blog-image

AI image generation and editing for blog content powered by Gemini via MCP. Generates hero images, inline illustrations, social preview cards, and OG images, and edits existing ones. Supports 6 domain modes (Editorial, Product, Landscape, UI/Web, Infographic, Abstract). Works standalone or internally from blog-write and blog-rewrite; falls back gracefully when MCP is unavailable. Use when user says "blog image", "generate hero image", "blog illustration", "edit blog image", "OG image".

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable and well-structured, with executable code, concrete MCP tooling, clear sequenced workflows, and explicit validation/retry checkpoints, all backed by real, correctly-signaled reference and script bundles. The only weakness is minor redundancy between the two aspect-ratio tables.

Suggestions

Consolidate the aspect-ratio guidance so it appears in one place; the "Blog Image Types" table and the "Set Aspect Ratio" table (Step 4) overlap and could be merged or cross-referenced.

Consider relocating the time-sensitive model-ID and shutdown-date notes (e.g. the 2026-06-25 preview-ID shutdown) into a clearly labeled deprecated/old-patterns section so they do not crowd the active workflow.

Dimension	Reasoning	Score
Conciseness	The body is dense with tables, executable commands, and templates with no padding of concepts Claude already knows, but the aspect-ratio information appears redundantly across the "Blog Image Types" and "Set Aspect Ratio" tables and could be consolidated.	4 / 5
Actionability	Executable ImageMagick commands, concrete MCP tool tables, exact prompt templates with placeholders, specific model IDs, and setup commands with flags make the guidance fully copy-paste-ready across generate/edit/setup.	5 / 5
Workflow Clarity	The generation workflow is a clear 7-step sequence with explicit validation checkpoints (MCP availability check, validate_image_setup.py, the safety auto-rephrase retry loop capped at 3 attempts) and an error-handling table mapping errors to resolutions.	5 / 5
Progressive Disclosure	The body is an overview pointing to three real reference files (prompt-engineering-blog.md, gemini-models.md, mcp-tools.md) and two real scripts, all one level deep, clearly signaled inline, and consolidated in a "Reference Documentation" section with an explicit load-on-demand directive.	5 / 5
	Total	19 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is exemplary: it names concrete capabilities, enumerates six domain modes, scopes to blog content, includes an explicit "Use when user says" trigger clause with natural synonyms, and uses third-person voice throughout. It answers both "what" and "when" clearly.

Dimension	Reasoning	Score
Specificity	"Generates hero images, inline illustrations, social preview cards, and OG images, and edits existing ones" plus "Supports 6 domain modes (Editorial, Product, Landscape, UI/Web, Infographic, Abstract)" lists multiple specific concrete actions with comprehensive coverage.	5 / 5
Completeness	It explicitly answers both "what" (image generation/editing for blog content, named types and 6 modes) and "when" (a "Use when user says..." clause with concrete trigger phrases), matching the 5 anchor.	5 / 5
Trigger Term Quality	"Use when user says 'blog image', 'generate hero image', 'blog illustration', 'edit blog image', 'OG image'" gives comprehensive coverage of natural user-speech phrases including synonyms; these are phrases a user would naturally say.	5 / 5
Distinctiveness Conflict Risk	"AI image generation and editing for blog content powered by Gemini via MCP" with blog-scoped quoted triggers carves a clear niche with distinct triggers and minimal conflict risk against general image skills.	5 / 5
	Total	20 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: AgriciDaniel/claude-blog
Path: skills/blog-image/SKILL.md
Commit: 84f7abf

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.