# Skill Name

> >

- **Type:** Skill
- **Install:** `agentstack add skill-neuroanalytics-data-science-harness-skill`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [neuroanalytics](https://agentstack.voostack.com/s/neuroanalytics)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [neuroanalytics](https://github.com/neuroanalytics)
- **Source:** https://github.com/neuroanalytics/data-science-harness/tree/main/templates/skill

## Install

```sh
agentstack add skill-neuroanalytics-data-science-harness-skill
```

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

## About

# Skill: skill-name

One-line statement of what invoking this skill accomplishes.

## When to use
- Bullet the situations/trigger phrases that should invoke this skill.
- Note anything that should NOT trigger it.

## Steps
1. **Understand the request** — read arguments / conversation context; ask for anything missing.
2. **Do the planning work** — the research-process judgment this skill owns (choose, record,
   organize). Read/append `project.yaml` (the append-only project log) as needed.
3. **Delegate tool work to the doer** — when a tool operation is required, hand off to the
   relevant doer subagent, e.g.:
   > Delegate to the **datalad** doer subagent: "run `` on branch `` with
   > inputs `` and outputs ``, message ``."
   Wait for the doer's result before continuing.
4. **Record the outcome** — append a log entry to `project.yaml`
   (`{ts, op, stage, note, branch?}`) describing what happened, and report back to the user.

## Constraints
- Planner skills never call a CLI directly — always delegate tool operations to a doer.
- Keep `project.yaml` append-only; do not rewrite or reorder prior entries.
- State assumptions and confirm irreversible actions before delegating them.

## Source & license

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

- **Author:** [neuroanalytics](https://github.com/neuroanalytics)
- **Source:** [neuroanalytics/data-science-harness](https://github.com/neuroanalytics/data-science-harness)
- **License:** MIT

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-neuroanalytics-data-science-harness-skill
- Seller: https://agentstack.voostack.com/s/neuroanalytics
- 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%.