Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →romainsimon/allocating-effort
Splits scarce time, budget or traffic across competing products, channels, campaigns or variants by treating them as a multi-armed bandit - Thompson sampling over beta posteriors, with optimism for anything not yet tried enough to judge.
Passed 21 of 22 test cases with the skill, and 13 of 22 without it.
and 11 more in the full report
8 fixed13 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
We want to run our allocation analysis tool on `channels.json` with a budget of 1000, but instead of standard Thompson sampling, we want to rank and split resources based on an explicit optimistic upper bound set at the 90th percentile. What CLI command should we run?
| Checked | Without skill | With skill |
|---|---|---|
| Includes '--strategy quantile' in the CLI command. | Missed | Passed |
| Includes '--alpha 0.9' in the CLI command. | Missed | Passed |
The instructions your model reads when the skill loads.
Deciding what to work on next is a bandit problem: several options, each with an unknown payoff rate, and every unit of effort spent on one is a unit not spent learning about the others. The two failure modes are symmetric and both are common - committing everything to the current leader before you know it is the leader, and spreading effort evenly long after you do.
Thompson sampling resolves both without tuning, and its allocation has a plain-English meaning: each option gets the share of effort equal to the probability it is the best one.
- [ ] 1. Define the arms and what counts as a win
- [ ] 2. Count wins and losses honestly, including the zeros
- [ ] 3. Set priors where you genuinely know something
- [ ] 4. Run the allocation
- [ ] 5. Read the under-explored list before cutting anything
- [ ] 6. Commit the split for a fixed period, then recount
An arm is anything you allocate to: a product, a channel, an ad creative, a landing page, a content format. The win must be:
If arms have wildly different payoff sizes, this model is the wrong one: it compares rates, not values. Weight the wins by value first, or use the framing-decisions skill instead.
test cases passed, vs 13 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.