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.

5,407 stars

Best use case

analyze-results is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

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

Teams using analyze-results should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/analyze-results/SKILL.md --create-dirs "https://raw.githubusercontent.com/wanshuiyin/Auto-claude-code-research-in-sleep/main/skills/analyze-results/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/analyze-results/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How analyze-results Compares

Feature / Agentanalyze-resultsStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

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

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# 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)

Related Skills

vast-gpu

5407
from wanshuiyin/Auto-claude-code-research-in-sleep

Rent, manage, and destroy GPU instances on vast.ai. Use when user says "rent gpu", "vast.ai", "rent a server", "cloud gpu", or needs on-demand GPU without owning hardware.

system-profile

5407
from wanshuiyin/Auto-claude-code-research-in-sleep

Profile a target (script, process, GPU, memory, interconnect) using external tools and code instrumentation. Produces structured performance reports with actionable recommendations. Use when user says "profile", "benchmark", "bottleneck", or wants performance analysis.

training-check

5407
from wanshuiyin/Auto-claude-code-research-in-sleep

Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running and you want automated health checks.

serverless-modal

5407
from wanshuiyin/Auto-claude-code-research-in-sleep

Run GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto scale-to-zero. Use when user says "modal run", "modal training", "modal inference", "deploy to modal", "need a GPU", "run on modal", "serverless GPU", or needs remote GPU compute.

semantic-scholar

5407
from wanshuiyin/Auto-claude-code-research-in-sleep

Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements /arxiv (preprints) with citation counts, venue metadata, and TLDR. Use when user says "search semantic scholar", "find IEEE papers", "find journal papers", "venue papers", "citation search", or wants published literature beyond arXiv preprints.

run-experiment

5407
from wanshuiyin/Auto-claude-code-research-in-sleep

Deploy and run ML experiments on local, remote, Vast.ai, or Modal serverless GPU. Use when user says "run experiment", "deploy to server", "跑实验", or needs to launch training jobs.

result-to-claim

5407
from wanshuiyin/Auto-claude-code-research-in-sleep

Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. Codex MCP evaluates results against intended claims and routes to next action (pivot, supplement, or confirm). Use after experiments finish — before writing the paper or running ablations.

research-review

5407
from wanshuiyin/Auto-claude-code-research-in-sleep

Get a deep critical review of research from GPT via Codex MCP. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.

research-refine

5407
from wanshuiyin/Auto-claude-code-research-in-sleep

Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.4 review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.

research-refine-pipeline

5407
from wanshuiyin/Auto-claude-code-research-in-sleep

Run an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from vague research direction to focused final proposal plus detailed experiment roadmap, or asks to "串起来", build a pipeline, do it end-to-end, or generate both the method and experiment plan together.

research-pipeline

5407
from wanshuiyin/Auto-claude-code-research-in-sleep

Full research pipeline: Workflow 1 (idea discovery) → implementation → Workflow 2 (auto review loop). Goes from a broad research direction all the way to a submission-ready paper. Use when user says "全流程", "full pipeline", "从找idea到投稿", "end-to-end research", or wants the complete autonomous research lifecycle.

research-lit

5407
from wanshuiyin/Auto-claude-code-research-in-sleep

Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers.