# Browser Evidence

> Use when claiming a visible, responsive, interactive, scroll-led, canvas, WebGL, or animated browser result is complete and fresh evidence is needed.

- **Type:** Skill
- **Install:** `agentstack add skill-twk0672005-sentence-to-site-browser-evidence`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [twk0672005](https://agentstack.voostack.com/s/twk0672005)
- **Installs:** 0
- **Category:** [Web & Browser](https://agentstack.voostack.com/c/web-and-browser)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [twk0672005](https://github.com/twk0672005)
- **Source:** https://github.com/twk0672005/sentence-to-site/tree/main/skills/browser-evidence

## Install

```sh
agentstack add skill-twk0672005-sentence-to-site-browser-evidence
```

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

## About

# Browser Evidence

Match proof to the claim. A build, HTTP 200, or one hero screenshot does not prove mobile behavior, interaction, motion, or visual quality.

For ordinary visible work, inspect the running page and a key desktop state. Add mobile, primary flow, and serious console/page errors for responsive or interactive work. Add representative states, a short clip or multi-state frames, and fallback review for motion-led work.

Use the bundled scripts when executable browser proof is appropriate. Report `pass`, `partial`, or `blocked` exactly; a missing runtime or unsupported capability is not a successful result.

Read `../../references/evidence-and-handoff.md` and `../../references/tooling.md`. Use `../../templates/evidence-report.md` for a reviewable result.

## Source & license

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

- **Author:** [twk0672005](https://github.com/twk0672005)
- **Source:** [twk0672005/sentence-to-site](https://github.com/twk0672005/sentence-to-site)
- **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-twk0672005-sentence-to-site-browser-evidence
- Seller: https://agentstack.voostack.com/s/twk0672005
- 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%.