agent-repo-architect
Agent skill for repo-architect - invoke with $agent-repo-architect
39
7%
Does it follow best practices?
Impact
94%
4.94xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-repo-architect/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 is an extremely weak description that fails on every dimension. It provides no information about what the skill does, when to use it, or what user requests should trigger it. It reads as a placeholder rather than a functional skill description.
Suggestions
Add concrete actions describing what repo-architect does (e.g., 'Analyzes repository structure, generates architecture diagrams, suggests project organization patterns').
Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when the user asks about repository structure, project architecture, codebase organization, or folder layout').
Remove the invocation instruction ('invoke with $agent-repo-architect') from the description, as it is operational detail not useful for skill selection, and replace it with capability and trigger information.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. It only names a tool ('repo-architect') without describing what it does. 'Agent skill for repo-architect' is entirely vague. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. The description only provides an invocation command ('$agent-repo-architect') but no explanation of capabilities or usage triggers. | 1 / 3 |
Trigger Term Quality | The only potentially relevant term is 'repo-architect', which is a tool name, not a natural keyword a user would say. There are no natural language trigger terms like 'repository structure', 'project layout', 'architecture', etc. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it's impossible to distinguish it from any other skill. Without knowing what 'repo-architect' does, it could conflict with any repository, architecture, or code-related skill. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
14%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is excessively verbose, hardcoded to a specific user's repositories, and lacks the validation/verification steps critical for the destructive operations it describes (pushing files, creating repos, cross-repo synchronization). The code examples use non-standard syntax that isn't clearly executable, and much of the content consists of generic best practices and placeholder strings rather than actionable guidance. The monolithic structure makes it difficult to navigate or maintain.
Suggestions
Cut content by at least 60%: remove generic best practices Claude already knows, eliminate placeholder strings like '[Architecture documentation]', and remove the monitoring/metrics section which is purely aspirational.
Add explicit validation steps after every destructive operation (repo creation, file pushing, cross-repo sync) - e.g., verify the push succeeded, validate YAML/JSON syntax before pushing, check that created repos are accessible.
Split into multiple files: keep SKILL.md as a concise overview with links to separate files for architecture patterns (PATTERNS.md), template examples (TEMPLATES.md), and batch operations (BATCH-OPS.md).
Replace hardcoded user-specific paths and repo names with parameterized placeholders that make the skill reusable, and ensure code examples use valid, executable syntax rather than pseudo-JavaScript.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. Contains extensive placeholder content ('[Integration issue template]', '[Standardized PR template]'), hardcoded user-specific paths ('$workspaces$ruv-FANN$claude-code-flow'), and lengthy code blocks that are more illustrative than instructive. The best practices and monitoring sections are generic bullet points Claude already knows. Much of this could be cut by 70%+. | 1 / 3 |
Actionability | Contains concrete tool calls and code examples with specific MCP tool invocations, but many are pseudocode-like (JavaScript with non-standard syntax like `mcp__claude-flow__swarm_init { topology: "mesh" }`), hardcoded to a specific user's repos (ruvnet), and include placeholder content like '[GitHub modes template]' and '[Architecture documentation]' rather than actual executable content. | 2 / 3 |
Workflow Clarity | Despite having numbered sections, there are no validation checkpoints, no error handling, no feedback loops for any of the batch/destructive operations (pushing files to repos, creating repositories, cross-repo synchronization). The 'Complete Repository Architecture Optimization' batch operation marks todos as 'completed' before they're actually done. No verification that pushed files are valid or that operations succeeded. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with everything inline. No references to external files despite the content being far too long for a single skill file. Architecture patterns, best practices, monitoring metrics, and integration details could all be split into separate reference files. The document tries to be both an overview and a comprehensive reference, succeeding at neither. | 1 / 3 |
Total | 5 / 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.
- Repository
- ruvnet/claude-flow
- Commit
f547cec
- 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.