github-code-review
Comprehensive GitHub code review with AI-powered swarm coordination
Install with Tessl CLI
npx tessl i github:ruvnet/agentic-flow --skill github-code-review38
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Evaluation results
94%
60%Automated Code Review Infrastructure for a Fintech Repository
Repository review infrastructure setup
Required agents in config
37%
100%
Optional agents in config
0%
100%
Security threshold blocks
100%
100%
Performance threshold warns
100%
100%
Style threshold suggests
0%
100%
Auth/payment/admin trigger
62%
100%
API/database/cache trigger
62%
100%
UI path trigger
0%
0%
review-all in workflow
0%
100%
Workflow fetches PR data and diff
50%
100%
Conditional approve or request-changes
0%
100%
PR template swarm config section
0%
100%
PR template tasks checklist
0%
100%
Setup script fetches PR context
50%
100%
Setup script posts initial status
0%
66%
Without context: $0.7700 · 3m 30s · 28 turns · 34 in / 13,747 out tokens
With context: $0.8477 · 3m 14s · 24 turns · 281 in / 12,494 out tokens
68%
68%Security Code Review Script for Sensitive Code Paths
Security severity-based PR handling
Uses review-security command
0%
100%
Full check suite
0%
100%
Suggest-fixes flag
0%
100%
Fetches changed files via gh
0%
100%
Critical issues request changes
0%
100%
Security label on critical
0%
100%
Non-critical posts comment
0%
100%
No-color diff flag
0%
0%
Inline comment via gh api
0%
0%
Constructive comment style
0%
0%
Without context: $0.4139 · 2m 32s · 19 turns · 25 in / 8,557 out tokens
With context: $0.5775 · 1m 57s · 21 turns · 278 in / 6,171 out tokens
94%
59%Smart PR Orchestration with Custom API Versioning Reviewer
Dynamic swarm topology and custom review agent
Ring topology for small PRs
0%
100%
Mesh topology for medium PRs
50%
100%
Hierarchical topology for large PRs
100%
100%
Label-to-agent mapping
37%
75%
Auto-merge checks swarm status
0%
100%
Auto-merge requires 2 reviews
100%
62%
Auto-merge uses squash
100%
100%
Custom agent async review method
25%
100%
Issue objects have required fields
25%
100%
Register agent with ruv-swarm
0%
100%
Create swarm from PR via pipe
0%
88%
Auto-spawn from labels
0%
100%
Without context: $1.1868 · 4m 26s · 46 turns · 2,521 in / 15,661 out tokens
With context: $0.6718 · 2m 13s · 24 turns · 281 in / 7,407 out tokens
- Evaluated
- Agent
- Claude Code
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.