Measurement discipline
Skill cdeust/zetetic-team-subagents/skills/measurement-discipline
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 measurement-disciplineAssembled 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
Fix the instrument before trusting the number. Use when someone says "the metric improved but I don't trust it", "measured more than the parts predict", "we want to improve X but nothing reads X", "the numbers don't add up", "requests/money/time are disappearing", or a measurement may perturb the system it measures.
SKILL.md
2.9 KB, as published. Nobody here has run it
Measurement Discipline
Problem shape: a quantity is being read, improved, or argued about, but the instrument, the unit, or the conservation ledger behind it has never been audited. Symptoms: residuals outside noise, metrics without operational definitions, inputs and outputs that don't balance, observer effects, one-method-only results.
Relevant geniuses
| Agent | Use when |
|---|---|
| curie | measured > predicted from known parts; instrument missing or unit undefined; measurement may perturb the system (Heisenbugs, observability overhead) |
| shannon | "improving X" where X has no formal definition; method proposed without knowing the theoretical limit; a metric with no repeatable procedure |
| lavoisier | money, data, requests, or time "disappearing"; inputs and outputs never balanced; the residual needs a name and a carrier |
| galileo | phenomenon obscured by secondary effects; too fast/large/rare to observe directly; qualitative claims that need a number |
| einstein | a concept in the metric has no measurement procedure; the rule gives different answers from different viewpoints |
| deming | reacting to noise as if it were signal — common vs special cause not separated |
| ekman | a "subjective" domain needs objective coding; signal hides below normal temporal resolution; per-subject baselines missing |
| wu | a "law" or assumption everyone trusts has never actually been tested; increased precision could refute it |
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 — do not skip steps — and answer in its<output-format>. - Chain when the problem spans shapes (e.g. lavoisier finds the residual,
curie isolates its carrier):
tools/genius-invoker.sh compose lavoisier curie -- "<problem>". - If no shape above matches, do not force a genius — use a standard team agent (INDEX.md routing rule).
Refuse when
- No reproduction or raw data exists — measurement discipline audits instruments, it does not invent readings.
- The request is "make the metric look better" rather than "make the metric true".