# Code Review Content

> Reviews changes to prose files (markdown, text, blog posts, docs). Focuses on voice, grammar, factual claims, dead links, and structure. Loads the project's voice or style guide when one exists. Skips linter and Actions hash verification.

- **Type:** Skill
- **Install:** `agentstack add skill-gsarig-skills-code-review-content`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [gsarig](https://agentstack.voostack.com/s/gsarig)
- **Installs:** 0
- **Category:** [Developer Tools](https://agentstack.voostack.com/c/developer-tools)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [gsarig](https://github.com/gsarig)
- **Source:** https://github.com/gsarig/skills/tree/main/skills/code-review-content

## Install

```sh
agentstack add skill-gsarig-skills-code-review-content
```

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

## About

## Steps

### 1. Source and diff

Read `~/.claude/skills/code-review/references/review-shared.md` and follow its source detection and diff fetching sections. If `--source` and the corresponding identifier args were passed, use those and skip any prompting.

### 2. Load voice reference (conditional)

If the project defines a voice or style guide (a styleguide doc, a writing-voice skill, or a CLAUDE.md section on tone), read it and apply its rules throughout the review.

### 3. Review

Read `~/.claude/skills/code-review/references/review-checklist.md` first for any general principles.

Focus on:

- Voice consistency. When a voice guide is loaded, follow its rules. Otherwise match the tone of adjacent prose.
- Grammar and tense agreement.
- Factual claims that can be verified (dates, numbers, names, attributions). Flag those you cannot verify and ask the user to confirm rather than guessing.
- Dead or wrong links. Fetch reachable URLs if helpful; flag any you cannot verify.
- Structure and flow. Section ordering, missing or redundant transitions, headings that don't match their content.
- Redundant phrasing.
- Accidental tone shifts within or across paragraphs.

Do not flag established prose-style preferences if they are already consistent with adjacent posts. Honour the common review rules in the shared doc.

### 4. Output

Format per the output section of `~/.claude/skills/code-review/references/review-shared.md`. The linter and GitHub Actions hash verification sections do not apply to content reviews; do not run those steps.

## Source & license

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

- **Author:** [gsarig](https://github.com/gsarig)
- **Source:** [gsarig/skills](https://github.com/gsarig/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-gsarig-skills-code-review-content
- Seller: https://agentstack.voostack.com/s/gsarig
- 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%.