Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →romainsimon/reading-rivals
Models what a competitor will do next and what happens if you respond - best response, equilibrium, and the difference between a rival who optimises perfectly and one who does not. Use before a price change or price war, when a competitor launches something, when deciding whether to match a rival's move, when analysing a market with few players, or when someone asks "what will they do if we do this".
Passed 19 of 23 test cases with the skill, and 11 of 23 without it.
and 9 more in the full report
8 fixed11 passed either way4 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 saved our market game configuration in `market.json`. What command syntax runs the game structure analysis script using the default game calculator?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies `node scripts/calc.js game market.json` as the execution command. | Missed | Passed |
The instructions your model reads when the skill loads.
The mistake is treating a competitor's behaviour as weather. It is not: they respond to you. A move evaluated against their current behaviour is evaluated against a world that will not exist once you make the move.
Three questions, in this order:
Question 3 is the one people skip, and it is where price wars come from.
- [ ] 1. Infer what they optimise, from what they have done
- [ ] 2. Build the payoff table for the moves in play
- [ ] 3. Check for a dominant strategy and an equilibrium
- [ ] 4. Check whether responses cycle
- [ ] 5. Adjust for the fact that they are not perfectly rational
- [ ] 6. Decide whether to play the game or change it
Do not assume they maximise profit. Observed behaviour reveals the objective, and a rival funded for growth, optimising for logo count, or run by someone who wants to sell in eighteen months will make moves that look irrational against a profit objective and are perfectly rational against theirs.
Method: list their last five or six visible moves and ask which objective makes all of
them sensible at once. See references/inferring-objectives.md. Getting this wrong makes
every subsequent step wrong, because you will be computing best responses to the wrong
payoff.
Two players, two to three moves each. Larger tables are not more accurate, only harder
test cases passed, vs 11 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.