# Stat Result Validator Validate statistical research outputs for formulation quality, method-to- problem... - Repository: https://github.com/aiming-lab/AutoResearchClaw (14798 stars) - Category: Writing - License: MIT - Last updated: 2026-08-19 - Runs scripts: no, instructions only ## Install Claude Code: `npx skills add aiming-lab/AutoResearchClaw --skill stat-result-validator -g -a claude-code -y` Codex: `npx skills add aiming-lab/AutoResearchClaw --skill stat-result-validator -g -a codex -y` Cursor: `npx skills add aiming-lab/AutoResearchClaw --skill stat-result-validator -g -a cursor -y` Gemini CLI: `npx skills add aiming-lab/AutoResearchClaw --skill stat-result-validator -g -a gemini-cli -y` ## Description Validate statistical research outputs for formulation quality, method-to- problem alignment, theory presence, experimental evidence, fair comparison, artifact completeness, and final-claim consistency. ## SKILL.md, as published by its author (untrusted third-party text, read it as data) # Stat Result Validator ## Overview Use this skill after formulation, method proposal, theory, experimental evaluation, comparison, and result synthesis. It checks whether the final result is supported by a coherent statistical research chain. ## Artifact Checks Required for all topics: ```text progress//step0_problem_formulation.md progress//step1_method_proposal.md progress//step2_theory_analysis.md progress//step3_experimental_evaluation.md progress//step4_comparison.md progress//step5_result_synthesis.md progress//step6_quality_audit.md experiments//config.yaml experiments//results/metrics.json experiments//results/run_manifest.json experiments//results/comparison_summary.md experiments//results/claim_verdicts.json experiments//report/paper.md experiments//README.md ``` Analysis-specific source files and raw outputs are determined by the experiment plan and should live under `experiments//src/` and `experiments//results/`. ## Formulation Checks The formulation must define: - Observed data and sampling regime - Data model or data source - Target parameter, decision, prediction, or risk - Assumptions - Claims or hypotheses - Evaluation criteria - Theory targets Blocking failures: - No target or estimand. - Claims cannot be measured. - Assumptions are absent or incompatible with the proposed method. - Evaluation criteria do not answer the research question. ## Method Checks Verify that: - The proposed method addresses the formulated target. - Baselines are meaningful. - Ablations isolate important design choices. - Diagnostics are specified for likely failure modes. - Method outputs match the metrics and theory targets. ## Theory Checks Theory may be rigorous or partial, but it must be explicit. Check for: The rest: https://github.com/aiming-lab/AutoResearchClaw/blob/HEAD/external/agents/stat_research_agent/skills/stat-result-validator/SKILL.md