --forward-browser-logs`\n5. Validate: `curl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" http:\u002F\u002Flocalhost:3000\u002Fdrafts\u002Ftmp\u002F{block-name}`\n6. Expected: `200` status\n7. **Note:** User must create CMS content before PR (required for preview link)\n\n---\n\n### Option C: Existing Block\n\n**When to use:** Modifying, fixing, or styling an existing block\n\n**What to do:**\n\n**First: Search for existing content**\n1. Invoke find-test-content skill\n2. Provide: block name, dev server URL (optional, defaults to localhost:3000)\n\n**What find-test-content will do:**\n- Search for existing content pages containing the block\n- Automatically detect and report all variants found\n- Report: URLs with instance counts and variant info\n\n**Then: Assess search results**\n\n**If sufficient content found:**\n1. Document URL(s)\n2. Validate URLs load: `curl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" http:\u002F\u002Flocalhost:3000\u002Fpath`\n3. Expected: `200` status\n4. Mark complete\n\n**If no content found OR insufficient coverage:**\n1. Create additional test content using approaches from Option B\n2. Validate URLs load\n3. Mark complete\n\n---\n\n**Success criteria:**\n- ✅ Test content accessible at known URL(s)\n- ✅ Content covers all test scenarios (variants, edge cases)\n- ✅ URLs validated (return 200)\n\n**Mark todo complete when:** Test content identified\u002Fcreated and validated\n\n---\n\n## Step 5: Implement\n\n**Invoke:** building-blocks skill\n\n**Provide:**\n- Content model from Step 3 (if applicable)\n- Test content URL(s) from Step 4\n- Analysis\u002Frequirements from Step 2\n- Type of changes: new block, existing block modification, CSS-only, etc.\n\n**The building-blocks skill will:**\n- Guide implementation approach based on change type\n- Handle JavaScript decoration (if needed)\n- Handle CSS styling (mobile-first, responsive)\n- Ensure iterative testing in browser throughout development\n\n**Success criteria:**\n- ✅ Code implementation complete\n- ✅ Functionality works across all viewports (mobile, tablet, desktop)\n- ✅ No console errors\n\n**Mark todo complete when:** building-blocks skill reports implementation complete and working across viewports\n\n---\n\n## Step 6: Lint & Test\n\n**What to do:**\n\n```bash\nnpm run lint\n```\n\n**If lint errors:**\n1. Fix issues (use `npm run lint:fix` for auto-fixable problems)\n2. Re-run lint until clean\n\n**Run existing tests:**\n```bash\nnpm test\n```\n\n**Note:** Unit tests are optional and only needed for logic-heavy utilities. The testing-blocks skill (invoked by building-blocks in Step 5) handles browser testing. This step catches any remaining lint issues and runs the project's test suite.\n\n**Success criteria:**\n- ✅ `npm run lint` passes with no errors\n- ✅ `npm test` passes (if tests exist)\n\n**Mark todo complete when:** All lint and test checks pass\n\n---\n\n## Step 7: Final Validation\n\n**What to do:**\n\n1. **Review acceptance criteria from Step 2**\n   - Read the analysis document created in Step 2\n   - Check each acceptance criterion is met\n\n2. **Final browser sanity check**\n   - Load test content URL(s) in browser\n   - Check mobile, tablet, and desktop viewports\n   - Verify no console errors\n   - Confirm no visual regressions\n\n3. **Verify no regressions**\n   - If modifying existing block: test existing variants still work\n   - If modifying core functionality: spot-check a few pages\n\n**Success criteria:**\n- ✅ All acceptance criteria from Step 2 met\n- ✅ Works across all viewports\n- ✅ No console errors\n- ✅ No regressions on existing functionality\n\n**Mark todo complete when:** All acceptance criteria verified and no regressions found\n\n---\n\n## Step 8: Ship It\n\n**What to do:**\n\n1. **Create feature branch (if not already on one):**\n   ```bash\n   git checkout -b block-name\n   ```\n\n2. **Stage specific files only:**\n   ```bash\n   git add blocks\u002F{block-name}\u002F{block-name}.js blocks\u002F{block-name}\u002F{block-name}.css\n   # Add only files you worked on - NEVER use `git add .`\n   ```\n\n3. **Commit with conventional commit format:**\n   ```bash\n   git commit -m \"feat(block-name): add new block\"\n   ```\n   Include relevant details in commit message and agent attribution in footer (agent adds `Co-authored-by: cursor \u003Cnoreply@cursor.com>`)\n\n4. **Push to feature branch:**\n   ```bash\n   git push origin HEAD\n   ```\n\n5. **Create PR with preview link:**\n   - Branch preview URL format: `https:\u002F\u002F{branch}--{repo}--{owner}.aem.page\u002F{path}`\n   - Example: `https:\u002F\u002Fcarousel--aem-skills-demo--shsteimer.aem.page\u002F`\n   - **REQUIRED:** Include preview link in PR description (used for automated PSI checks)\n   - Add multiple preview links if needed (e.g., different variants, edge cases)\n\n   **Determining if you need a draft PR:**\n\n   Create a **draft PR** when:\n   - ✅ Only local test content exists for NEW functionality\u002Fvariants\n   - ✅ Test content demonstrates new features not yet in CMS\n   - ✅ You need user to create CMS content before final validation\n\n   Create a **regular PR** when:\n   - ✅ All test content exists in CMS and is previewable\n   - ✅ Changes only affect existing content (regressions can be tested with existing CMS content)\n\n   **Workflow for draft PRs:**\n   1. Create the PR as a draft using `gh pr create --draft`\n   2. Include existing content preview links (for regression testing if applicable)\n   3. Include next steps in PR description (see template below):\n      - Describe the test content used locally and what scenarios it covered\n      - Suggest that same\u002Fsimilar content be created and previewed, and links added to PR\n      - Keep steps brief but actionable for any reviewer\n   4. Instruct the user to create CMS content following the steps:\n      - Open local test content in browser: `http:\u002F\u002Flocalhost:3000\u002Fdrafts\u002Ftmp\u002F[test-file]`\n      - Right-click AEM Sidekick extension\n      - Click \"View document source\" option\n      - Use the copy button to copy the document content\n      - Paste into Word\u002FGoogle Docs\u002FDocument Authoring (for UE: use as guide, copy\u002Fpaste won't work directly)\n      - Preview the CMS content\n   5. User adds preview URL(s) to PR description and marks PR ready for review (or agent does with user's input)\n\n**PR Description Template:**\n\nUse this template for all PRs, including all relevant preview links and adapting as needed:\n\n```markdown\n## Description\nBrief description of changes\n\n[If an issue exists]\nFix #\u003Cgh-issue-id>\n\nTest URLs:\n\n[Repeat for all relevant test urls]\n- Before: https:\u002F\u002Fmain--{repo}--{owner}.aem.page\u002F{path}\n- After: https:\u002F\u002F{branch}--{repo}--{owner}.aem.page\u002F{path} \n\n[If only local test content (draft PR):]\n\nThis PR is currently a **draft** pending creation of CMS test content.\n\n### Next Steps to Complete PR:\n\n[add relevant steps here]\n```\n\n**Success criteria:**\n- ✅ Changes committed with proper message format and attribution\n- ✅ Pushed to feature branch (not main)\n- ✅ PR created with preview link in description\n\n**Mark todo complete when:** PR created and ready for review\n\n---\n\n## Related Skills\n\n- **analyze-and-plan**: Invoked in Step 2 for requirements analysis and acceptance criteria\n- **content-modeling**: Invoked in Step 3 for designing content models\n- **da-auth**: Obtain a valid Adobe IMS token before pushing content to DA or triggering DA previews programmatically — invoke at the start of Step 4 when using DA\n- **find-test-content**: Invoked in Step 4, Option C for finding existing content\n- **building-blocks**: Invoked in Step 5 for implementation\n- **testing-blocks**: Invoked by building-blocks for browser testing\n- **block-collection-and-party**: Used to find similar blocks and reference implementations\n\n## Anti-Patterns to Avoid\n\nCommon mistakes that violate CDD principles:\n- ❌ Starting with code before understanding the content model\n- ❌ Making assumptions about content structure without seeing real examples\n- ❌ Creating developer-friendly but author-hostile content models\n- ❌ Skipping content creation \"to save time\" (costs more time later)\n\n## Resources\n\n- **Philosophy:** `resources\u002Fcdd-philosophy.md` - Why content-first matters\n- **HTML Structure:** `resources\u002Fhtml-structure.md` - Guide for creating local HTML test files\n",{"name":5,"license":15,"metadata":24,"description":7},{"version":25},"1.1.0","main","b30820b3248f6676d5389f0ccabd4e5250c9c536","skills\u002Fadobe-content-driven-development","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack","https:\u002F\u002Fgithub.com\u002Fkalash33","kalashpoddar.me","Tech-savvy Full Stack Developer 🚀 | Cybersecurity enthusiast 🔒 | Passionate about innovation and securing the digital world 🌐 | Let's code securely! 💻🔐","2026-05-20 04:11:22",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add kalash33\u002Fkstack --skill content-driven-development",{"tool":40,"command":41},"bunx","bunx skills add kalash33\u002Fkstack --skill content-driven-development",{"tool":43,"command":44},"pnpm","pnpm dlx skills add kalash33\u002Fkstack --skill content-driven-development","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fadobe-content-driven-development\u002FSKILL.md",true,[48,54,58,62,66],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},".releaserc.json","REFERENCE","参考文档",49,"https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fadobe-content-driven-development\u002F.releaserc.json",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"CHANGELOG.md",9022,"https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fadobe-content-driven-development\u002FCHANGELOG.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"package.json",106,"https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fadobe-content-driven-development\u002Fpackage.json",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"resources\u002Fcdd-philosophy.md",4742,"https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fadobe-content-driven-development\u002Fresources\u002Fcdd-philosophy.md",{"path":67,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":68,"sourceHtmlUrl":69},"resources\u002Fhtml-structure.md",14856,"https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fadobe-content-driven-development\u002Fresources\u002Fhtml-structure.md",[71,79,86,93,100,107],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M73CFERCR43JCAP606E41EFB","zustand-store-ts","Create Zustand stores with TypeScript, subscribeWithSelector middleware, and proper state\u002Faction separation. Use when building React state management, creating global stores, or implementing reacti...","MIT","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzustand-store-ts\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M73CFCMFVTAQEMTZ5HR10X8V","zoom-automation","Automate Zoom meeting creation, management, recordings, webinars, and participant tracking via Rube MCP (Composio). Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzoom-automation\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M73CFAA7EBWXJVXDQ1X555MB","zoho-crm-automation","Automate Zoho CRM tasks via Rube MCP (Composio): create\u002Fupdate records, search contacts, manage leads, and convert leads. Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzoho-crm-automation\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M73CF80XCM9K81567MJ8QZFW","zod-validation-expert","Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzod-validation-expert\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M73CF4YPMF3RA8ZJDXZSMD93","zeroize-audit","Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C\u002FC++\u002FRust code handling secrets, keys, passwords, or other sensitive data.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzeroize-audit\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M73CF2S25EN3XNAMKY47XHPS","zendesk-automation","Automate Zendesk tasks via Rube MCP (Composio): tickets, users, organizations, replies. Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzendesk-automation\u002FSKILL.md",[],[]]