# Review

> Review all pending changes on the current branch: diff, unpushed commits, linters, tests, a fresh-context adversarial pass, and a structured report. Use when the user asks to review pending changes or before declaring work done.

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

## Install

```sh
agentstack add skill-srrenks-prometheus-ai-review
```

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

## About

Review all pending changes on the current branch:
1. git diff - show the full diff
2. git log @{u}..HEAD - commits not yet pushed
3. Run linters on all changed files
4. Run tests for all changed packages/modules
5. Fresh-context review: delegate the diff (or a structured summary of it) to a subagent that does not share this conversation. Instruct it to hunt for bugs, overreach beyond the request, missing tests, unintended changes, and comment noise - not to praise the work. Fix anything it finds that is valid.
6. Report: summary of changes, any lint warnings, test results, fresh-review findings, files touched

## Source & license

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

- **Author:** [SrRenks](https://github.com/SrRenks)
- **Source:** [SrRenks/prometheus-ai](https://github.com/SrRenks/prometheus-ai)
- **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-srrenks-prometheus-ai-review
- Seller: https://agentstack.voostack.com/s/srrenks
- 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%.