agent-base-template-generator
Agent skill for base-template-generator - invoke with $agent-base-template-generator
38
6%
Does it follow best practices?
Impact
94%
1.01xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-base-template-generator/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 rather than a functional description. It provides no information about what the skill does, what triggers should activate it, or how it differs from other skills. It fails on every dimension of the rubric.
Suggestions
Describe the concrete actions the skill performs, e.g., 'Generates base project templates for [specific framework/language], including directory structure, configuration files, and boilerplate code.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to scaffold a new project, create a starter template, or set up boilerplate for [specific technology].'
Specify what types of templates are generated and for what domain to distinguish this skill from other template or code generation skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for base-template-generator' is entirely vague—it doesn't describe what the skill actually does, what templates it generates, or what domain it operates in. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. There is no 'Use when...' clause, no description of capabilities, and no explicit trigger guidance. | 1 / 3 |
Trigger Term Quality | There are no natural keywords a user would say. 'base-template-generator' is an internal tool name, not a term users would naturally use in a request. No domain-specific or action-oriented trigger terms are present. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it's impossible to distinguish this skill from any other template-related or code-generation skill. 'Base template generator' could overlap with countless other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
12%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a persona description rather than an actionable skill. It tells Claude what kind of agent it should be and lists abstract responsibilities, but provides zero concrete templates, code examples, file structures, or executable guidance. The content is verbose, explaining concepts Claude already understands (like TypeScript types, error handling, and best practices), while failing to provide the actual novel information that would make this skill useful.
Suggestions
Replace abstract descriptions with concrete, executable template examples (e.g., an actual React component template, an actual API endpoint template) that Claude can use as starting points.
Remove the persona description and category lists that describe general software engineering knowledge Claude already has, and focus on project-specific patterns, conventions, or template structures that are unique to this codebase.
Add a quick-start section showing a specific input/output example: given a request like 'create a React component', show the exact file structure and code that should be generated.
If there are project-specific conventions or patterns referenced (e.g., CLAUDE.md guidelines, SPARC methodology), either inline the key rules or provide clear one-level-deep references to those files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive explanations of general concepts Claude already knows. Lists of categories, quality standards, and responsibilities are largely redundant descriptions of good software engineering practices rather than specific, novel instructions. The content reads like a job description rather than a concise skill. | 1 / 3 |
Actionability | No concrete code examples, no executable commands, no specific templates or patterns. Everything is abstract description ('Generate comprehensive base templates', 'Include proper TypeScript definitions') without any actual template code, file structures, or copy-paste-ready content. | 1 / 3 |
Workflow Clarity | There is a numbered 5-step 'template generation approach' that provides a sequence (Analyze Requirements → Apply Best Practices → Structure Foundation → Include Essentials → Enable Extension → Provide Context), but it lacks any validation checkpoints, concrete commands, or feedback loops. The steps are abstract rather than actionable. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files, no clear navigation structure, and no separation of overview from detailed content. Everything is dumped into a single flat document with bullet lists that could benefit from being organized into separate reference files. | 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.