estimate-sample-size

SkillMedia

Lets your agent calculate how many samples or repeats an experiment needs to reliably detect an effect.

Use estimate-sample-size in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add estimate-sample-size and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the estimate-sample-size skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

estimate-sample-sizeStart free
About this skill

Estimate sample/repetition requirements from detectable effect, uncertainty, power/precision target, and design structure.

What this skill tells your AI

The instructions your AI receives, as published by yogsoth-ai/de-anthropocentric-research-engine in skills/estimate-sample-size/SKILL.md and read by Ahel’s review.

Purpose

Estimate sample/repetition requirements from detectable effect, uncertainty, power/precision target, and design structure.

Input contract

required: [effect_target, uncertainty_model, power_target, design_structure]
optional: [evidence, assumptions, prior_results]
constraints: [use named scientific objects; retain provenance and missingness; $\alpha$ = 0.05 and power = 0.8 where applicable]

Procedure

  1. Validate the typed inputs and state the decision this operation must support.
  2. Apply the declared operation to the named object; record intermediate values that affect interpretation.
  3. Check boundary conditions and counterexamples, then emit the result with uncertainty and source links.

If the precision or power requirement is fixed, consider select-statistical-method as the next tactic.

Output contract

produces: [estimate_sample_size_result, evidence_trace, uncertainties]
delta_fields: [evidence_updates, uncertainties]

Quality gates

  • Inputs are named scientific objects with compatible schemas.
  • Every material result has a derivation or source reference.
  • Fixed statistical criteria remain exact where applicable: $\alpha$ 0.05 and power 0.8.

Failure and counterexamples

Return a failed operation with the violated precondition when inputs are incomplete, assumptions are unsupported, or a counterexample defeats the result.

Provenance map

  • intermediate: experiment-execution/sample-size-estimation

Signals

GitHub stars
503
Forks
42
Last commit
Sep 2026
Advanced
Item type
skill
Key
estimate-sample-size
Source
github.com/yogsoth-ai/de-anthropocentric-research-engine