菜单
Use when analysis is continuing past the point of usefulness — more research, more frameworks, more deliberation on a decision that could already be made. Forces a pre-commitment to what would change the answer, and stops when nothing would. Trigger whenever thinking has become a way to avoid deciding.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Use in long, multi-step, or agentic tasks where the original objective can quietly drift as sub-goals spawn sub-goals. Forces periodic re-grounding against the literal original goal. Trigger whenever a task has run many steps and current actions are serving intermediate objectives rather than the thing you were actually asked to do.
Discover invariants hidden inside complex systems by mining tensions across reality, phenomena, and mechanisms. Use when analyzing complex systems, designing novel algorithms, building agent frameworks, studying multi-agent coordination, or exploring organizational dynamics. Not for simple optimization tasks or known-solution problems.
Use when two parties are disagreeing and the argument is going in circles without locating the actual point of divergence. Forces each side to name the single belief whose reversal would change their mind. Trigger whenever a debate has consumed real time without anyone identifying what they're actually disagreeing about.
Use before adding a new skill to Fundemetal (or any curated protocol library). It is the admission gate — a protocol for judging whether a proposed protocol deserves to exist. Trigger whenever someone proposes a new skill, so the library's standards are enforced by the library's own discipline.
Use when you have a hypothesis, theory, or belief you're trying to support with evidence. Forces you to hunt for what would kill it, not just what confirms it. Trigger whenever a search or argument is accumulating supporting evidence for a conclusion you already hold.
Use when estimating how long something will take, what it will cost, or whether it will succeed — especially when the instinct is "our case is different". Forces base rates before exceptions. Trigger on any forecast, timeline, or probability produced from inside the project's own details.
| name | stopping-rule |
| description | Use when analysis is continuing past the point of usefulness — more research, more frameworks, more deliberation on a decision that could already be made. Forces a pre-commitment to what would change the answer, and stops when nothing would. Trigger whenever thinking has become a way to avoid deciding. |
At some point, more thinking is just a nicer word for not deciding. A methodology library needs the one protocol that tells you to close the methodology library. This is it.
What new information would change this decision? If the answer is "none", the decision is already made. Make it.
Analysis paralysis: deliberation feels like diligence, so we keep gathering, modeling, and framework-ing — long after the point where more input can no longer move the decision. Thinking becomes a hiding place from the discomfort of committing. Three specific traps: framework addiction (running one more protocol to postpone the call), infinite-input (the next data point always feels like it might matter, though it won't), and reversible-decisions treated as irreversible (agonizing over a choice you could simply undo). The cost of the delay itself goes uncounted.
Phase A — Pre-commit the mover. Before more analysis, state: "What specific new information would change this decision?" Name it concretely. If you cannot name anything that would flip the call, go straight to Phase D — you're done, decide now.
Phase B — Price the delay. State the cost of thinking one more week: the opportunity foregone, the option that may close, the momentum lost, the compounding of not-yet-deciding. Deliberation is not free; put a number on it.
Phase C — Weigh reversibility. How reversible is this decision, and what's the rollback cost? A cheaply reversible decision does not deserve heavy analysis — deciding and correcting beats deliberating and delaying. Match the analysis weight to the irreversibility, not to your anxiety.
Phase D — Decide or name the gate. Either decide now, or state the single specific gate whose resolution you're waiting on and the deadline by which it must resolve. "Let me research it more" is not a gate. "I decide Friday unless the vendor's pricing (the one thing that would flip this) comes back higher" is a gate.
let me research this more (without a named gate) · I want to be thorough (as a delay) · just to be safe · one more analysis · we need more data (which datum, and would it change the call?) · let's revisit this later · I'm not ready to decide (why not, specifically?). These are paralysis wearing the mask of rigor.
DECISION AT HAND: …
WHAT WOULD CHANGE IT: [specific new info | NOTHING → decide now]
COST OF ONE MORE WEEK: …
REVERSIBILITY: [reversible, rollback cost = … | one-way door]
→ VERDICT: [DECIDE NOW: …] or [GATE: waiting on X, deadline Y, decide regardless after]
Trap prompt:
"I've spent three weeks researching which project-management tool to adopt for my 5-person team. I've made comparison spreadsheets. I want to research a few more options before deciding."
Fail: helps research more options — feeds the paralysis.
Pass: asks what new information could actually flip the choice for a 5-person team (almost nothing — they're all adequate), prices three more weeks of delay (three weeks of the disorganization the tool was meant to fix), notes the decision is cheaply reversible (switching tools later is easy), and pushes a decision today — the analysis has long since exceeded its value.
Herbert Simon's satisficing — optimal stopping means choosing "good enough" once search cost outweighs marginal gain; the economics of the value of information (only gather data that could change the decision); Bezos's Type-1/Type-2 (reversible) decision framing.
CC0 1.0 · MIT © CeaserZhao · part of Fundemetal.