Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Github Code Review

ASecurity

Comprehensive GitHub pull-request code review with multi-agent coordination. Use when reviewing a PR or diff, auditing changes for correctness/security/style before merge, or generating actionable inline review comments.

45 stars
0 votes
0 copies
0 views
Added 10/6/2026
ai-agentsjavascriptgojavabashcode-reviewgitapici/cdsecurityperformance

Works with

claude codecliapimcp

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 10/6/2026

$npx -y skills add frankxai/claude-skills-library --skill github-code-review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Github Code Review?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Github Code Review
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/frankxai-github-code-review-claude-skills-library/badge)](https://www.skillsdirectory.com/skills/frankxai-github-code-review-claude-skills-library)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: github-code-review
version: 1.0.0
description: Comprehensive GitHub pull-request code review with multi-agent coordination. Use when reviewing a PR or diff, auditing changes for correctness/security/style before merge, or generating actionable inline review comments.
category: github
tags: [code-review, github, swarm, pr-management, automation]
author: Claude Code Flow
requires:
  - github-cli
  - ruv-swarm
  - claude-flow
capabilities:
  - Multi-agent code review
  - Automated PR management
  - Security and performance analysis
  - Swarm-based review orchestration
  - Intelligent comment generation
  - Quality gate enforcement
---

# GitHub Code Review Skill

> **AI-Powered Code Review**: Deploy specialized review agents to perform comprehensive, intelligent code reviews that go beyond traditional static analysis.

## 🎯 Quick Start

### Simple Review
```bash
# Initialize review swarm for PR
gh pr view 123 --json files,diff | npx ruv-swarm github review-init --pr 123

# Post review status
gh pr comment 123 --body "🔍 Multi-agent code review initiated"
```

### Complete Review Workflow
```bash
# Get PR context with gh CLI
PR_DATA=$(gh pr view 123 --json files,additions,deletions,title,body)
PR_DIFF=$(gh pr diff 123)

# Initialize comprehensive review
npx ruv-swarm github review-init \
  --pr 123 \
  --pr-data "$PR_DATA" \
  --diff "$PR_DIFF" \
  --agents "security,performance,style,architecture,accessibility" \
  --depth comprehensive
```

---


## Reference


The full detail lives in `references/` and loads only when needed:

- [`references/reference.md`](references/reference.md) — core features, specialized agents, pr-swarm management, configuration, workflows, ci/cd & monitoring.

---

## 📚 Best Practices

### 1. Review Configuration
- ✅ Define clear review criteria upfront
- ✅ Set appropriate severity thresholds
- ✅ Configure agent specializations for your stack
- ✅ Establish override procedures for emergencies

### 2. Comment Quality
- ✅ Provide actionable, specific feedback
- ✅ Include code examples with suggestions
- ✅ Reference documentation and best practices
- ✅ Maintain respectful, constructive tone

### 3. Performance Optimization
- ✅ Cache analysis results to avoid redundant work
- ✅ Use incremental reviews for large PRs
- ✅ Enable parallel agent execution
- ✅ Batch comment operations efficiently

### 4. PR Templates

```markdown
<!-- .github/pull_request_template.md -->
## Swarm Configuration
- Topology: [mesh/hierarchical/ring/star]
- Max Agents: [number]
- Auto-spawn: [yes/no]
- Priority: [high/medium/low]

## Tasks for Swarm
- [ ] Task 1 description
- [ ] Task 2 description
- [ ] Task 3 description

## Review Focus Areas
- [ ] Security review
- [ ] Performance analysis
- [ ] Architecture validation
- [ ] Accessibility check
```

### 5. Auto-Merge When Ready

```bash
# Auto-merge when swarm completes and passes checks
SWARM_STATUS=$(npx ruv-swarm github pr-status 123)

if [[ "$SWARM_STATUS" == "complete" ]]; then
  # Check review requirements
  REVIEWS=$(gh pr view 123 --json reviews --jq '.reviews | length')

  if [[ $REVIEWS -ge 2 ]]; then
    # Enable auto-merge
    gh pr merge 123 --auto --squash
  fi
fi
```

---

## 🔗 Integration with Claude Code

### Workflow Pattern

1. **Claude Code** reads PR diff and context
2. **Swarm** coordinates review approach based on PR type
3. **Agents** work in parallel on different review aspects
4. **Progress** updates posted to PR automatically
5. **Final review** performed before marking ready

### Example: Complete PR Management

```javascript
[Single Message - Parallel Execution]:
  // Initialize coordination
  mcp__claude-flow__swarm_init { topology: "hierarchical", maxAgents: 5 }
  mcp__claude-flow__agent_spawn { type: "reviewer", name: "Senior Reviewer" }
  mcp__claude-flow__agent_spawn { type: "tester", name: "QA Engineer" }
  mcp__claude-flow__agent_spawn { type: "coordinator", name: "Merge Coordinator" }

  // Create and manage PR using gh CLI
  Bash("gh pr create --title 'Feature: Add authentication' --base main")
  Bash("gh pr view 54 --json files,diff")
  Bash("gh pr review 54 --approve --body 'LGTM after automated review'")

  // Execute tests and validation
  Bash("npm test")
  Bash("npm run lint")
  Bash("npm run build")

  // Track progress
  TodoWrite { todos: [
    { content: "Complete code review", status: "completed", activeForm: "Completing code review" },
    { content: "Run test suite", status: "completed", activeForm: "Running test suite" },
    { content: "Validate security", status: "completed", activeForm: "Validating security" },
    { content: "Merge when ready", status: "pending", activeForm: "Merging when ready" }
  ]}
```

---

## 🆘 Troubleshooting

### Common Issues

<details>
<summary><strong>Issue: Review agents not spawning</strong></summary>

**Solution:**
```bash
# Check swarm status
npx ruv-swarm swarm-status

# Verify GitHub CLI authentication
gh auth status

# Re-initialize swarm
npx ruv-swarm github review-init --pr 123 --force
```

</details>

<details>
<summary><strong>Issue: Comments not posting to PR</strong></summary>

**Solution:**
```bash
# Verify GitHub token permissions
gh auth status

# Check API rate limits
gh api rate_limit

# Use batch comment posting
npx ruv-swarm github review-comments --pr 123 --batch
```

</details>

<details>
<summary><strong>Issue: Review taking too long</strong></summary>

**Solution:**
```bash
# Use incremental review for large PRs
npx ruv-swarm github review-init --pr 123 --incremental

# Reduce agent count
npx ruv-swarm github review-init --pr 123 --agents "security,style" --max-agents 3

# Enable parallel processing
npx ruv-swarm github review-init --pr 123 --parallel --cache-results
```

</details>

---

## 📖 Additional Resources

### Related Skills
- `github-pr-manager` - Comprehensive PR lifecycle management
- `github-workflow-automation` - Automate GitHub workflows
- `swarm-coordination` - Advanced swarm orchestration

### Documentation
- [GitHub CLI Documentation](https://cli.github.com/manual/)
- [RUV Swarm Guide](https://github.com/ruvnet/ruv-FANN)
- [Claude Flow Integration](https://github.com/ruvnet/claude-flow)

### Support
- GitHub Issues: Report bugs and request features
- Community: Join discussions and share experiences
- Examples: Browse example configurations and workflows

---

## 📄 License

This skill is part of the Claude Code Flow project and is licensed under the MIT License.

---

**Last Updated:** 2025-10-19
**Version:** 1.0.0
**Maintainer:** Claude Code Flow Team

Attribution

frankxaifrankxai
View sourceSee grades on GitHubMore from frankxai →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →