cli-patterns
Patterns for building production-quality CLI tools with predictable behavior, parseable output, and agentic workflows. Triggers: cli tool, command line tool, build cli, cli patterns, agentic cli, cli design, typer cli, click cli.
78
72%
Does it follow best practices?
Impact
94%
1.64xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/skills-md/0xdarkmatter/claude-mods/cli-patterns/SKILL.mdQuality
Discovery
72%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description establishes a clear domain niche around CLI tool development with good trigger term coverage including specific framework names. However, it lacks specific concrete actions (what exactly does the skill teach?) and would benefit from an explicit 'Use when...' clause to improve completeness. The description reads more like a topic label than an actionable guide for skill selection.
Suggestions
Add specific concrete actions like 'structure subcommands, handle exit codes, format parseable output, implement progress indicators, and design argument parsing'.
Add an explicit 'Use when...' clause, e.g., 'Use when the user needs to build a CLI application, design command-line interfaces, or implement agentic tool workflows with typer or click.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (CLI tools) and mentions some qualities (predictable behavior, parseable output, agentic workflows), but doesn't list specific concrete actions like 'parse arguments', 'generate help text', 'handle exit codes', or 'structure subcommands'. | 2 / 3 |
Completeness | The 'what' is partially addressed (patterns for building CLI tools with certain qualities), but there is no explicit 'Use when...' clause. The 'Triggers:' list partially serves this purpose but doesn't clearly state when Claude should select this skill in a structured way. | 2 / 3 |
Trigger Term Quality | Includes a good range of natural trigger terms users would say: 'cli tool', 'command line tool', 'build cli', 'cli patterns', 'agentic cli', 'cli design', 'typer cli', 'click cli'. These cover common variations and specific framework names. | 3 / 3 |
Distinctiveness Conflict Risk | The focus on CLI tool patterns with specific framework mentions (typer, click) and the 'agentic workflows' angle creates a clear niche that is unlikely to conflict with other skills like general Python development or web application skills. | 3 / 3 |
Total | 10 / 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 strong, well-structured CLI patterns skill that provides highly actionable guidance with excellent use of tables, concrete code examples, and clear anti-patterns. Its main weaknesses are moderate verbosity with some redundancy between sections, and the lack of an explicit build workflow with validation checkpoints. The progressive disclosure to reference files is well-executed.
Suggestions
Consolidate the exit codes and error codes sections to eliminate redundancy - the error codes table largely duplicates the exit codes table with minor additions.
Add a brief sequenced workflow section (e.g., 'Building a new CLI: 1. Scaffold with Typer, 2. Implement resource commands, 3. Add --json output, 4. Verify with checklist, 5. Test error paths') with explicit validation steps.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is well-organized with tables and clear structure, but it's quite lengthy (~400+ lines) with some redundancy (error codes appear in both Exit Codes and Error Handling sections). Some sections like Data Conventions and Filtering/Pagination cover patterns Claude likely already knows. However, most content is presented efficiently via tables rather than prose. | 2 / 3 |
Actionability | Provides concrete, executable code examples throughout - Python implementation patterns, bash usage examples, specific flag conventions, JSON output schemas, and copy-paste ready patterns. The exit code bash example, error handling implementation, and interactive detection code are all directly usable. | 3 / 3 |
Workflow Clarity | The skill is more of a reference/pattern guide than a step-by-step workflow, which is appropriate for its purpose. However, it lacks explicit validation checkpoints - there's no 'build a CLI in this order' workflow, no testing/verification steps after implementation, and the checklist at the end is a static list rather than a sequenced process. For a skill involving building production tools, some build-then-validate flow would strengthen it. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with clear references to external files: 'See references/json-schemas.md for complete JSON response patterns' and 'See references/implementation.md for complete Python implementation templates.' The main file serves as a comprehensive overview with well-signaled one-level-deep references for detailed implementations. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (633 lines); consider splitting into references/ and linking | Warning |
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
- Repository
- NeverSight/skills_feed
- Commit
f772de4
- 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.