# Experiment Tracking

> Track ML experiments systematically with MLflow, W&B, or similar tools. Use when running experiments, comparing model versions, or managing reproducibility.

- **Type:** Skill
- **Install:** `agentstack add skill-ihatesea69-kiro-kit-experiment-tracking`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ihatesea69](https://agentstack.voostack.com/s/ihatesea69)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [ihatesea69](https://github.com/ihatesea69)
- **Source:** https://github.com/ihatesea69/kiro-kit/tree/main/.kiro/skills/experiment-tracking
- **Website:** https://www.npmjs.com/package/kiro-kit

## Install

```sh
agentstack add skill-ihatesea69-kiro-kit-experiment-tracking
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Experiment Tracking

Activate this skill when managing ML experiments and reproducibility.

## When to Use

- Logging hyperparameters and metrics
- Comparing experiment runs
- Tracking model artifacts and versions
- Reproducing previous results
- Sharing experiment results with team

## Tools

- **MLflow**: Open-source, self-hosted
- **Weights & Biases**: Cloud-hosted, rich UI
- **DVC**: Git-based data/model versioning
- **Neptune.ai**: Metadata management

## Patterns

```python
import mlflow

mlflow.set_experiment("text-classification")

with mlflow.start_run(run_name="bert-base-lr3e5"):
    mlflow.log_params({
        "model": "bert-base-uncased",
        "lr": 3e-5,
        "epochs": 10,
        "batch_size": 32,
    })
    # Training...
    mlflow.log_metrics({"val_f1": 0.89, "val_loss": 0.34})
    mlflow.log_artifact("confusion_matrix.png")
    mlflow.transformers.log_model(model, "model")
```

## Rules

- Log everything: params, metrics, artifacts, environment
- Use meaningful run names and tags
- Track data versions alongside model versions
- Set random seeds and log them
- Never delete experiment history

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [ihatesea69](https://github.com/ihatesea69)
- **Source:** [ihatesea69/kiro-kit](https://github.com/ihatesea69/kiro-kit)
- **License:** MIT
- **Homepage:** https://www.npmjs.com/package/kiro-kit

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-ihatesea69-kiro-kit-experiment-tracking
- Seller: https://agentstack.voostack.com/s/ihatesea69
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.