foxrun-ai/foxrun / skillwright/skills/decide
decide
VerifiedDecide one choice through a door check and one resolver: two-way door, the 4-step, the algorithm, inversion, hell yes or no, and kill criteria. Use when an agent or the person must decide, size the rigor, stop something, or say no.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.6 KB |
| frameworks/algorithm.md | markdown | 1.1 KB |
| frameworks/four-step.md | markdown | 1.1 KB |
| frameworks/hell-yes.md | markdown | 766 B |
| frameworks/inversion.md | markdown | 1.1 KB |
| frameworks/kill-criteria.md | markdown | 1.1 KB |
| frameworks/two-way-door.md | markdown | 1.3 KB |
| replays/read-door-first.json | config | 255 B |
| replays/read-output-contract.json | config | 201 B |
frameworks/kill-criteria.md
View on GitHub# Kill criteria
**Source:** Annie Duke, "Quit: The Power of Knowing When to Walk Away" (2022) and "Thinking in Bets" (2018). Former professional poker player, World Series of Poker bracelet 2004.
**Use when:** something is about to start running, or is already running: an overnight run, an experiment, a tool eval, a campaign, a project. Set the stop rule before the sunk cost exists.
## The questions, in order
1. What signal would tell us this is not working? Name the signal, the number, and the date. "If by <date> we do not see <signal>, we stop."
2. Who calls it? One name.
3. What do we do the moment it fires? Stop, archive, and write the one-line lesson.
4. Already running with no kill criteria? Write them now. Then ask: knowing what we know today, would we start this? If not, stop.
5. Judge the decision by the process at the time, not the result. Good decision, bad outcome happens.
## Output
- Kill criteria: signal + number + date
- Owner:
- On fire: stop / archive / lesson
- Start it? yes / no
## Traps
- Criteria with no date. They never fire.
- Moving the goalposts when the signal fires.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |