Lean body with no padding about what dose-response is; every section earns its place (data-prep table, executable command, parameter table, gotchas) and assumes Claude's competence.

Provides a copy-paste-ready `tu run DoseResponse_calculate_ic50` invocation with concrete inputs/outputs, plus a real executable script (scripts/fit_dose_response.py) with usage examples and a working scipy 4PL fit.

Four clearly sequenced steps (Prepare -> Fit -> Interpret -> Quality) with explicit validation checkpoints (r^2 >= 0.95, >=4 points, IC50 within range) and feedback loops ('recommend wider concentrations', 'flag rather than forcing one IC50').

Body is a concise overview with a single one-level-deep, clearly signaled reference (scripts/fit_dose_response.py) that genuinely exists in the bundle; content is appropriately split with easy navigation.

Lists multiple concrete actions — 'IC50, EC50, Hill slope, Emax/Emin efficacy, and relative potency' and 'compare two compounds' potency' — from paired concentration vs response data, matching the highest anchor.

Explicitly answers what it does (fits 4PL, returns IC50/EC50 etc.) and when to use it ('Use when you have concentrations + responses and need a potency value, to compare two compounds' potency, or to judge curve quality'), with explicit exclusions.

Covers natural terms users would say — 'dose-response', 'concentration-response', 'IC50', 'EC50', 'drug screening', 'agonist/antagonist pharmacology' — with good breadth and variations.

Clear pharmacology niche with distinct triggers, plus explicit NOT-for clauses routing image-derived and survival/regression cases to sibling skills, minimizing misfires.