yogsoth-ai/de-anthropocentric-research-engine

specify-metrics

Define primary/secondary metrics, estimands, directionality, uncertainty reporting, and decision thresholds before analysis.

ソースを見る

使い方

インストールコマンドをコピーし、自分の環境へ導入する前にソースを確認します。
必要なツール、認証情報、対応環境を原文で確認します。
入力と成果物を指定し、出力を資料と照合します。

npx skills add https://github.com/yogsoth-ai/de-anthropocentric-research-engine --skill specify-metrics

開始前の確認

導入にはモデル契約、API枠、ファイルへのアクセス許可は含まれません。
スター数や導入数は活動の指標であり、独立した品質・安全性試験ではありません。

リポジトリの原文

見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。

specify-metrics

Purpose

Define primary/secondary metrics, estimands, directionality, uncertainty reporting, and decision thresholds before analysis.

Input contract

yaml

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

Procedure

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

If estimands, metrics, and decision thresholds are fixed, consider estimate-sample-size as the next tactic.

Output contract

yaml

produces: [specify_metrics_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.