← LeaderboardThe Skill Leaderboard

analyze-results

Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpret experimental data.

Published by wanshuiyin ↗wanshuiyin/Auto-claude-code-research-in-sleep

Try your first task

Compare a baseline with one experimental method

Start a fresh conversation.

Use analyze-results to compare my baseline and one experimental method using the supplied JSON or CSV results. Show the raw data and comparison table, compute relative improvement on the primary metric, and report mean and standard deviation if multiple seeds are available. Give concise findings, flag suspicious results, and suggest one next experiment.

Required inputs

  • Paths to existing JSON or CSV result files.
  • The baseline and method identifiers, primary metric, and whether higher or lower values are better.
  • The research question and relevant configuration differences.

Previously published starter task based on a pinned source version; check the source and required inputs before running. Task evidence ↗

SKILL.md

name: analyze-resultsdescription: Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpret experimental data.argument-hint: "[results-path-or-description]"allowed-tools: Bash(*), Read, Grep, Glob, Write, Edit

Analyze Experiment Results

Analyze: $ARGUMENTS

Workflow

Step 1: Locate Results

Find all relevant JSON/CSV result files:

  • Check figures/, results/, or project-specific output directories
  • Parse JSON results into structured data

Step 2: Build Comparison Table

Organize results by:

  • Independent variables: model type, hyperparameters, data config
  • Dependent variables: primary metric (e.g., perplexity, accuracy, loss), secondary metrics
  • Delta vs baseline: always compute relative improvement

Step 3: Statistical Analysis

  • If multiple seeds: report mean +/- std, check reproducibility
  • If sweeping a parameter: identify trends (monotonic, U-shaped, plateau)
  • Flag outliers or suspicious results

Step 4: Generate Insights

For each finding, structure as:

  1. Observation: what the data shows (with numbers)
  2. Interpretation: why this might be happening
  3. Implication: what this means for the research question
  4. Next step: what experiment would test the interpretation

Step 5: Update Documentation

If findings are significant:

  • Propose updates to project notes or experiment reports
  • Draft a concise finding statement (1-2 sentences)

Output Format

Always include:

  1. Raw data table
  2. Key findings (numbered, concise)
  3. Suggested next experiments (if any)