# Skill With Scripts

> Use this skill for local agent tasks that benefit from small helper scripts, templates and basic checks.

- **Type:** Skill
- **Install:** `agentstack add skill-podcast72-agent-skill-starter-kit-skill-with-scripts`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Podcast72](https://agentstack.voostack.com/s/podcast72)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Podcast72](https://github.com/Podcast72)
- **Source:** https://github.com/Podcast72/agent-skill-starter-kit/tree/main/examples/skill-with-scripts

## Install

```sh
agentstack add skill-podcast72-agent-skill-starter-kit-skill-with-scripts
```

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

## About

# Skill With Scripts

## Activation

Use this skill when a local task benefits from small repeatable helpers and a structured report.

## Scope

- Local agent tasks with clear boundaries.
- Small documentation or code changes.
- Optional checks before completion.

## Helpers

- `scripts/mode_detect.py` can classify the request into a simple working mode.
- `scripts/scope_guard.py` can validate whether a target path stays inside an allowed root.
- `scripts/report_check.py` can validate the final report structure.
- `templates/final_report.md` provides a reusable report shape.
- `checks/validate_skill.py` validates the example folder structure.

## Rules

- Scripts are helpers, not replacements for judgment.
- Use scripts for repeatable checks.
- Use the agent for reasoning, interpretation and decisions.
- Keep edits scoped to the approved folder.
- Report what was changed and what was not checked.

## Final Report

Use `templates/final_report.md` as the preferred report structure.

## Source & license

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

- **Author:** [Podcast72](https://github.com/Podcast72)
- **Source:** [Podcast72/agent-skill-starter-kit](https://github.com/Podcast72/agent-skill-starter-kit)
- **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-podcast72-agent-skill-starter-kit-skill-with-scripts
- Seller: https://agentstack.voostack.com/s/podcast72
- 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%.