Como usar
- Copie o comando e verifique o pacote antes de instalar no seu ambiente de agente.
- Consulte no original as ferramentas, credenciais e ambientes necessários.
- Descreva os dados de entrada e a entrega esperada; confira a saída com as fontes.
npx skills add https://github.com/yogsoth-ai/de-anthropocentric-research-engine --skill specify-metricsAntes de começar
- A instalação não inclui assinatura de modelo, franquia API ou acesso aos seus arquivos.
- Estrelas e instalações indicam atividade, não um teste independente de qualidade ou segurança.
Documento original do Skill
Renderizado do repositório de origem, preservando títulos, exemplos, código, tabelas, links e imagens.
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.
Provenance map
- intermediate: experiment-execution/metric-specification
