analyze-results — Claude Code skill: analyze ML experiment results
This skill reads JSON and CSV experiment outputs, builds comparison tables and runs the statistics. Useful when you have many runs and need to know what they actually show.
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill analyze-results -a claude-codeWhat analyze-results does
The skill walks through result files in figures/, results/ or another project directory, parses JSON into structured data and assembles a comparison table. Rows hold model type, hyperparameters and data config; columns hold the primary metric, secondary metrics and the delta against baseline.
Then comes the statistics. With multiple seeds it reports mean and standard deviation and checks reproducibility. When you sweep a parameter it looks for the trend — monotonic, U-shaped or plateau — and flags outliers. Every finding gets the same shape: observation with numbers, interpretation, what it means for the research question, and which experiment would test that interpretation.
Output is a raw data table, a numbered list of key findings and suggested next experiments. If the findings look significant, the skill proposes updates to project notes or the experiment report and drafts a one- or two-sentence finding statement. It needs result files in JSON or CSV to work on — there is nothing to analyze without them.
What it helps with
- build a comparison table across runs and metrics
- compute mean and standard deviation over multiple seeds
- spot the trend when sweeping a hyperparameter
- flag outliers and suspicious results
- draft a finding statement and update the report
Example prompts for the agent
- analyze the results in
results/and compare against baseline - compute stats across seeds and check reproducibility
- compare model configs and suggest the next experiments
How to install analyze-results
1Skills CLI (Vercel)
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill analyze-results -a claude-code2Manually: put the files in place
~/.claude/skills/analyze-results/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/analyze-results/
1Skills CLI (Vercel)
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill analyze-results -a codex2Manually: put the files in place
.agents/skills/analyze-results/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill analyze-results -a cursor2Manually: put the files in place
.cursor/skills/analyze-results/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install wanshuiyin/Auto-claude-code-research-in-sleep analyze-results2Manually: put the files in place
.github/skills/analyze-results/SKILL.md1Skills CLI (Vercel)
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill analyze-results -a gemini-cli2Platform CLI
gemini skills install https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep --path skills/analyze-resultsManually: put the files in place
.devin/skills/analyze-results/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill analyze-results -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about analyze-results
How do I install analyze-results in Claude?
Run npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill analyze-results -a claude-code. The skill lands in ~/.claude/skills/analyze-results/SKILL.md.
What does analyze-results do?
It locates experiment result files, builds a comparison table, computes statistics across seeds and parameter sweeps, then writes up findings and suggests follow-up experiments.
What files does the skill need?
Results in JSON or CSV. It looks in figures/, results/ or another project directory you point it at in the argument.
Source text
SKILL.md · MIT
--- name: analyze-results description: 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)
© wanshuiyin · MIT · wanshuiyin/Auto-claude-code-research-in-sleep
