Agent Skills
› wanshuiyin/Auto-claude-code-research-in-sleep
› analyze-results
analyze-results
GitHub分析机器学习实验结果，定位数据并构建对比表，执行统计分析与异常检测，生成包含观察、解释及下一步建议的洞察报告，辅助科研决策。
Trigger Scenarios
analyze results
compare
interpret experimental data
Install
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill analyze-results -g -y
SKILL.md
Frontmatter
{
"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.",
"allowed-tools": "Bash(*), Read, Grep, Glob, Write, Edit",
"argument-hint": "[results-path-or-description]"
}
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:
- Observation: what the data shows (with numbers)
- Interpretation: why this might be happening
- Implication: what this means for the research question
- 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:
- Raw data table
- Key findings (numbered, concise)
- Suggested next experiments (if any)
Version History
- 53562a7 Current 2026-07-25 10:39
