cost-effectiveness
Say and defend what a round of spend buys in a place (deaths averted, cost per death, multiple of GiveWell's bar) for ORS/zinc or malaria PMC. Use when a funder asks the expected return, or before a B
SKILL.mdskills/cost-effectiveness/SKILL.md
GitHubCost-effectiveness
The method lives in the GiveWell project, not here. It is the shared skill
cost-effectiveness of the canopy workspace project connect/givewell, so every agent and
person values Connect programs the same way. Load it and follow it:
project_skill "connect/givewell" "cost-effectiveness"
(mcp__plugin_canopy_projects__project_skill, from the canopy plugin.) It picks the Connect Labs
tool per intervention (targeting_cost_effectiveness for ORS/zinc, targeting_pmc_rank and
targeting_pmc_run_model for PMC), fixes the inputs from the proposal, runs the scenarios, and
says what is not counted. The same project holds GiveWell's own models and values (cea) and
the review a figure needs before it goes to GiveWell (givewell-review). Change the method there,
never by copying it back into this file.
In an ACE run
- Products: the tool's answer for each scenario, in the run folder; a short defence (the
headline at the price the funder judges by, the weakest input, what survives an argument, what
is not counted); for PMC, the
explorer_pathat that price; and the Sheet, viabuild-targeting-model, which gets a Cost-effectiveness sheet with live formulas. - Auto: run the scenarios, write the defence, hand off to
build-targeting-model. - Review: stop after the defence for the operator to confirm the scenarios before anything is built.
Change Log
| Date | Change | Author |
|---|---|---|
| 2026-10-25 | Method moved to the GiveWell project's shared cost-effectiveness skill (connect/givewell); this file keeps ACE's products and modes |
Eva |