Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →romainsimon/stress-testing-plans
Validates a plan before committing to it - checks whether the ranking survives the assumptions, finds the most likely way it fails, and makes the trade-offs explicit via a Pareto frontier instead of an invented single score. Use before a launch, price change, migration, infrastructure change or major commitment, when running a premortem, when two objectives conflict, or when a decision depends on an assumption nobody has tested.
Passed 21 of 22 test cases with the skill, and 10 of 22 without it.
and 17 more in the full report
12 fixed9 passed either way0 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
A full immediate rollout of our core database redesign carries a high likelihood of downtime. To address this risk, the team wants to introduce a phased canary deployment plan with an automated kill-switch. Which of the five standard response options does this intervention represent?
| Checked | Without skill | With skill |
|---|---|---|
| Categorizes adding staged rollouts as changing the action space. | Missed | Passed |
The instructions your model reads when the skill loads.
A plan is optimized against a model of the world. The model is wrong. Validation asks three questions, in this order:
The governing principle: plan with a simple model, evaluate with a rich one. A simple planning model resists overfitting to assumptions you cannot verify. The evaluation model can be as elaborate as you can justify, because nothing is being fitted to it.
- [ ] 1. List the assumptions the plan depends on
- [ ] 2. Score each option under each plausible variant
- [ ] 3. Check whether the ranking survives
- [ ] 4. Find the most likely failure and read it back
- [ ] 5. Make the trade-off explicit
- [ ] 6. Pick a response from the fixed menu
Not risks. Assumptions: quantities the plan's ranking depends on and which you have not measured. Churn stays flat. The infra bill scales linearly. Conversion holds at the new price. No rival ships a free tier.
Keep the ones where a plausible alternative value is materially different. Three to five is the working range; more and the matrix becomes unreadable.
Build a matrix of option by scenario and run:
node scripts/calc.js robust plan.json
test cases passed, vs 10 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.