New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Stat Result Validator

by aiming-lab in aiming-lab/AutoResearchClaw

Validate statistical research outputs for formulation quality, method-to- problem alignment, theory presence, experimental evidence, fair comparison, artifact completeness, and final-claim…

MITAuto-check passed

Install Stat Result Validator

skills CLI
$ npx skills add aiming-lab/AutoResearchClaw --skill stat-result-validator -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install aiming-lab/AutoResearchClaw stat-result-validator --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/aiming-lab/AutoResearchClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/external/agents/stat_research_agent/skills/stat-result-validator .claude/skills/stat-result-validator && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
stat-result-validator
GitHub stars
15k
Token cost
~951 tokens
SKILL.md length
329 words
Files
1
Skills in repo
34
Repo updated
First seen
Licence
MIT

At a glance

Validate statistical research outputs for formulation quality, method-to- problem alignment, theory presence, experimental evidence, fair comparison, artifact completeness, and final-claim…

  • SKILL.md covers Overview, Artifact Checks, Formulation Checks and Method Checks, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Stat Result Validator is an agent skill from aiming-lab/AutoResearchClaw. Validate statistical research outputs for formulation quality, method-to- problem alignment, theory presence, experimental evidence, fair comparison, artifact completeness, and final-claim consistency.

Its SKILL.md is about 950 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞. The licence is MIT.

Example prompts

  • “/stat-result-validator”

What it can do on your machine

Read from SKILL.md and the folder at commit be4ba47. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Stat Result Validator loads about 951 tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 329 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~56
When it runs · the whole SKILL.md, loaded when a task matches
~951

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from aiming-lab/AutoResearchClaw at commit be4ba47, republished under its MIT licence (© aiming-lab). 329 words, ~951 tokens.

Download SKILL.mdSave it as .claude/skills/stat-result-validator/SKILL.md (or your agent's skills folder).
name
stat-result-validator
description
Validate statistical research outputs for formulation quality, method-to- problem alignment, theory presence, experimental evidence, fair comparison, artifact completeness, and final-claim consistency.
metadata.category
domain
metadata.trigger-keywords
validation,audit,formulation,theory,comparison,claims,statistical sanity,quality gate
metadata.applicable-stages
10,11,12,13,14,15,16,17,20
metadata.priority
1

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/<TOPIC_ID>/step0_problem_formulation.md
progress/<TOPIC_ID>/step1_method_proposal.md
progress/<TOPIC_ID>/step2_theory_analysis.md
progress/<TOPIC_ID>/step3_experimental_evaluation.md
progress/<TOPIC_ID>/step4_comparison.md
progress/<TOPIC_ID>/step5_result_synthesis.md
progress/<TOPIC_ID>/step6_quality_audit.md
experiments/<TOPIC_ID>/config.yaml
experiments/<TOPIC_ID>/results/metrics.json
experiments/<TOPIC_ID>/results/run_manifest.json
experiments/<TOPIC_ID>/results/comparison_summary.md
experiments/<TOPIC_ID>/results/claim_verdicts.json
experiments/<TOPIC_ID>/report/paper.md
experiments/<TOPIC_ID>/README.md

Analysis-specific source files and raw outputs are determined by the experiment plan and should live under experiments/<TOPIC_ID>/src/ and experiments/<TOPIC_ID>/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:

  • Definitions and assumptions.
  • Proposition, theorem, derivation, counterexample, or clearly labeled heuristic analysis.
  • Predicted empirical patterns.
  • Limitations and regimes not covered.

Blocking failures:

  • No theory section at all.
  • Theory analyzes a different target than the formulation.
  • Final claims are stronger than the theory supports.

Experimental Evidence Checks

Check that:

  • Experiments test the formulated claims.
  • Conditions are aligned with assumptions and stress tests.
  • Proposed method, baselines, and ablations are run on comparable conditions.
  • Failure counts are recorded.
  • Runtime reductions are recorded in run_manifest.json.
  • Metrics are grouped at the right level.

Comparison Checks

Verify that:

  • Comparisons include proposed method vs baseline.
  • Ablations are interpreted.
  • Experimental patterns are compared with theoretical predictions.
  • Disagreements between theory and experiments are discussed.
  • Claim verdicts cite both theoretical and empirical support when available.

Final Claim Checks

Every final claim must be traceable to:

text
formulation -> method -> theory -> experiment -> comparison

Use:

  • PASS: formulation, theory, experiments, and comparisons support the claims.
  • WARN: usable but has limitations that must be disclosed.
  • FAIL: missing formulation, theory, evidence, or fair comparison prevents a valid conclusion.

© aiming-lab, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in external/agents/stat_research_agent/skills/stat-result-validator of aiming-lab/AutoResearchClaw.

Open the folder on GitHubat commit be4ba47

Compare with similar skills

Stat Result Validator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Stat Result Validator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Stat Result Validator this skillaiming-lab/AutoResearchClaw15k—~951Automated safety check: PassMIT
Analytical Method Validation PlannerK-Dense-AI/scientific-agent-skills48k1 repos~4.9kAutomated safety check: NotesMIT
Quant Statistical MethodsHKUDS/Vibe-Trading35k—~4kAutomated safety check: PassMIT
Output Validationbenchflow-ai/skillsbench1.8k—~462Automated safety check: PassApache-2.0
Video Template Frame Pentagram Statnexu-io/open-design100k—~381Automated safety check: PassApache-2.0
Statistical PowerK-Dense-AI/scientific-agent-skills48k1 repos~4.4kAutomated safety check: NotesMIT

Similar skills

  • Analytical Method Validation Planner

    K-Dense-AI/scientific-agent-skills

    Plans, runs, and documents analytical method validation, verification, or transfer studies under ICH Q2(R2)/Q14, USP, ICH M10, CLSI EP, or ISO/IEC 17025.

    48k GitHub starsUsed in 1 repo~4.9k tokens
    Research & ScienceAuto-check: notes

  • Quant Statistical Methods

    HKUDS/Vibe-Trading

    Guides your agent through unit-root, cointegration, GARCH, bootstrap and regression-diagnostic tests on financial time series, using a tested helper module.

    35k GitHub stars~4k tokensUpdated yesterday
    Data & AnalyticsAuto-check passed

  • Output Validation

    benchflow-ai/skillsbench

    Local self-check of instructions and mask outputs (format/range/consistency) without using GT.

    1.8k GitHub stars~462 tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed

  • Video Template Frame Pentagram Stat

    nexu-io/open-design

    Use this plugin when the user wants a "Pentagram Stat Frame" HyperFrames motion video — Swiss-grid statistic anchor — giant number, red accent, growing bars, black data bar.

    100k GitHub stars~381 tokensUpdated today
    Media & CreativeAuto-check passed

  • Statistical Power

    K-Dense-AI/scientific-agent-skills

    Calculates sample sizes and statistical power for study planning.

    48k GitHub starsUsed in 1 repo~4.4k tokens
    Research & ScienceAuto-check: notes

  • Form Validation

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing templates, rendered HTML, or shared components related to Validate forms accessibly.

    74k GitHub stars~633 tokensUpdated yesterday
    Frontend & DesignAuto-check passed

More from aiming-lab/AutoResearchClaw

All 34 skills in this repo

  • A-Evolve Agent Improvement

    aiming-lab/AutoResearchClaw

    Diagnoses where an agent failed across runs and turns the findings into new skills, system prompt patches and knowledge entries, using the A-Evolve loop.

    15k GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed

  • Metabolic Study Planner

    aiming-lab/AutoResearchClaw

    Turns a broad metabolic modelling topic into a concrete, paper-shaped plan with organism, model, perturbations, metrics and figures before any FBA code is written.

    15k GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check passed

  • MFA Pipeline Orchestrator

    aiming-lab/AutoResearchClaw

    Runs a metabolic flux analysis from model loading to phenotype prediction and figures by handing work to four sub-agents in sequence.

    15k GitHub stars~923 tokensUpdated 1 mo ago
    Auto-check passed

  • Qiskit 2.x Quantum ML Reference

    aiming-lab/AutoResearchClaw

    Reference patterns for writing qiskit 2.x code for variational quantum machine learning: feature maps, VQC training, VQE for chemistry, MPS circuits and noise models.

    15k GitHub stars~4.7k tokensUpdated 1 mo ago
    Auto-check passed

  • Genome-Scale Metabolic Model Builder

    aiming-lab/AutoResearchClaw

    Builds or loads a genome-scale metabolic model in COBRApy, sets its growth medium and objective, and exports it as a validated JSON file for flux analysis.

    15k GitHub stars~1.4k tokensUpdated 1 mo ago
    Auto-check passed

  • Biopython Bioinformatics

    aiming-lab/AutoResearchClaw

    Quick reference for Biopython work: sequence operations, SeqIO file parsing, BLAST searches, Entrez queries, phylogenetic trees and PDB structure analysis.

    15k GitHub stars~810 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Stat Result Validator

What does Stat Result Validator do?

Validate statistical research outputs for formulation quality, method-to- problem alignment, theory presence, experimental evidence, fair comparison, artifact completeness, and final-claim…. Stat Result Validator is an agent skill from aiming-lab/AutoResearchClaw. Validate statistical research outputs for formulation quality, method-to- problem alignment, theory presence, experimental evidence, fair comparison, artifact completeness, and final-claim consistency.

How do I install Stat Result Validator in Claude Code?

Run `npx skills add aiming-lab/AutoResearchClaw --skill stat-result-validator -a claude-code`. Or copy the skill folder (external/agents/stat_research_agent/skills/stat-result-validator in aiming-lab/AutoResearchClaw) into .claude/skills/stat-result-validator in your project. Claude Code loads it when a task matches its description.

How do I install Stat Result Validator in Codex?

Run `npx skills add aiming-lab/AutoResearchClaw --skill stat-result-validator -a codex`. Or copy the skill folder (external/agents/stat_research_agent/skills/stat-result-validator in aiming-lab/AutoResearchClaw) into .agents/skills/stat-result-validator in your project. Codex loads it when a task matches its description.

Can I use Stat Result Validator in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aiming-lab/AutoResearchClaw --skill stat-result-validator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/stat-result-validator, .gemini/skills/stat-result-validator, .github/skills/stat-result-validator and .opencode/skills/stat-result-validator in your project.

What does Stat Result Validator need to run?

SKILL.md names no scripts, command-line tools or credentials: Stat Result Validator is instructions for the agent only.

Does Stat Result Validator access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Stat Result Validator safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Stat Result Validator use?

Stat Result Validator is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Stat Result Validator use?

About 951 tokens (SKILL.md is roughly 3.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Stat Result Validator?

Skills that share tags, products or a category with Stat Result Validator: Analytical Method Validation Planner (K-Dense-AI/scientific-agent-skills, 48k stars), Quant Statistical Methods (HKUDS/Vibe-Trading, 35k stars), Output Validation (benchflow-ai/skillsbench, 1.8k stars) and Video Template Frame Pentagram Stat (nexu-io/open-design, 100k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Stat Result Validator?

aiming-lab (a GitHub organization) maintains it in aiming-lab/AutoResearchClaw, which has 14,587 GitHub stars. The repository holds 34 skills in this directory. The repository was last updated on August 19, 2026.

Source: aiming-lab/AutoResearchClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.