agent-repo-architect
Agent skill for repo-architect - invoke with $agent-repo-architect
Install with Tessl CLI
npx tessl i github:ruvnet/claude-flow --skill agent-repo-architect43
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 94%
↑ 4.94xAgent success when using this skill
Validation for skill structure
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is critically deficient across all dimensions. It functions more as a label than a description, providing only an invocation command without explaining what the skill does, when to use it, or what problems it solves. Users and Claude would have no basis for selecting this skill appropriately.
Suggestions
Add concrete actions describing what repo-architect does (e.g., 'Analyzes repository structure, suggests folder organization, creates architecture diagrams, refactors project layouts')
Include a 'Use when...' clause with natural trigger terms (e.g., 'Use when the user asks about repository structure, project organization, folder layout, or codebase architecture')
Remove or relocate the invocation syntax ($agent-repo-architect) as it doesn't help with skill selection and add domain-specific keywords users would naturally use
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for repo-architect' is completely abstract and does not describe what the skill actually does. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. It only provides an invocation command ($agent-repo-architect) with no explanation of capabilities or use cases. | 1 / 3 |
Trigger Term Quality | The only potential trigger term is 'repo-architect' which is a technical/internal name, not a natural keyword users would say. No natural language terms like 'repository', 'architecture', 'structure', or 'organize' are present. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it's impossible to distinguish from other skills. 'Agent skill' could apply to any agent-based functionality, and 'repo-architect' provides no clarity on scope or purpose. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill suffers from severe verbosity and poor organization. It attempts to document an entire architecture system in one file rather than providing a concise overview with references. The code examples use an unclear pseudo-syntax that isn't directly executable, and the workflow sections lack validation checkpoints for what are clearly risky multi-step operations.
Suggestions
Reduce content by 70%+ by moving architecture patterns, best practices, and detailed examples to separate reference files (e.g., PATTERNS.md, EXAMPLES.md)
Convert pseudo-JavaScript examples to actual executable CLI commands or properly formatted MCP tool calls with clear syntax
Add explicit validation steps after each major operation (e.g., 'Verify repository created: gh repo view owner/repo')
Remove obvious best practices sections that explain concepts Claude already understands (e.g., 'Clear separation of concerns', 'Maintainable documentation')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive boilerplate, repetitive patterns, and unnecessary explanations. The skill is over 300 lines when the core concepts could be conveyed in under 100. Contains redundant sections like 'Best Practices' that state obvious principles Claude already knows. | 1 / 3 |
Actionability | Provides code examples but they are pseudocode-like JavaScript that isn't directly executable (e.g., `mcp__claude-flow__swarm_init { topology: "mesh" }` syntax is unclear). Missing actual CLI commands or real executable snippets. The forEach loop and JSON.stringify examples are illustrative but not copy-paste ready. | 2 / 3 |
Workflow Clarity | Steps are listed in sequences but lack explicit validation checkpoints. The 'Complete Repository Architecture Optimization' section shows a workflow but doesn't include error handling or verification steps between operations. No feedback loops for failed operations. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All content is inline including detailed patterns, examples, and best practices that should be split into separate reference documents. The skill tries to cover too much in a single file. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.