CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-code-review-swarm

Agent skill for code-review-swarm - invoke with $agent-code-review-swarm

34

2.64x
Quality

0%

Does it follow best practices?

Impact

98%

2.64x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-code-review-swarm/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

45%

Automated Code Review Pipeline Setup

CI workflow for automated PR review

Criteria
Without context
With context

PR event trigger

100%

100%

Full git history fetch

100%

100%

GH CLI auth via token

0%

100%

PR data JSON fetch

100%

100%

PR diff fetch

0%

100%

Swarm review-init command

0%

100%

PR data passed to swarm

30%

100%

Multiple review agents

100%

100%

Initial status comment

0%

100%

Conditional final review action

80%

100%

Review output posted to PR

100%

100%

96%

65%

Security-Focused PR Review Automation

Security review with severity routing

Criteria
Without context
With context

Security agent command

0%

100%

OWASP/CVE check categories

0%

100%

Suggest fixes flag

0%

100%

Critical issue detection

100%

100%

Request changes on critical

100%

100%

Security label on critical

0%

100%

Comment for non-critical

100%

100%

Severity indicator in template

0%

50%

Template sections present

25%

100%

Auth verification

0%

100%

Changed files retrieval

0%

100%

100%

73%

Code Review System Configuration for Multi-Component Platform

Review system configuration file

Criteria
Without context
With context

Correct config filename

0%

100%

Config version field

40%

100%

Auto-trigger enabled

0%

100%

Required agents

30%

100%

Optional agents

0%

100%

Security threshold blocks

37%

100%

Performance threshold warns

0%

100%

Style threshold suggests

100%

100%

Security rules

0%

100%

Performance rules

10%

100%

Architecture coupling limit

0%

100%

Architecture cohesion minimum

28%

100%

High-risk path triggers

88%

100%

Repository
ruvnet/claude-flow
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.