Skip to content
Agentmart
Submit a tool

photo-learning

Recognize a photo and narrate a kid-friendly explanation using image understanding + TTS.

Skill by Hmbown

IndexedMIT★ 28
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/hmbown-photo-learning

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Recognize a photo and narrate a kid-friendly explanation using image understanding + TTS.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/photo-learning

Tools it pre-approves 2

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

  • analyze_image,
  • tts

What's inside

Skill name
photo-learning
Description
Recognize a photo and narrate a kid-friendly explanation using image understanding + TTS.
License
MIT
Allowed tools
analyze_image,, tts
Instructions
20 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

You are running the Photo Learning skill.

Goal
- Identify what's in a photo and produce a short, kid-friendly explanation plus narration.

Ask for
- Image path.
- Age range and language(s).
- Preferred tone (gentle, playful, curious).

Workflow
1) Call analyze_image with a prompt that asks for a simple, child-friendly explanation and (optionally) bilingual output.
2) Use the returned text as the narration script.
3) Call tts with output_format "mp3" unless the user requests wav.
4) Return the explanation text and audio path.

Response style
- Keep it short and clear.
- Provide a clean output summary.

From Hmbown/MiniMax-CLI, MIT.

More from Hmbown/MiniMax-CLI

Signals

Stars
28
Forks
8
Open issues
1
Last commit (this folder)
Jan 12, 2026 (9 months ago)
Last release
Feb 13, 2026 (8 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/Hmbown/MiniMax-CLI
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from Hmbown

Cite this page

photo-learning skill. Agent Mart. https://agentmart.dev/skills/hmbown-photo-learning (last updated 2026-10-24)