{"slug":"stijnman-experiment-results-analysis","source_name":"stijnman/experiment-results-analysis","name":"Stijnman/Experiment Results Analysis","description":"Analyze completed experiment results with effect sizes, uncertainty, guardrails, limitations, and evidence-based next steps. Use for: experiment results, A/B test analysis, test readout, experiment decision.","version":1,"lift":{"pass_rate_delta_pts":40.91,"pass_rate_pct":90.9,"total_cases":22,"passed_cases":20,"tokens_delta_pct":15.5,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-09-04T00:42:24.381441+00:00"},"skill_score":0.9091,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":40.91,"with_pass_pct":90.9,"without_pass_pct":50,"tokens_delta_pct":15.5,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-09-04T00:42:24.381441+00:00","run_id":"5e1bb42b-8041-470c-b2f3-ffe12efc74eb","latest_attempt":{"id":"5e1bb42b-8041-470c-b2f3-ffe12efc74eb","runner_model":"gemini-3.6-flash","overall_verdict":"mixed","completed_at":"2026-09-04T00:42:24.381441+00:00","gate":null},"version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"Apache-2.0","install_count":1,"total_uses":0,"total_users":0,"manifest_hash":"dc34364281a36992e4292ab2c262a7f11fb470e87fee72595a51cb9e93ec6346","install_name":"stijnman-experiment-results-analysis","version_id":"4faf8be3-5b11-4bbd-8c0f-01863816fb8d","body_sha256":"dc34364281a36992e4292ab2c262a7f11fb470e87fee72595a51cb9e93ec6346","render_hash":"ded7b68677b3b3e52eb135fb3ce32611fd8b269490ef8409b20951a68c7c25c9","raw_url":"https://app.decimal.ai/s/stijnman-experiment-results-analysis/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/stijnman-experiment-results-analysis"}