seo-image-gen
Skill10 starsChanged 27 days agoMITView on GitHub
Generate SEO-ready images — OG/social previews, blog heroes, product shots, infographics, and favicons — at correct dimensions with SEO-aware filenames and alt text. Uses the Gemini CLI or a connected image-gen MCP/provider key when available; otherwise delivers production-ready prompts and exact specs to render elsewhere (there is no built-in renderer). Trigger when the user says "generate image", "og image", "social preview", "hero image", "product photo", "infographic", "favicon", or "create a visual".
18 other projects use a version of this.
Adopted by
Most recently taken up by
- joaoguirunas/team-ostheir own version, first seen Nov 15, 2026
- alpit-patel/seo-aeo-geo-kittheir own version, first seen Nov 8, 2026
- zhtyyx/codex-seotheir own version, first seen Nov 1, 2026
- susantedit/claude-skillstheir own version, first seen Oct 20, 2026
- webdevarif/claude-skillstheir own version, first seen Oct 20, 2026
- Solnest-AI/solnest-seo-aeotheir own version, first seen Oct 15, 2026
Used with
Projects with it also use seo-agentic, find-animation-opportunities and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
AgriciDanielSkillseo-agentic
Audit and fix agent readiness: the Lighthouse Agentic Browsing fraction, accessibility tree for agents, robots.txt and Content-Signal for AI agents, WAF treatment of agent traffic, llms.txt, Markdown delivery, ai-catalog.json, /.well-known discovery files, and WebMCP tools. Use when the user asks whether AI agents can use or browse the site, or about llms.txt or WebMCP. Exclude AI citability and brand signals (seo-geo) and commerce protocol depth (seo-ecommerce).
Also in 4 projects that use this
wxyhgkSkillfind-animation-opportunities
Search a codebase or UI for places that don't animate but should, and reject everything that shouldn't. Read-only; it proposes motion with exact values, it does not implement it. Use when the user asks "what could be animated here?" or wants to "make this feel more alive". For fixing existing animations, use improve-animations or review-animations instead.
Also in 3 projects that use this
wxyhgkSkillimprove-animations
Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the animations", "audit the motion", "make this app feel better", or wants a roadmap of animation fixes rather than a review of a single diff.
Also in 3 projects that use this
arkanSkillreview-animations
Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.
Also in 3 projects that use this
Other versions18 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 18
- AgriciDaniel/claude-seo★ 30ksame name
- zhtyyx/codex-seo★ 152same name
- joaoguirunas/team-os★ 6same name
- avalonreset/legends-seo-dungeon★ 4same name
- alpit-patel/seo-aeo-geo-kit★ 2same name
- agrivisionai/claude-skills★ 1same name
- mahiunfiltered/claude-code-skills★ 1same name
- unknownking07/claude-skills★ 1same name
- ahmedaminsa/aljazeera360-mcp-server★ 0same name
- bbeliso/belisodw-★ 0same name
8 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository46 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- blast-promptSkill
- client-outreachSkill
- content-draftSkill
- copywritingSkill
- csv-to-reportSkill
- design-accessibilitySkill
- design-buildSkill
- design-croSkill
- design-dimensionsSkill
- design-motionSkill
- design-researchSkill
- design-system-genSkill
- design-system-persistSkill
- design-tokens-emitSkill
- design-visual-qaSkill
- html-extractSkill
- parallel-buildSkill
- portable-html-portSkill
- qa-gateSkill
- route-codex-reviewSkill
- route-gemini-contextSkill
- route-three-brainSkill
- seo-auditSkill
- seo-backlinksSkill
- seo-clusterSkill
- seo-competitor-pagesSkill
- seo-content-briefSkill
- seo-contentSkill
- seo-dataforseoSkill
- seo-driftSkill
- seo-ecommerceSkill
- seo-firecrawlSkill
- seo-geoSkill
- seo-googleSkill
- seo-hreflangSkill
- seo-image-auditSkill
- seo-local-unifiedSkill
- seo-pageSkill
- seo-programmaticSkill
- seo-schemaSkill
- seo-sitemapSkill
- seo-strategySkill
- seo-sxoSkill
- seo-technicalSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 17 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 41
Detect generators: Run python3 "${CLAUDE_PLUGIN_ROOT}/scripts/workflow/capability_probe.py" and check for a connected image-gen MCP.
- Distinctive: line 43
Generate or hand off: If a generator is available, render at the preset dimensions into the user's workspace.
- Very specific: line 57
Tier 3 — Gemini CLI (preferred): If gemini is on PATH (per capability_probe.py), use it to render at the preset dimensions.
- Very specific: line 61
Tier 4 — guided (always available): If neither is present, deliver the production-ready prompts + exact specs + filenames + alt text, and …
- Distinctive: line 65
Always state which tier ran and how to enable rendering if it didn't.
“Common” is measured: kept by at least 6 in 10 of the 17 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
seo-image-gen
Family: seo Status: Stable
Purpose
The generation half of image SEO (split from the audit because it carries different legal/asset/API risk). Produces images at correct dimensions with SEO-aware presets, file naming, and suggested alt text. It is tool-aware: it renders through whatever generator you have — preferring the Gemini CLI — and, when no generator is available, still delivers production-ready prompts + exact specs + filenames + alt text so you can generate elsewhere. That prompts-and-specs output is real value on its own; it never just fails.
Triggers
- "generate image" / "create a visual"
- "og image" / "social preview"
- "hero image" / "blog image"
- "product photo" / "infographic" / "favicon"
Inputs
- Subject/prompt and brand context (palette, style — pull from a design system)
- Preset: og | hero | product | infographic | favicon
- Output path (in the user's project workspace)
Steps
- Pick the preset and resolve its spec — e.g. OG 1200×630; hero ~1600×900;
favicon set (16/32/180/512). Pull palette/style from a
design-system-genresult so generated images match the brand. - Compose the generation prompt — subject + style + palette + composition, with negative prompts to avoid unwanted text artifacts.
- Detect generators. Run
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/workflow/capability_probe.py"and check for a connected image-gen MCP. Route per the cascade below. - Generate or hand off. If a generator is available, render at the preset dimensions into the user's workspace. If none is, output the prompt + exact specs and stop with a one-line note on how to enable rendering (install the Gemini CLI or connect an image-gen MCP/provider key).
- Name + alt. SEO-friendly filename (kebab-case, descriptive) + suggested alt text per image.
- Hand to
seo-image-auditto verify generated assets pass the audit.
Capability routing
This skill follows the plugin's capability-tier cascade
(references/CAPABILITY-TIERS.md). For image generation there is no built-in Claude
renderer, so the numbers run 3 → 1 → 4 by design (the CLI is preferred over an MCP):
- Tier 3 — Gemini CLI (preferred). If
geminiis on PATH (percapability_probe.py), use it to render at the preset dimensions. - Tier 1 — image-gen MCP / provider key. Otherwise, if an image-gen MCP is
connected or a provider key is set (see
extensions/nanobanana/), render with it. - Tier 4 — guided (always available). If neither is present, deliver the
production-ready prompts + exact specs + filenames + alt text, and offer the
options to enable rendering (install
@google/gemini-cli, or connect an image MCP).
Always state which tier ran and how to enable rendering if it didn't.
Outputs
- Generated image(s) at preset dimensions (Tier 3 or Tier 1)
- Otherwise: ready-to-use prompts + exact specs + SEO filenames + suggested alt text
- A one-line "to render here, install/connect …" note when handing off
Dependencies
- Optional generator (one of): the Gemini CLI (
@google/gemini-cli, preferred), or an image-gen MCP / provider key (extensions/nanobanana/). Required only to actually render; the prompts+specs path works without any. design-system-gen(optional — for brand-matched output)scripts/workflow/capability_probe.py
Notes
You are responsible for the commercial rights to generated images; review the
model's terms (see extensions/nanobanana/README.md). Pairs with seo-image-audit.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

