# Review

> Use this skill when evaluating analyze/plan outputs before implementation, especially for feasibility, risk, security, performance, compatibility, and testability gates. It produces evidence-based pass, conditional pass, or fail conclusions.

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

## Install

```sh
agentstack add skill-colacn-agent-pipeline-review
```

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

## About

# Review

## Instructions

1. 完整执行规范见 [`references/execution-playbook.md`](references/execution-playbook.md)。落盘前若工区不存在，执行 [`scripts/bootstrap-run.sh`](scripts/bootstrap-run.sh) ``。
2. **Inputs**：`analyze` + `plan` 产出；补充人类约束（窗口、合规、性能等）。
3. **分层对照**：[`references/layering-appendix-a.md`](references/layering-appendix-a.md) + 项目 overlay（若有）。
4. **Ruling**：`通过` / `有条件通过` / `不通过`；关键发现须带证据；必改 vs 建议分离；纪律见 [`references/review-discipline.md`](references/review-discipline.md)。
5. **流水线**：[`references/workflow-pipeline.md`](references/workflow-pipeline.md)。
6. **极简需求清单闸门**：短编号需求须核对 plan 的 §0 与正文逐条可验收落点。

## On-demand references

- `references/review-discipline.md` — 五轴、验证故事、评论分级
- `references/review-gate-checklist.md`
- `references/ruling-criteria.md`
- `references/execution-playbook.md`

## When not to use

- 无 `analyze` / `plan` 可评材料且拒绝补充。
- 用户明示跳过评审（须留痕）。

## Source & license

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

- **Author:** [Colacn](https://github.com/Colacn)
- **Source:** [Colacn/agent-pipeline](https://github.com/Colacn/agent-pipeline)
- **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-colacn-agent-pipeline-review
- Seller: https://agentstack.voostack.com/s/colacn
- 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%.