agent-code-review-swarm
Agent skill for code-review-swarm - invoke with $agent-code-review-swarm
34
0%
Does it follow best practices?
Impact
98%
2.64xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-code-review-swarm/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is essentially a label with an invocation command rather than a functional description. It provides no information about what the skill does, what actions it performs, or when it should be selected. It fails on every dimension of the rubric.
Suggestions
Add concrete actions the skill performs, e.g., 'Coordinates multiple review perspectives to analyze code for bugs, security vulnerabilities, style issues, and performance problems.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks for a code review, PR feedback, code quality analysis, or wants multiple perspectives on their code changes.'
Explain what 'swarm' means in this context to distinguish it from a simple code review skill, e.g., 'Uses a multi-agent swarm approach to provide comprehensive code review from different specialist viewpoints (security, performance, readability).'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description provides no concrete actions whatsoever. It only says 'Agent skill for code-review-swarm' without describing what the skill actually does — no mention of reviewing code, finding bugs, suggesting improvements, or any other specific capability. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. There is no explanation of capabilities and no 'Use when...' clause or equivalent trigger guidance. | 1 / 3 |
Trigger Term Quality | The only potentially relevant term is 'code-review' embedded in the skill name, but there are no natural user keywords like 'review my code', 'PR review', 'code quality', 'bugs', or 'feedback'. The invocation syntax '$agent-code-review-swarm' is technical jargon, not a natural trigger. | 1 / 3 |
Distinctiveness Conflict Risk | While the name 'code-review-swarm' hints at a niche, the description itself is so vague that it provides no distinguishing information. It could easily conflict with any other code review or code analysis skill since no specific scope or triggers are defined. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is an aspirational feature catalog for a fictional tool ('npx ruv-swarm') rather than actionable guidance Claude can execute. It is extremely verbose, with most content being decorative JSON objects listing check categories and non-executable CLI commands. The lack of real tools, clear workflows, validation steps, and proper content organization makes this skill ineffective for its stated purpose.
Suggestions
Replace fictional 'npx ruv-swarm' commands with actual executable steps using real tools (gh CLI, existing linters, Claude's own analysis capabilities) that Claude can run
Reduce content to under 100 lines by removing the descriptive JSON blocks listing check categories and consolidating the agent descriptions into a brief table or list
Define a clear numbered workflow: 1) Get PR diff via gh CLI, 2) Analyze specific aspects, 3) Validate findings, 4) Post review comments, with explicit validation checkpoints between steps
Extract configuration examples, comment templates, and CI/CD integration into separate bundle files referenced from a concise overview
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Massive amounts of JSON config objects that merely list check names without actionable instructions, repetitive CLI examples with fictional tools (npx ruv-swarm), and explanatory sections like 'Best Practices' that state obvious things Claude already knows. Most content is aspirational documentation for a non-existent tool rather than lean, token-efficient guidance. | 1 / 3 |
Actionability | Nearly all code examples reference a fictional CLI tool ('npx ruv-swarm') with invented subcommands that don't exist. The JSON blocks are descriptive lists of what agents would check, not executable code. The GitHub Actions workflow and gh CLI usage have some concrete elements, but the core review functionality is entirely non-executable pseudocode dressed up as real commands. | 1 / 3 |
Workflow Clarity | There is no clear sequential workflow with validation checkpoints. The skill presents a sprawling catalog of features and agent types without defining a coherent step-by-step process for actually performing a code review. No feedback loops, no error recovery steps, no validation gates between steps. The 'quality gates' section mentions thresholds but doesn't integrate them into a workflow. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with everything inline. References to swarm-pr.md and workflow-automation.md at the bottom, but no bundle files exist. The massive inline JSON config blocks, agent descriptions, workflow YAML, and comment templates should be split into separate reference files. No clear overview-to-detail navigation structure. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (543 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- ruvnet/claude-flow
- Commit
9d4a9ea
- Reviewed
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.