/publish-blog

name: publish-blog
description: "Publish a blog post to WordPress or Webflow through the connected CMS MCP with SEO metadata, categories and tags, featured image, slug optimization, and optional scheduling. Runs pre-publish gates — content-scorer.py, brand-voice-scorer.py, SEO and compliance checks — and a MANDATORY approval gate: an Execution Summary the user must approve with an explicit typed yes (logged via approval-manager.py) before anything goes live, then verifies the live URL and schema markup and submits to Google Search Console if connected. Triggers on \"/digital-marketing-pro:publish-blog\", \"publish this post to WordPress\", \"push the draft live on Webflow\", \"schedule this article for Monday\", \"take this blog post live\". Reads the brand profile and platform-publishing-specs.md for CMS field mappings."
disable-model-invocation: false
argument-hint: "[--platform=wordpress|webflow]"

/digital-marketing-pro:publish-blog

Purpose

Publish a fully optimized blog post to the brand's CMS (WordPress or Webflow) with SEO metadata, categories and tags, featured image, and optional scheduling. Includes pre-publish quality checks for content scoring and brand voice alignment, plus post-publish verification to confirm the live URL is accessible and rendering correctly. Designed to be the final step in a content workflow — taking a draft from ready to live with all optimization gates enforced.

Execution gate (MANDATORY — cannot be skipped)

1. Present the full preview — recipients / spend / changes / compliance — as an **Execution Summary** before touching any live system. 2. The user must type `yes` (or an equivalent explicit approval). ANY other input — ambiguous, implied, partial, or absent approval — cancels the run. 3. Never proceed on ambiguous input. Never auto-retry a failed execution; a failure needs human review before any re-run. 4. Record the approval with `python "${CLAUDE_PLUGIN_ROOT}/scripts/approval-manager.py" --brand {slug} --action create-approval --data '{"risk_level":"<tier>","summary":"..."}'` **before** executing, then `python "${CLAUDE_PLUGIN_ROOT}/scripts/approval-manager.py" --brand {slug} --action mark-executed --id {approval_id}` after the platform confirms success.

Input Required

The user must provide (or will be prompted for):

• **Blog content**: The full blog post draft or a rough draft to refine — title, body, any inline images or embeds, and blockquotes or callout boxes
• **Target CMS platform**: Which publishing platform to use — WordPress or Webflow — must have the corresponding MCP server connected
• **Publish date**: Immediate publish or a scheduled date and time with timezone — scheduling uses the platform's native scheduling feature
• **Categories and tags**: Content categories and taxonomy tags for organization and discoverability, or allow auto-suggestion based on content analysis and existing taxonomy
• **Featured image**: Image file path, URL, or description for generation — used as the hero image and social sharing thumbnail (Open Graph and Twitter Card)
• **SEO metadata**: Primary keyword, secondary keywords, meta title (50-60 chars), meta description (150-160 chars) — or request auto-generation based on content analysis and keyword strategy
• **Author attribution**: Author name and bio link if different from the default brand author configured in the CMS
• **Slug preference**: Custom URL slug or auto-generate from the title with keyword optimization and stop-word removal
• **Internal links**: Specific internal pages to link to within the post, or allow auto-detection of linking opportunities based on existing site content
• **Social sharing text**: Custom Open Graph title and description for social previews, or auto-generate from the meta title and description
• **Content format**: Post format — standard article, listicle, how-to guide, case study, or thought leadership — determines schema markup type and structural expectations
• **Excerpt or summary**: A 1-2 sentence excerpt for archive pages, RSS feeds, and social cards, or auto-generate from the opening paragraph
• **Related posts**: Optional — specific posts to link as related content at the end of the article, or auto-detect based on category and topic overlap
• **CTA block**: Optional — custom call-to-action block to append at the end of the post (newsletter signup, product trial, content upgrade, consultation booking)

Process

1. **Load brand context**: Read `~/.claude-marketing/brands/_active-brand.json` for the active slug, then load `~/.claude-marketing/brands/{slug}/profile.json`. Apply brand voice, compliance rules for target markets (`skills/context-engine/compliance-rules.md`), and industry context. Also check for guidelines at `~/.claude-marketing/brands/{slug}/guidelines/_manifest.json` — if present, load restrictions. Check for agency SOPs at `~/.claude-marketing/sops/`. If no brand exists, ask: "Set up a brand first (/digital-marketing-pro:brand-setup)?" — or proceed with defaults. 2. **Verify CMS connection**: Check which CMS MCP server is connected (wordpress or webflow) and confirm it matches the user's target platform. If not connected, instruct the user to configure the MCP server first and provide the relevant setup link. 3. **Score content quality**: Run `content-scorer.py` on the blog draft to evaluate readability (Flesch-Kincaid grade), structure (heading hierarchy, paragraph length, list usage), depth (word count vs topic complexity), and engagement potential. Flag any issues that need fixing before publish. 4. **Score brand voice alignment**: Run `brand-voice-scorer.py` to verify the content matches the brand's tone, vocabulary, and messaging guidelines. Suggest specific edits if the score falls below the brand's minimum threshold defined in profile.json. 5. **Optimize for SEO**: Ensure the primary keyword appears in the title, H1, first 100 words, URL slug, and meta description. Verify meta description is 150-160 characters and m