cli-developer
Use when building CLI tools, implementing argument parsing, or adding interactive prompts. Invoke for parsing flags and subcommands, displaying progress bars and spinners, generating bash/zsh/fish completion scripts, CLI design, shell completions, and cross-platform terminal applications using commander, click, typer, or cobra.
90
86%
Does it follow best practices?
Impact
91%
1.33xAverage score across 6 eval scenarios
Passed
No known issues
Quality
Discovery
100%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 strong skill description that clearly defines its scope around CLI tool development and terminal applications. It provides explicit trigger guidance with a 'Use when...' clause, lists concrete capabilities, and includes both natural user terms and specific library names for precise matching. The description is well-structured and distinctive enough to avoid conflicts with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'parsing flags and subcommands', 'displaying progress bars and spinners', 'generating bash/zsh/fish completion scripts', 'implementing argument parsing', 'adding interactive prompts'. These are detailed, actionable capabilities. | 3 / 3 |
Completeness | Explicitly answers both 'what' (parsing flags, displaying progress bars, generating completion scripts, cross-platform terminal apps) and 'when' with a clear 'Use when building CLI tools, implementing argument parsing, or adding interactive prompts' clause at the start. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'CLI tools', 'argument parsing', 'interactive prompts', 'flags', 'subcommands', 'progress bars', 'spinners', 'bash/zsh/fish completion scripts', 'shell completions', 'terminal applications', and specific library names like 'commander', 'click', 'typer', 'cobra'. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly carved out niche around CLI tool development with distinct triggers like 'CLI', 'argument parsing', 'shell completions', 'progress bars', and specific framework names (commander, click, typer, cobra). Unlikely to conflict with general coding or other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured CLI development skill with strong progressive disclosure and actionable guidance. The reference table pattern is particularly effective for multi-language coverage. Main weaknesses are some unnecessary verbosity in the constraints and knowledge sections, and the workflow could benefit from explicit error recovery steps.
Suggestions
Remove the 'Knowledge Reference' keyword list at the bottom — it provides no actionable guidance and wastes tokens.
Add a feedback loop to the workflow for when validation fails (e.g., 'If --help output is wrong, check command registration order; if startup >50ms, profile with --inspect or pprof').
Trim MUST DO items that Claude already knows (like 'validate user input early') and make the Output Templates section either concrete with an example or remove it.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary content. The 'Knowledge Reference' section at the bottom is just a keyword list that adds no value. The MUST DO list contains items Claude already knows (e.g., 'validate user input early'). The Output Templates section is vague filler. However, the reference table and code examples are well-targeted. | 2 / 3 |
Actionability | Provides a fully executable Node.js quick-start example, concrete TTY detection snippets across three languages, specific performance targets (50ms startup), and clear framework recommendations per language. The constraints section gives specific, actionable do/don't guidance with code. | 3 / 3 |
Workflow Clarity | The 5-step core workflow is clearly sequenced with validation checkpoints (running --help, --version, verifying TTY detection). However, there's no explicit error recovery or feedback loop — if help text doesn't render correctly or startup time exceeds 50ms, there's no guidance on what to fix or how to iterate. | 2 / 3 |
Progressive Disclosure | Excellent use of a reference table with clear 'Load When' conditions pointing to one-level-deep reference files. The main skill provides a concise overview and quick-start, then directs to specific reference files for Python, Go, design patterns, and UX patterns. Navigation is clear and well-signaled. | 3 / 3 |
Total | 10 / 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
- jeffallan/claude-skills
- Commit
3d95bb1
- 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.