measurement-discipline
Skill8 starsChanged 59 days agoMITView on GitHub
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.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- Avarok-Cybersecurity/atlastheir own version, first seen Oct 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- Avarok-Cybersecurity/atlas★ 705same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- boundary-designSkill
- causal-auditSkill
- decision-bias-checkSkill
- estimationSkill
- evidence-synthesisSkill
- experience-and-transmissionSkill
- failure-forensicsSkill
- formal-correctnessSkill
- narrative-sensemakingSkill
- normative-designSkill
- problem-reframingSkill
- representation-and-possibilitySkill
- structure-discoverySkill
- systems-leverageSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 41
If no shape above matches, do not force a genius — use a built-in agent with the closest GENIUS: pattern (rules/agent-routes.json, INDEX.md …
- Distinctive: line 46
No reproduction or raw data exists — measurement discipline audits instruments, it does not invent readings.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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 built-in agent with the closest
GENIUS:pattern (rules/agent-routes.json, 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".
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.