Estimation
11 problem-shaped skills backed by 97 sourced reasoning patterns — Curie to Toulmin, as Claude Code agents. Every claim cites its source; a pre-commit gate blocks unsourced constants. Install the gates alone in 30s (zetetic-gates). The only agent system where "I don't know" is a feature.
npx -y skills add cdeust/zetetic-team-subagents --skill estimationAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 7 stars7 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Bound it before you build it. Use when a decision is blocked by "we don't have data", an estimate looks suspiciously precise, someone asks "is this even feasible?", "how much capacity do we need?", "will this scale?", or a claimed number has never been cross-checked by a second method.
SKILL.md
2.4 KB, as published. Nobody here has run it
Estimation
Problem shape: a quantity is needed for a decision, but there is no measurement — or there is a single number with false precision and no bracket. The move is order-of-magnitude decomposition, two-sided bounds, and limits derived before methods are chosen.
Relevant geniuses
| Agent | Use when |
|---|---|
| fermi | decision blocked by missing data; single number with no bracket; feasibility check before committing resources; sanity-check a claimed figure |
| erlang | capacity planning, queue sizing, arrival-vs-service balance, latency exploding near saturation (Little's law audits) |
| thompson | "will this design survive 10x scale?" — surface-to-volume and allometric scale-break analysis |
| laplace | priors need eliciting; estimates need updating as evidence arrives; forecaster calibration is unknown |
| carnot | efficiency claims with no derived theoretical limit; "where is the irreversible loss?" |
| erdos | existence/threshold questions on large combinatorial spaces — probabilistic method instead of enumeration |
Invocation
- Pick the best-fit agent above. If two or more fit, run
tools/genius-invoker.sh route "<problem>"and take the top ranked match. - Load it:
tools/genius-invoker.sh invoke <agent> "<problem>", then readagents/genius/<agent>.mdin full. - Apply the agent's
<workflow>step by step and answer in its<output-format>. Every estimate ships as a two-sided bracket with the dominant uncertainty named — never a bare point value. - Cross-check: two independent decompositions must agree within ×10 before the estimate is used for a decision (fermi's sanity-check shape).
- If no shape above matches, use a standard team agent instead.
Refuse when
- The requester wants a precise number a bracket cannot honestly provide — say what measurement would be needed instead.
- The estimate would be quoted without its bounds.