estimation
Skill8 starsChanged 57 days agoMITView on GitHub
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.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- jame-hv/brse-toolkittheir own version, first seen Nov 8, 2026
- meaningfy-ws/skillerytheir own version, first seen Oct 27, 2026
- razbakov/skillstheir own version, first seen Oct 17, 2026
- yuanJewel/skillstheir own version, first seen Oct 11, 2026
- Abdox-menara/guard-skillstheir own version, first seen Aug 24, 2026
- senior-sigan/llm-skillstheir own version, first seen Apr 6, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- razbakov/skills★ 4same name
- meaningfy-ws/skillery★ 2same name
- yuanJewel/skills★ 2same name
- Abdox-menara/guard-skills★ 0same name
- jame-hv/brse-toolkit★ 0same name
- senior-sigan/llm-skills★ 0same 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
- evidence-synthesisSkill
- experience-and-transmissionSkill
- failure-forensicsSkill
- formal-correctnessSkill
- measurement-disciplineSkill
- 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
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
0
Distinctive
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 40
If no shape above matches, use a built-in agent with the closest GENIUS: pattern from rules/agent-routes.json instead.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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 built-in agent with the closest
GENIUS:pattern fromrules/agent-routes.jsoninstead.
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.
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.