Tech Manga Explainer
Turns a tech concept into a manga tutorial; needs the separate nanobanana skill
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 30, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Jul 30, 2026 · 25f338b
⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 30, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.
The artwork could not be tested at all: the generator delegates to a separate nanobanana skill that lives in a different repository and needs a Gemini API key, and without it the script prints 'cannot find nanobanana.py' and writes no file. What does run offline is real work - the prompt builder expands a one-line scene description into a 6,283-character prompt carrying full head-to-toe consistency cards for both characters, and the bundled templates assembled a five-page 12 KB responsive HTML tutorial with no placeholders left unfilled. The written workflow is the strongest part, with a page-count formula tied to the number of core concepts, a mandatory page where the student gets it wrong and is corrected, and a lookup table mapping ninjutsu to technical concepts. Two rough edges: SKILL.md tells you to invoke the script from /mnt/skills/user/tech-manga-explainer/, a path that does not exist in a normal ~/.claude install, and the script prints the wrong character names when running its own default preset. Output is scored as no measured difference because the deliverable that matters, the images, was never produced.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 4/5
- Triggers reliably 5/5
- Output vs. baseline 5/10
- Docs & honesty 3/5
What Tech Manga Explainer does
Plans a multi-page teaching comic in which a mentor explains a technical concept to a novice, sizing the page count from the number of core concepts and requiring a page where the learner gets it wrong, then builds image prompts carrying full character-consistency cards and assembles the finished pages into a responsive HTML tutorial. Triggers on Chinese requests to explain a technology as a comic or manga tutorial, for topics like Docker, Kubernetes, RAG or Transformers. Image generation is delegated to the separate nanobanana skill and a Gemini API key, neither of which ships with this repo.
How to install Tech Manga Explainer
Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.
Commands — how to trigger Tech Manga Explainer
-
/tech-manga-explainerTurns a tech concept into a manga tutorial; needs the separate nanobanana skill
It also activates on plain-language prompts like these:
-
用漫画教学的形式给我讲解一下Kubernetes里面Pod到底是什么，要通俗易懂 -
把这篇讲Transformer原理的论文改编成一个多页的技术漫画教程，给完全新手看的 -
生成一个讲解Docker镜像和容器区别的新手漫画教程，要有师徒对话情节和配图提示词
Frequently asked questions
- Is the Tech Manga Explainer skill free?
- Yes. The skill itself is free from lqshow/claude-skills. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Tech Manga Explainer work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 30, 2026. Verdict: Works with setup. The artwork could not be tested at all: the generator delegates to a separate nanobanana skill that lives in a different repository and needs a Gemini API key, and without it the script prints 'cannot find nanobanana.py' and writes no file. What does run offline is real work - the prompt builder expands a one-line scene description into a 6,283-character prompt carrying full head-to-toe consistency cards for both characters, and the bundled templates assembled a five-page 12 KB responsive HTML tutorial with no placeholders left unfilled. The written workflow is the strongest part, with a page-count formula tied to the number of core concepts, a mandatory page where the student gets it wrong and is corrected, and a lookup table mapping ninjutsu to technical concepts. Two rough edges: SKILL.md tells you to invoke the script from /mnt/skills/user/tech-manga-explainer/, a path that does not exist in a normal ~/.claude install, and the script prints the wrong character names when running its own default preset. Output is scored as no measured difference because the deliverable that matters, the images, was never produced.
- What is the Tech Manga Explainer SkillProof Score?
- 6.8/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 3/5.
- How do I install Tech Manga Explainer?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Tech Manga Explainer with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.