Find image for blog post

VerifiedSafe

Find and suggest appropriate images for blog posts, provide search links, filenames, and proper HTML markup with descriptive alt text.

Sby Skills Guide Bot
ContentBeginner
7/26/2026
Claude Code
#images#blog#stock-photos#alt-text#html-markup

Recommended for

Automated summary

Helps find royalty-free images for a blog post and generates the matching <figure> HTML markup, filename, and accessible alt text.

Strengths

  • Provides direct search links to Unsplash, Pexels, Pixabay, and Undraw
  • Outputs complete HTML markup with WCAG 2.1 AA-friendly alt text kept under 125 characters
  • Enforces a descriptive lowercase-hyphenated filename convention
  • Restates project constraints: /assets/images/ location, WebP/PNG/JPG formats, 500KB max size
  • Suggests diagram tools (Excalidraw, Draw.io, Mermaid) for technical content

Limitations

  • Does not download or embed the image itself — it only returns search links and copy-paste markup
  • Relies on web search, so results may be off-target and licensing still needs manual confirmation
  • The sample figcaption is a fixed humorous placeholder that must be replaced by hand
When to use it

Use it when a writer asks for an image, a stock photo, or visuals to illustrate a blog post.

When not to use it

Skip it if you need a custom-generated image, automatic download and insertion, or a definitive license check.

Security analysis

Safe
Quality score80/100

The skill is purely instructional: it directs the agent to suggest stock-image search links, filenames, and figure HTML. There are no destructive shell commands, no credential or token handling, no obfuscated payloads, and no attempts to disable safety behavior. Network use is limited to recommending search URLs on well-known stock-photo sites, which is a low-risk, legitimate purpose.

No concerns found

How this analysis is made

Examples

AI agents blog post
Find me a good hero image for my blog post about building AI agents with Claude, and give me the HTML to paste in.
Security article visual
I need a stock photo for a post on GDPR-compliant logging in Python — suggest a filename and alt text too.
Technical diagram
What tool should I use to draw an architecture diagram for my blog post, and how should I caption it?

name: find-image description: Find and suggest images for blog posts. Use when the user asks to find images, needs a picture, wants stock photos, or is looking for visuals for their blog post.

Find Image for Blog Post

Help the user find appropriate images for their blog posts and generate the proper HTML markup.

Instructions

  1. Understand the context: Ask or determine what the blog post is about

  2. Search for images: Use web search to find relevant free stock images from sources like:

    • Unsplash (https://unsplash.com) - High-quality free photos
    • Pexels (https://pexels.com) - Free stock photos and videos
    • Pixabay (https://pixabay.com) - Free images and royalty-free stock
    • Undraw (https://undraw.co) - Free illustrations for tech/business
  3. Provide search links: Give the user direct search URLs to find images

  4. Suggest filenames: Propose descriptive filenames following the convention:

    • Use lowercase with hyphens
    • Be descriptive (e.g., gdpr-logging-architecture-diagram.png)
    • Include the main topic
  5. Generate HTML markup: Provide the complete figure HTML with:

    • Proper alt text (descriptive, WCAG 2.1 AA compliant, under 125 chars)
    • Standard figcaption

Image Guidelines (from project standards)

  • Location: /assets/images/
  • Preferred formats: WebP (best compression), PNG (diagrams/screenshots), JPG (photos)
  • Max size: < 500KB (images are auto-optimized via pre-commit hook)
  • Alt text requirements:
    • Be descriptive and specific
    • Relate to surrounding content
    • Aim for 125 characters or less
    • Don't start with "Image of" or "Picture of"
    • Include relevant keywords naturally

Output Format

When suggesting an image, provide:

  1. Search links for finding the image:
Unsplash: https://unsplash.com/s/photos/[search-term]
Pexels: https://www.pexels.com/search/[search-term]/
  1. Suggested filename:
[topic]-[description].webp
  1. HTML markup to use:
<figure>
  <img src="/assets/images/[filename]" alt="[Descriptive alt text]">
  <figcaption>This is what AI thinks an image for this blog should look like...</figcaption>
</figure>

Examples

Example 1: AI Development Post

User asks for an image for a post about "Building AI Agents with Claude"

Search links:

  • Unsplash: https://unsplash.com/s/photos/artificial-intelligence-robot
  • Pexels: https://www.pexels.com/search/artificial%20intelligence/

Suggested filename: claude-ai-agent-development.webp

HTML markup:

<figure>
  <img src="/assets/images/claude-ai-agent-development.webp" alt="Abstract visualization of AI neural network connections representing intelligent agent systems">
  <figcaption>This is what AI thinks an image for this blog should look like...</figcaption>
</figure>

Example 2: Python Security Post

User asks for an image for a post about "GDPR-Compliant Logging in Python"

Search links:

  • Unsplash: https://unsplash.com/s/photos/data-security-privacy
  • Pexels: https://www.pexels.com/search/data%20protection/

Suggested filename: gdpr-python-logging-security.webp

HTML markup:

<figure>
  <img src="/assets/images/gdpr-python-logging-security.webp" alt="Secure data protection concept with lock symbol representing GDPR privacy compliance">
  <figcaption>This is what AI thinks an image for this blog should look like...</figcaption>
</figure>

Technical Diagrams

For technical content, also suggest tools to create diagrams:

  • Excalidraw (https://excalidraw.com) - Hand-drawn style diagrams
  • Draw.io (https://draw.io) - Professional flowcharts and architecture diagrams
  • Mermaid (in markdown) - Code-based diagrams

For diagrams, use a specific figcaption describing what the diagram shows instead of the standard AI humor caption.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/find-image-for-blog-post-ms1aw5v8/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/find-image-for-blog-post-ms1aw5v8' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/find-image-for-blog-post-ms1aw5v8/download' --output '.skill-downloads/find-image-for-blog-post-ms1aw5v8/SKILL.md.part' && mv '.skill-downloads/find-image-for-blog-post-ms1aw5v8/SKILL.md.part' '.skill-downloads/find-image-for-blog-post-ms1aw5v8/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/find-image-for-blog-post-ms1aw5v8/SKILL.md' && test -s '.skill-downloads/find-image-for-blog-post-ms1aw5v8/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/find-image' && cp -R '.skill-downloads/find-image-for-blog-post-ms1aw5v8' '.claude/skills/find-image'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/find-image-for-blog-post-ms1aw5v8'

openskills read 'find-image-for-blog-post-ms1aw5v8'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/find-image-for-blog-post-ms1aw5v8/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills