blog-enhance

Analyzes blog drafts and builds interactive Prismic slice enhancements with a preview page.

2|Updated Mar 21, 2026
One-click install
npx skills add https://github.com/ghoshsam/claude-code-skills --skill blog-enhance-ghoshsam
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: blog-enhance
Source: https://github.com/ghoshsam/claude-code-skills/tree/main/skills/blog-enhance
Command: npx skills add https://github.com/ghoshsam/claude-code-skills --skill blog-enhance-ghoshsam

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning long-form blog posts into engaging interactive essays requires deciding which sections deserve visual treatment, choosing the right component for each, and producing correctly shaped slice data — a slow, error-prone manual process. ## Core Features & Use Cases - Two-phase workflow: First explores the content and presents 2-3 visual treatment options per section (researched against the swipe file, existing site pages, and the slice catalog), then builds only the treatments the user selects. - Slice data generation: Produces exact data objects for 10 slice types (toggles, expandable tables, comparison grids, assessments, accordions, system diagrams, pyramids, timelines, code blocks) with strict StructuredText span validation. - Preview page output: Writes a ready-to-view Next.js preview page at app/blog/preview-enhance so enhancements can be reviewed in the browser before integration. - Use Case: Paste a draft blog post, review proposed interactive treatments per section, pick your favorites, and get a working preview page with correctly typed slice data. ## Quick Start Run /blog-enhance with a draft file path, a Prismic UID, or pasted content to get visual treatment options for each section.

Frequently Asked Questions about blog-enhance

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add interactive elements to a blog post draft?

Provide the draft as a file path, Prismic UID, or pasted content. The skill breaks the post into sections, proposes 2-3 visual treatment options per section, and builds only the ones you select into a preview page.

What input formats does blog-enhance accept?

Three input modes are supported: a local file path to a draft, a Prismic document UID prefixed with uid:, or content pasted directly inline into the conversation.

Which interactive slice types are available for blog enhancements?

Ten slice types exist: interactive toggle, expandable table, comparison table (2 and 3 column), self-assessment checklist, default and structured accordions, system diagram, investment pyramid, process timeline, and code block.

Why does my slice render incorrectly in the preview page?

Most render failures come from wrong data shapes: StructuredText span offsets that exceed text length, strings instead of booleans for flags like is_critical, arrays instead of comma-separated strings in system diagrams, or a mismatched variation name.

What happens when no existing slice fits the content?

The skill flags the section as needing a new slice and describes the interaction model. You can then simplify it to the closest existing slice, send it to a Gemini sandbox for prototyping, or skip it.