GitHub README and Documentation Quality Audit
Test a README for clarity and accuracy.
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
[VERIFY] is an editorial flag, not a blank to fill. Wherever the prompt shows [VERIFY], check that item against a reliable source before you use it.
Audit a README and docs. Text: [README_TEXT]. Setup steps tested by a newcomer, with the problems they met: [NEWCOMER_FEEDBACK]. Run the audit in the order a newcomer meets the page: first lines, prerequisites, install, first success, next steps. For each stage quote the line, say what a reader would think or do, and mark where they would give up. Check the purpose in the first lines, accuracy of commands, missing prerequisites, unclear terms, broken links, working examples, structure and length, and accessibility basics. Score each criterion 1 to 5, quote the weakest line and rewrite it. Map each problem the newcomer met to a fix, and list problems nobody reported but that you can see, such as a command that assumes a tool is installed. Return a table and a rewritten quick start as numbered steps with the expected output after each. Do not invent commands; flag any you could not verify [VERIFY]. Be constructive and specific, and finish with a ten-minute test to repeat after each release.
Fill in before use
Optional: type your details and the prompt above updates. Nothing is saved or sent.
Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.
See an example result (fictional data)
Invented review by a newcomer. Time to first successful run: 45 minutes. Problems: prerequisites not listed (lost 15 minutes), one command used a wrong flag (10 minutes), configuration example missing (12 minutes), unclear what the output should look like (8 minutes). Total 45 minutes. Scores: purpose 4, quick start 2, configuration 2, examples 3, links 4; average 3.0. Fixes: add prerequisites list, correct the command, add a configuration example, show expected output. Target time to first run: under 10 minutes. Retest with a different newcomer.
Illustrative only, made-up data. Your results will differ and must be reviewed.