dimagi-internal/ace / skills/cost-effectiveness
cost-effectiveness
UnverifiedSay and defend what a round of spend buys in a place (deaths averted, cost per death, multiple of GiveWell's bar): Connect's own programs (the CHC, MBW and KC models, in Labs' cost-effectiveness explorer), and what reaching everyone in chosen places would cost. Use when a funder asks the expected return, or before a BOTEC goes into a pitch.
Cost-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 says where each answer
comes from in Connect Labs' cost-effectiveness explorer (/labs/cea/): CEA models, or the agent tool
cea_model_run, for Connect's own programmes (CHC, MBW, KC) at any inputs, with sensitivity over the inputs you
switch on; Implementations, or the agent tool cea_opportunities (full tokens only), for what delivered
opportunities achieved: any selection by programme, partner, country or model, with its roll-up, and for one
opportunity every step and a link that opens CEA models at that opportunity's own place and price; Market size
for what it would cost to reach everyone in chosen places and where a model says it is worth it, or the agent
tool cea_market_size with model (the page's answer and its link). It fixes the inputs from the proposal, runs the scenarios, and says what
is not counted. There is no ORS tool: targeting_cost_effectiveness was removed on 11 Nov 2026, and
which components count for the Child Health Campaign is the CHC model's own vitamin A and deworming
switches (va_on, dw_on). Malaria PMC was retired on 13 Nov 2026. 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); the explorer link for each scenario (
explorer_path); 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 |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 192k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 192k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 192k | Updated | Claude CodeCodex | Verified | Install |