@se-studio/project-build 1.0.131 → 1.0.133

package/skills/contentful-cms/image-guide/SKILL.md

@@ -1,240 +0,0 @@
----
-name: "Image Guide"
-description: "Generate a comprehensive image guide (both Markdown and HTML) for a site's CMS image assets, with rich AI-generated visual descriptions and content relationship trees."
----
-
-# Skill: contentful-cms — Image Guide
-
-Use this skill to generate a **fully enriched image guide** for a site. The guide documents every image in the CMS with:
-- Rich visual descriptions generated by inspecting each image
-- Content relationship tree showing which pages/components use each image
-- Two output formats: Markdown (AI-consumable) and HTML (human reference)
-
-The output files are written to the app's `docs/` directory (or a path you specify).
-
-## When to use
-
-- Client or team wants a reference guide for all images in the CMS
-- Need to know where a specific image is used across the site
-- Preparing image guidance for AI agents that will be choosing images
-- Auditing image coverage or identifying unused assets
-
-## Prerequisites
-
-- `cms-edit` is configured for the target space (run `cms-edit health` to verify)
-- You have read access to the image URLs (standard Contentful CDN URLs work)
-- The app directory is known (e.g. `apps/example-brightlifekids/`)
-
-## Brand Context
-
-Before starting, check if a brand context skill is available (e.g., "BrightLife Kids Brand Context"). If so, incorporate brand terminology in the descriptions and "When to use" guidance.
-
----
-
-## Workflow
-
-### Step 0 — Load description cache
-
-Each image's description is stored as its own small file to avoid token-limit issues when reading or writing:
-
-```
-docs/descriptions/{assetId}.json
-```
-
-**To check if an image is already cached:**
-```bash
-ls docs/descriptions/{assetId}.json 2>/dev/null && echo "cached" || echo "not cached"
-```
-
-**Per-image file format:**
-```json
-{
-  "subjects": "...",
-  "setting": "...",
-  "composition": "...",
-  "colours": "...",
-  "mood": "...",
-  "style": "...",
-  "constraints": "...",
-  "whenToUse": "...",
-  "inspectedAt": "2026-04-15T10:00:00Z"
-}
-```
-
-**Write-through caching — CRITICAL:** After visually inspecting each NEW image, immediately write its description to `docs/descriptions/{assetId}.json` using the Write tool BEFORE inspecting the next image. One image → one Write call → next image. Each file is tiny (~1KB), so no token limits apply.
-
-If `docs/descriptions/{assetId}.json` already exists, read it and use the cached data — **skip the vision call entirely**.
-
-At the end of the run, report: `N from cache, M newly inspected`.
-
-**Phase discipline — cache first, guides second:** Complete ALL image inspections and per-image cache writes before starting any guide file. Do not interleave inspection with guide writing.
-
-> **Note:** If a legacy `docs/image-descriptions-cache.json` file exists, ignore it. The per-file cache supersedes it.
-
-### Step 1 — Gather structural data
-
-Run the audit command to get all images and their page/component usages:
-
-```bash
-cms-edit --json audit images
-```
-
-This outputs JSON with every image asset including:
-- Asset ID, title, filename, dimensions, MIME type, CDN URL
-- `usages[]`: the slug-bearing ancestors (page, article, articleType, pageVariant, tag, person) that ultimately use this asset. Intermediate wrapper entries (media, visual, component, etc.) are walked through transparently and not included. Each usage has `{ id, contentType, label, slug }`.
-
-Save the output to a temporary file or keep it in context.
-
-If the output is large, focus on images grouped by page. Use `cms-edit audit tree --page /<slug>` to see the relationship tree for a specific page:
-
-```bash
-cms-edit audit tree --page /
-cms-edit audit tree --page /families
-```
-
-### Step 2 — Inspect each image visually
-
-For each image in the JSON output, fetch the image URL and inspect it carefully. The CDN URL supports resize parameters — use `?w=800&q=85` for a good preview:
-
-```
-https://images.ctfassets.net/{spaceId}/{assetId}/{hash}/{filename}?w=800&q=85
-```
-
-For each image generate a **visual description** covering ALL of these fields:
-
-| Field | What to capture |
-|-------|----------------|
-| **Subjects** | Count of people, apparent ages, genders (if relevant), expressions, what they are doing |
-| **Setting** | Indoor/outdoor, room type or environment, background detail level, time of day |
-| **Composition** | Landscape or portrait, crop tightness (headshot / mid-shot / wide / full-bleed), focal point position, negative space |
-| **Colours** | 3–5 dominant colours with approximate descriptions (e.g. "warm cream, sage green, muted terracotta"), warm vs cool tone, contrast level |
-| **Mood** | One or two words: playful, warm, clinical, energetic, calm, aspirational, inclusive, serious |
-| **Style** | Photography (stock / custom-produced), illustration, icon, UI mockup, logo |
-| **Constraints** | What the image does NOT have — e.g. "no text overlay space", "subject fills frame", "no negative space for overlay", "transparent background" |
-
-For icons, logos, and UI mockups, the description can be shorter and focus on what the graphic represents and its visual style.
-
-### Step 3 — Determine "When to use" guidance
-
-Based on the image's current usages and its visual content, write a concise "When to use" paragraph covering:
-- Component types it suits (Hero, CtaCard, wide-format, etc.)
-- Content topics or page contexts where it fits
-- What NOT to use it for (age group constraints, format constraints, etc.)
-- Any reuse notes (e.g. "also used as /partners hero — suitable for both card and full-width formats")
-
-### Step 4 — Write the Markdown guide
-
-Output path: `docs/image-guide.md` inside the app directory (e.g. `apps/example-brightlifekids/docs/image-guide.md`).
-
-**IMPORTANT — chunked writing to avoid output token limits:** The guide file will be large (many KB). Never try to write the entire file in a single Write tool call. Instead, use bash heredoc append operations in batches:
-
-```bash
-# First call — write file header + first ~35 images (use actual app path)
-cat > apps/example-brightlifekids/docs/image-guide.md << 'MDEOF'
-# BrightLife Kids — Image Guide
-
-> Generated 2026-04-15. Space: blk. 202 images documented.
-...
-## Image 1 · filename.jpg
-...
-MDEOF
-
-# Subsequent calls — APPEND next batch (note >>)
-cat >> apps/example-brightlifekids/docs/image-guide.md << 'MDEOF'
-## Image 36 · filename.jpg
-...
-MDEOF
-```
-
-Keep each bash call to **35 images maximum** (~18,000 tokens of content per call). Use as many `cat >>` append calls as needed. For descriptions, read from the cached `docs/descriptions/{assetId}.json` files rather than re-inspecting.
-
-Use this structure:
-
-```markdown
-# {Brand} — Image Guide
-
-> Generated {date}. Space: {spaceKey}. {N} images documented.
->
-> **AI usage note**: Each entry below has consistent fields for programmatic selection.
-> Match `Subjects`, `Setting`, and `Mood` to the content context. Use `Constraints` to
-> rule out images that won't work for a given layout. `Used on` shows exact page/component context.
-
----
-
-## {image title} · {filename}
-
-**Asset ID**: `{id}`  
-**Dimensions**: {width}×{height} · {contentType}  
-**CDN URL**: `{url}?w=800&q=85`
-
-**Used on**:
-- {slug} — {contentType} "{label}"
-- _(repeat for each usage; omit if usages array is empty — mark as "Unused / unattached")_
-
-**Subjects**: {description}  
-**Setting**: {description}  
-**Composition**: {description}  
-**Colours**: {description}  
-**Mood**: {description}  
-**Style**: {description}  
-**Constraints**: {description}
-
-**When to use**: {paragraph}
-
----
-```
-
-Repeat for every image. Group images by page/section using `## Section: {page title}` headings before each page's images, matching the structure the `audit images` output provides.
-
-### Step 5 — Write the HTML guide
-
-Output path: `docs/image-guide.html` inside the app directory.
-
-**IMPORTANT — chunked writing:** HTML files are much larger than Markdown. Use the same bash heredoc append strategy, but with **smaller batches of 15–20 image cards** per operation. Start with the full `<html>`, `<head>`, CSS, and opening body tags, then append cards in batches, then append the closing tags last.
-
-The HTML guide is a self-contained human reference (no server needed). Model it on the existing `tmp/blk-image-guide.html` style but with the following enhancements:
-
-1. **Visual detail block**: Add a new `<div class="visual-detail-box">` section in each card containing the structured visual fields (Subjects, Setting, Composition, Colours, Mood, Style, Constraints) as a compact `<table>`.
-
-2. **Usage tree**: In the metadata table, expand the `Pages` row to show the full chain: `{pageSlug} → {componentType} "{label}" (field: {fieldName})`.
-
-3. **Site tree section**: Add a collapsible `<details>` section at the top of the page titled "Full Site Content Tree" that shows the inverse view — for each page, what images appear on it.
-
-4. **LLM note**: Update the LLM usage note at the top to reference the structured visual fields.
-
-The HTML must:
-- Be fully self-contained (inline CSS, no external dependencies)
-- Work without a web server (file:// protocol)
-- Match the brand colours of the target site
-- Show thumbnail images with lazy loading
-
-### Step 6 — Verify and report
-
-After writing both files, confirm:
-1. Every image from the `audit images` output has an entry in both files
-2. The "Used on" relationships match what `audit tree` shows
-3. The Markdown file is clean and can be read without a browser
-
-Present a summary:
-
-| Image | Pages used on | Visual description added | Notes |
-|-------|--------------|--------------------------|-------|
-| ...   | ...           | ✓                        | ...   |
-
-Report the output paths and any images that had no usages (potential orphans).
-
----
-
-## Tips
-
-- **Efficient image inspection**: Fetch images in batches. Process all images for a page together before moving to the next page.
-- **Orphaned assets**: Images with no usages (`usages: []` in the JSON) are likely unused. Flag them but still document them — they may be intentionally held in reserve.
-- **SVG icons**: For SVG assets, use the direct URL (no resize params needed). Describe the graphic shape and colour precisely.
-- **Stock vs custom**: Check the filename for patterns like `AdobeStock_`, `pexels-`, `unsplash-` to identify stock images. Custom-produced images typically have branded filenames.
-- **Mobile variants**: Some components have both `visual` and `mobileVisual` fields. If the same image appears in both, note the dual-use in the description.
-
-## Related skills
-
-- **core**: Full cms-edit workflow reference
-- **alt-text-audit**: Audit and improve alt text on existing images
-- **contentful-cms-screenshots**: Take live screenshots of pages for reference

package/skills/contentful-cms/manifest.json

@@ -1,11 +0,0 @@
-{
-  "core": "Main workflow, refs, session, and all cms-edit commands",
-  "templates": "Create and edit templates (preContent, postContent, menu, footer, colours)",
-  "navigation": "Create navigation, nav open/add, set nav item fields, remove",
-  "rich-text": "Rich text (rtf) and embeds (append/insert); Markdown support",
-  "screenshots": "Screenshot command, agent-browser requirement, mock vs live, --url-only",
-  "alt-text-audit": "Audit and improve image alt text across site pages",
-  "image-guide": "Generate a comprehensive image guide (MD + HTML) with AI visual descriptions and content relationship trees",
-  "seo-descriptions": "Generate or improve SEO meta descriptions for pages",
-  "schema-org": "Generate Schema.org structured data as Mustache templates"
-}

package/skills/contentful-cms/navigation/SKILL.md

@@ -1,23 +0,0 @@
----
-name: "contentful-cms:navigation"
-description: "Create or edit navigation entries and nav items in Contentful via cms-edit."
----
-
-# Skill: contentful-cms — Navigation
-
-Use this skill when creating or editing **navigation** entries and their items in Contentful via `cms-edit`.
-
-## Workflow
-
-1. **Create** a navigation: `cms-edit create navigation --label 'Main menu'`
-2. **Open** the nav: `cms-edit nav open <slug-or-id>` (or after create, use the printed open command)
-3. **Add** items: `cms-edit nav add --label "Pricing" --slug /pricing` or `--label "Docs" --href https://docs.example.com`; use `--after @cN` to insert after a ref.
-4. **Set** nav item fields (use snapshot refs): `cms-edit set @c1 label "New label"`, `cms-edit set @c1 page <entry-id> --link`, `cms-edit set @c1 externalUrl "https://..."`.
-5. **Remove** an item: `cms-edit remove @cN`
-6. **Save**: `cms-edit save`
-
-Navigation entries are often linked from templates as **menu** or **footer**; set those with `set ... menu <nav-id> --link` from a template session.
-
-## Related skills
-
-See the **core** skill for session, refs, and all commands. For templates that use menu/footer see the **templates** skill.

package/skills/contentful-cms/rich-text/SKILL.md

@@ -1,96 +0,0 @@
----
-name: "contentful-cms:rich-text"
-description: "Edit rich-text fields and insert embedded entries/assets via cms-edit."
----
-
-# Skill: contentful-cms — Rich text and embeds
-
-Use this skill when editing **rich text** fields (body, additionalCopy) and inserting **embedded entries/assets** via `cms-edit`.
-
-## Rich text (rtf)
-
-- **Replace** body with Markdown (single paragraph, no newlines): `cms-edit rtf @c1 body "Simple body with **bold** and [link](https://example.com)."`
-- **Multiline content** — use `printf` piped to stdin; `\n` in a double-quoted shell string is **not** a newline in bash:
-  ```bash
-  printf '## Heading\n\nParagraph with **bold** and [link](https://example.com).\n' | cms-edit rtf @c1 body -
-  ```
-- Use `--file path/to/file.md` or stdin (`-`) for long content.
-- Markdown supported: headings, bold/italic, links, lists, blockquote, inline code, `---`.
-
-Use **set** for scalar and link fields; use **rtf** only for rich text fields.
-
-## Embeds (v1: append/insert only)
-
-- **Append** an embedded entry: `cms-edit rtf embed @c1 body <entry-id>`
-- **Insert** at position: `cms-edit rtf embed @c1 body <entry-id> --at 0`
-- **Raw asset** embed: `cms-edit rtf embed @c1 body <asset-id> --asset` — inserts an `embedded-asset-block` with **no** width/alignment on the block (Contentful only allows `data.target`).
-- **Width / horizontal position:** use a **Media** entry (not `--asset`). Create one with `cms-edit create media --asset-id <id> --name "…" [--position Middle] [--width 40]` (prints the new entry ID; does not replace your session), then `cms-edit rtf embed @c1 body <media-entry-id> --at 12`. Or set fields in the Contentful app. Same image, different layout in two places ⇒ two Media entries pointing at the same asset.
-
-Editing or moving existing embeds is **not supported in v1**.
-
-## rtf replace — additional flags
-
-These flags provide finer control when using `rtf replace`:
-
-| Flag | Description |
-|------|-------------|
-| `--find-plain <text>` | Alias for `--find`; treats the search string as literal text (use when the string contains `*`) |
-| `--ignore-marks` | Match across adjacent bold/plain splits within the same block node |
-| `--protect-pattern <regex>` | Skip matches that fall inside spans matching this regex (e.g. existing quidget tokens) |
-| `--dry-run` | Count matches without writing any changes |
-| `--in-table-row <n>` | Restrict matches to row N (1-indexed; row 1 = header) |
-| `--in-row-containing <text>` | Restrict to rows where any cell contains this text |
-| `--in-col-containing <text>` | Restrict to the column whose header cell contains this text |
-
-Example — replace a value only in the column whose header contains "CSP":
-```bash
-cms-edit rtf replace @c1 body \
-  --find 'None' \
-  --replace-plain '{*credit_card_id*:*5048345*,*field*:*foreign_transaction_fee*,*api*:*cc*}' \
-  --in-col-containing 'CSP' \
-  --mode all
-```
-
-## rtf patch — JSON batch find/replace
-
-Apply multiple find/replace operations in a single call. All ops are validated before any write.
-
-```bash
-# From file
-cms-edit rtf patch @c0 body --file patch.json
-
-# From stdin
-echo '[{"find":"old","replaceWith":"new","mode":"exactlyOne"}]' | cms-edit rtf patch @c0 body
-```
-
-Each op in the JSON array supports:
-
-| Key | Required | Description |
-|-----|----------|-------------|
-| `find` | yes | Search string (Markdown-interpreted) |
-| `replaceWith` | yes | Replacement string (Markdown-interpreted unless `replaceIsMarkdown: false`) |
-| `replaceIsMarkdown` | no | Set to `false` to treat `replaceWith` as plain text (like `--replace-plain`) |
-| `mode` | no | `"exactlyOne"` (default), `"all"`, `"first"` |
-| `ignoreMarks` | no | Match across adjacent bold/plain splits |
-| `inTableCol` | no | Restrict to column N (1-indexed) |
-| `inTableRow` | no | Restrict to row N (1-indexed) |
-| `inRowContaining` | no | Restrict to rows where any cell contains this text |
-| `inColContaining` | no | Restrict to the column whose header cell contains this text |
-| `section` | no | Restrict to a document section |
-| `protectPattern` | no | Skip matches inside spans matching this regex |
-
-Add `--dry-run` to count matches without writing.
-
-## rtf edit — replace field via stdin
-
-Replace an entire rich text field by piping Markdown from stdin. Avoids shell quoting issues for long content.
-
-```bash
-echo "## New heading\n\nNew body text." | cms-edit rtf edit @c1 body
-```
-
-In human (interactive) mode, the command prints the current Markdown to stdout first, then reads the replacement from stdin.
-
-## Related skills
-
-See the **core** skill for workflow, refs, and all commands.

package/skills/contentful-cms/schema-org/SKILL.md

@@ -1,74 +0,0 @@
----
-name: "Schema.org Generation"
-description: "Generate Schema.org structured data as Mustache templates for site pages and upload via cms-edit."
----
-
-# Skill: contentful-cms — Schema.org Generation
-
-Use this skill when generating **Schema.org structured data** (JSON-LD) as Mustache templates for pages and uploading via `cms-edit`. Works with any brand context skill for customer name and site URL.
-
-## Brand Context
-
-Before starting, check if a brand context skill is available. You'll need the customer name and site URL for Organisation and publisher fields in the schema templates.
-
-If no brand context is available, ask the user for these details.
-
-## Phase 1: Analyse Site Structure
-
-1. `cms-edit sitemap` to get all pages and articles
-2. For each page, use `fetch_page_markdown` (from site-workflows MCP server) to read content
-3. Categorise each page by Schema.org type:
-
-| Page Type | Likely Schema.org Type |
-|-----------|----------------------|
-| Homepage | Organization + WebSite |
-| About | AboutPage + Organization |
-| Service/Product | Service or Product |
-| Pricing | Product with Offer |
-| Blog listing | CollectionPage |
-| Article | Article or BlogPosting |
-| FAQ | FAQPage with Question/Answer |
-| Contact | ContactPage |
-| Team/People | ProfilePage or Person |
-| Case study | Article |
-| Landing page | WebPage |
-
-## Phase 2: Generate Mustache Templates
-
-Create JSON-LD templates using these standard Mustache variables:
-
-- `{{title}}` — page/article title
-- `{{seoDescription}}` — SEO meta description
-- `{{slug}}` — page slug
-- `{{publishDate}}` — article publish date
-- `{{updatedAt}}` — last modification date
-- `{{authorName}}` — article author name
-- `{{heroImageUrl}}` — primary image URL
-- `{{customerName}}` — from brand context
-- `{{siteUrl}}` — from brand context
-
-## Phase 3: Upload via cms-edit
-
-1. Check available fields:
-   - `cms-edit schema page` — page content type fields
-   - `cms-edit schema template` — template content type fields
-   - Look for `schemaOrg`, `jsonLd`, `structuredData`, or similar
-2. For **template-level** schemas (Organization, WebSite — shared): `cms-edit list --type template` → open → set
-3. For **page-level** schemas: open each page → set its schema field
-4. `cms-edit diff` then `cms-edit save`
-
-## Best Practices
-
-- Don't duplicate — template-level Organization schema covers all pages
-- Use specific types — `MedicalBusiness` over `LocalBusiness` if applicable
-- Validate all required properties are present
-- Schema must reflect actual page content
-
-## Output
-
-| Page/Template | Schema.org Type(s) | Variables Used | Applied To |
-|--------------|-------------------|---------------|-----------|
-
-## Related skills
-
-See the **core** skill for the full cms-edit workflow. See the **seo-descriptions** skill for meta description generation.

package/skills/contentful-cms/screenshots/SKILL.md

@@ -1,46 +0,0 @@
----
-name: "contentful-cms:screenshots"
-description: "Capture screenshots of components, collections, pages or persons via cms-edit."
----
-
-# Skill: contentful-cms — Screenshots
-
-Use this skill when capturing **screenshots** of components, collections, pages, or persons with `cms-edit`. **Requires agent-browser** to be installed.
-
-## Prerequisites
-
-- `npm install -g agent-browser && agent-browser install`
-- Without agent-browser, the command exits with install instructions (use `--url-only` to only print the URL).
-- For `@ref` and `--json-file`: the app must be running at `devBaseUrl` (see `.contentful-cms.json`).
-
-## Commands
-
-- **From session ref** (full-fidelity): `cms-edit screenshot @c0` — uses the convert API and `/cms/preview/render-json` so **all** entry types render with real data: component, collection, externalComponent, person. Add `--full` for full-page capture (auto-applied for component/collection).
-- **From JSON file** (no Contentful): `cms-edit screenshot --json-file path/to/entry.json` — reads an IBase* JSON (e.g. from `read @c0 --json` or an export), base64-encodes it, and opens `/cms/preview/render-json?data=...`. Use to validate or screenshot without a session or preview token.
-- **By type** (no session, mock): `cms-edit screenshot --component HeroSimple`, `cms-edit screenshot --collection CardGrid` — uses `/cms/showcase/render` with mock data.
-- **Page**: `cms-edit screenshot` (current open page) or `cms-edit screenshot /resources/publications/other/my-slug`
-- **URL only** (no agent-browser needed): `cms-edit screenshot @c0 --url-only`
-
-## Target path: use the full site path
-
-When passing a path target (e.g. `cms-edit screenshot /path`), the target must be the **full path** on the site — not just the final slug segment. cms-edit prepends `devBaseUrl` from your config to build the URL.
-
-> **Correct:** `cms-edit screenshot /resources/publications/other/my-article`
-> **Incorrect:** `cms-edit screenshot /my-article` ← will 404 if the site expects a longer path
-
-Check the site's URL structure (e.g. `/resources/publications/<type>/<slug>`) and use the complete path. The `devBaseUrl` is set in `.contentful-cms.json` (defaults to `http://localhost:3000` if not configured).
-
-## Mock vs live (type-only mode only)
-
-When using `--component <type>` or `--collection <type>` (no session), the default is **mock** (showcase). Use `--live` with a ref to prefer the legacy direct preview URL; for `@ref`, full-fidelity is already the default via convert → render-json.
-
-- **Mock:** `/cms/showcase/render` with mock data; fast, no preview token.
-- **Live** (with ref): `cms-edit screenshot @c0 --live` — uses `/cms/preview/render?id=...`; equivalent for component/collection/externalComponent to the default @ref path.
-
-## Checking your work
-
-After editing content, run `cms-edit screenshot @ref` or `cms-edit screenshot /slug` to capture and verify. Use `--out before.png` / `--out after.png` and `agent-browser diff screenshot` for visual diffing. To validate a component from exported JSON, use `cms-edit screenshot --json-file <path>`.
-
-## Related skills
-
-See the **core** skill for session, open, and snapshot.

package/skills/contentful-cms/seo-descriptions/SKILL.md

@@ -1,54 +0,0 @@
----
-name: "SEO Descriptions"
-description: "Generate or improve SEO meta descriptions for pages using cms-edit, targeting keywords with the brand voice."
----
-
-# Skill: contentful-cms — SEO Descriptions
-
-Use this skill when generating or improving **SEO meta descriptions** for pages using `cms-edit`. Works with any brand context skill for customer-specific voice and audience.
-
-## Brand Context
-
-Before starting, check if a brand context skill is available (e.g., "OM1 Brand Context"). If so, use its brand voice, target audience, SEO focus areas, and tone when writing descriptions.
-
-If no brand context is available, ask the user about their brand voice and target audience before proceeding.
-
-## Workflow
-
-1. **Get all pages**: `cms-edit sitemap`
-2. **For each page** (or a specific page):
-   a. **Read page content** using `fetch_page_markdown` (from the site-workflows MCP server) to understand what the page covers
-   b. **Check current SEO**:
-      - `cms-edit open /<slug>`
-      - `cms-edit read @page seoDescription` (or `read @page` for all fields)
-   c. **Analyse** the page — primary purpose, problem it solves, desired user action
-   d. **Generate** a meta description following the guidelines below
-   e. `cms-edit set @page seoDescription "new description"`
-   f. `cms-edit diff` then `cms-edit save`
-
-## Meta Description Guidelines
-
-1. **Length:** 150–160 characters (Google truncates at ~160)
-2. **Include the target keyword** naturally — don't stuff it
-3. **Use the brand voice** from the brand context
-4. **Include a call to action** — "Learn more", "Get started", "Discover", etc.
-5. **Be specific** — mention concrete benefits, not vague claims
-6. **Match search intent** — what would someone search to land on this page?
-7. **Avoid:**
-   - Starting with the brand name (it's in the title tag)
-   - "Welcome to..." or "This page is about..."
-   - Duplicating descriptions across pages
-   - Quotes (truncated in SERPs)
-
-## Output
-
-For each page, present:
-
-| Page | Current Description | New Description | Chars | Target Keyword |
-|------|-------------------|-----------------|-------|----------------|
-
-Then apply changes via cms-edit.
-
-## Related skills
-
-See the **core** skill for the full cms-edit workflow. See the **alt-text-audit** skill for image accessibility.

package/skills/contentful-cms/templates/SKILL.md

@@ -1,21 +0,0 @@
----
-name: "contentful-cms:templates"
-description: "Create or edit templates (preContent, postContent, menu, footer, colours) in Contentful via cms-edit."
----
-
-# Skill: contentful-cms — Templates
-
-Use this skill when creating or editing **templates** (layout shells with preContent, postContent, menu, footer) in Contentful via `cms-edit`.
-
-## Workflow
-
-1. **Create** a template: `cms-edit create template --label 'Campaign Landing'`
-2. **List** templates: `cms-edit list --type template`
-3. **Open** by ID: `cms-edit open <template-id> --id`
-4. Edit content: set **preContent** and **postContent** (content arrays) via session snapshot refs; use `add`, `set`, `remove`, `move` as for pages. Set **menu** and **footer** (single navigation links) with `cms-edit set @ref menu <nav-entry-id> --link` and same for `footer`.
-5. Set **colours**: `cms-edit set @ref backgroundColour Navy`, `cms-edit set @ref textColour White` (or project colour names).
-6. **Save**: `cms-edit save`
-
-## Related skills
-
-See the **core** skill for the full workflow (open, snapshot, set, save). For menu/footer navigation entries use the **navigation** skill.