cli-building
Build command-line interfaces with async-first design, composable commands, and proper output formatting. Use when creating CLI tools, commands, or interactive terminal applications.
70
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/skillValidation for skill structure
Discovery
89%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 a solid skill description with explicit 'Use when' guidance and good trigger term coverage for CLI-related tasks. The main weakness is that the capabilities listed are more architectural principles (async-first, composable) rather than concrete actions a user might request. The description would benefit from more specific action verbs.
Suggestions
Replace abstract design principles with concrete actions like 'parse arguments', 'define subcommands', 'format output tables', 'handle stdin/stdout'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (CLI) and some actions ('async-first design, composable commands, proper output formatting'), but these are more design principles than concrete actions. Missing specific verbs like 'parse arguments', 'handle subcommands', 'format tables'. | 2 / 3 |
Completeness | Clearly answers both what ('Build command-line interfaces with async-first design, composable commands, and proper output formatting') and when ('Use when creating CLI tools, commands, or interactive terminal applications') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms: 'CLI tools', 'commands', 'command-line interfaces', 'terminal applications'. These are terms users would naturally use when requesting CLI-related help. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on CLI/terminal applications with distinct triggers. Unlikely to conflict with web, GUI, or general coding skills due to specific 'command-line', 'CLI', 'terminal' terminology. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
44%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable overview of CLI building principles with good progressive disclosure to reference materials. However, it lacks concrete, executable examples for most patterns it describes, and the workflow for actually building a CLI is unclear. The content would benefit from more actionable code examples and a clearer step-by-step process.
Suggestions
Add complete, executable code examples for the strategy pattern and composable commands sections instead of just describing the concepts
Create a clear numbered workflow showing the steps to build a CLI from scratch, including validation checkpoints
Replace abstract descriptions like 'Design commands as reusable modules' with concrete code showing the pattern
Trim framework descriptions to essential differentiators only - remove explanations of what each framework is 'good for'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some unnecessary explanation (e.g., describing what frameworks are 'good for' when Claude already knows). The framework descriptions could be tighter, and some bullet points repeat concepts. | 2 / 3 |
Actionability | Provides two basic code examples but they are minimal stubs rather than fully executable patterns. Many sections describe concepts abstractly ('Design commands as reusable modules') without showing concrete implementation. The strategy pattern section has no code examples. | 2 / 3 |
Workflow Clarity | No clear multi-step workflow is provided. The content lists principles and best practices but doesn't sequence them into a coherent process for building a CLI. No validation checkpoints or feedback loops for the development process. | 1 / 3 |
Progressive Disclosure | Good structure with clear overview sections and well-signaled references to detailed materials at the end. The references section points to one-level-deep files for specific topics (async patterns, composable commands, etc.). | 3 / 3 |
Total | 8 / 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.