Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →hashgraph-online/technical-book-lab-design
Design hands-on technical nonfiction chapters as runnable labs, worked examples, exercises, checkpoints, troubleshooting paths, and reader outcomes.
Passed 19 of 22 test cases with the skill, and 14 of 22 without it.
and 2 more in the full report
5 fixed14 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
I'm developing a hands-on tutorial for a self-hosted media server stack using Docker Compose and Caddy reverse proxy. Help me format this into a comprehensive lab module. Make sure to specify the practical reader objective and baseline software/hardware dependencies, lay out the milestone-based exercise sequence, show example command outputs for verification at each stage, provide a failure resolution matrix for common mistakes, detail teardown/cleanup actions and security considerations, and suggest related background concepts.
| Checked | Without skill | With skill |
|---|---|---|
| The response includes a section for suggested companion resources or prerequisites. | Passed | Passed |
| The response includes explicit safety notes addressing permission exposures, security warnings, or financial and data risks. | Missed | Passed |
The instructions your model reads when the skill loads.
A technical book lab is not a pile of commands. It is a guided reader transformation with a clear starting state, safe path, visible progress, expected output, and exit criteria. The reader should know what they built, why it works, how to verify it, and what to do when it fails.
Use this skill to design or improve:
| Need | Read |
|---|---|
| Core lab concepts and terminology | references/core/knowledge.md |
| Lab design rules | references/core/rules.md |
| Before/after examples | references/core/examples.md |
| Lab review checklist | references/core/checklist.md |
| Step-by-step lab design | workflows/design-runnable-lab.md |
State what the reader will be able to do, decide, deploy, debug, or explain after the lab.
If the outcome is only "learn about X," sharpen it until there is visible proof of progress.
List what the reader already has and knows:
test cases passed, vs 14 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.