Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →learnprompt/learnprompt-single-mdx
Create or rewrite exactly one LearnPrompt Starlight MDX tutorial to the repository's golden-sample standard, with bottom-of-page auditable sources instead of SourceCard, a research pack, evidence ledger, reproducible showcase, independent review, quality score, and successful site build.
Passed 12 of 17 test cases with the skill, and 3 of 17 without it.
and 12 more in the full report
13 fixed3 passed either way5 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
After completing the deterministic gate script and making final frontmatter updates to `quality_score`, what final build verification command must be run?
| Checked | Without skill | With skill |
|---|---|---|
| Executes npm run build inside the starlight directory | Missed | Passed |
The instructions your model reads when the skill loads.
Produce one publishable tutorial and its auditable evidence. Do not batch several chapters inside one invocation.
Before editing, read:
research/golden-samples/README.mdresearch/golden-samples/quality-rubric.mdUse an Orange Book as a topic map when relevant. Verify current product behavior with primary sources and live tools.
Record the topic, target reader, one-sentence outcome, destination MDX path, research path, non-goals, source families, showcase question, and build command.
If a missing decision would materially change the article, ask at most three focused questions. In an unattended goal, make the smallest safe assumption and record it in brief.md.
git status --short.Create research/articles/<slug>/ unless the user supplies another path. Produce:
brief.md
horizontal-research.md
vertical-research.md
test cases passed, vs 3 / 17 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.