Analyze results
Skill OleksiiDotsenko/test-builder/plugins/test-builder/skills/analyze-results
Claude Code plugin for educators: evidence-based test construction — blueprints, Bloom matrices, item writing by format rules, review checklists, and classroom psychometrics (P-value, D-index, Rit, distractor analysis).
npx -y skills add OleksiiDotsenko/test-builder --skill analyze-resultsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 27 days oldThe repository was created 27 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Compute item statistics (P-value, D-index, Rit, distractor analysis) from a response CSV. Explicit shortcut into the test-builder analysis mode.
SKILL.md
1.0 KB, as published. Nobody here has run it
Read ${CLAUDE_PLUGIN_ROOT}/skills/test-builder/SKILL.md and follow its
analysis mode (Steps 8–10).
Response data: $ARGUMENTS
(a CSV path — rows = takers, columns = items, plus a KEY row with the
correct answers; or an already-scored 0/1/points matrix, then add --scored).
From the user's project directory, run:
python3 "${CLAUDE_PLUGIN_ROOT}/skills/test-builder/scripts/psychometrics.py" <csv> --out report.md
Then interpret the report against the guide's interval tables in
${CLAUDE_PLUGIN_ROOT}/skills/test-builder/references/psychometrics.md:
per-item verdicts (bank / revise / retire), dead distractors, negative
discrimination, keying anomalies, whole-test reliability, and whether the
test was too hard or too easy for this group. State the small-sample caveat
when n < 20.