# Validate

> >

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

## Install

```sh
agentstack add skill-daddia-skills-validate
```

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

## About

# Validate

## Conventions

Read [../backlog/references/delivery-conventions.md](../backlog/references/delivery-conventions.md)
when resolving `{epic}`.

## Sub-agents

When the epic has many tasks (roughly >5) or complex Gherkin, spawn **ac-evidence-verifier**
([agents/ac-evidence-verifier.md](agents/ac-evidence-verifier.md)) to build the acceptance
matrix before writing the report and updating tasks.md.

For eval runs on skills in this repo, use root **eval-grader** (`agents/eval-grader.md`).

## Gotchas

- **Code review ≠ validate** — review judges the diff; validate judges epic done-ness vs AC.
- **Resolve slug from backlog** when user passes only an Epic ID.
- **Update tasks.md status** only with evidence; do not invent new AC.
- **Epic status in backlog** updates only when all tasks for the epic are verified.

Follow [prompts/run.prompt.md](prompts/run.prompt.md).

## Source & license

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

- **Author:** [daddia](https://github.com/daddia)
- **Source:** [daddia/skills](https://github.com/daddia/skills)
- **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-daddia-skills-validate
- Seller: https://agentstack.voostack.com/s/daddia
- 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%.