Guide for writing skills that wrap CLI tools. Use when creating a new CLI skill. For review, run through the Checklist section.
56
62%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./writing-cli-skills/SKILL.mdQuality
Discovery
75%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 is functional and clearly communicates its purpose with explicit 'use when' guidance, making it easy for Claude to know when to select it. However, it could benefit from more specific concrete actions and broader trigger term coverage (e.g., 'command line', 'terminal'). The description is concise and distinctive but slightly underspecified in terms of what concrete guidance it provides.
Suggestions
Add more specific actions the skill covers, e.g., 'Covers argument parsing, error handling, output formatting, and installation instructions for CLI wrapper skills.'
Include natural keyword variations like 'command line', 'terminal', 'shell command', 'command-line tool' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain ('CLI tools', 'CLI skill') and mentions some actions ('writing skills that wrap CLI tools', 'run through the Checklist section'), but doesn't list specific concrete actions like template generation, argument parsing, error handling, etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (guide for writing skills that wrap CLI tools) and 'when' (use when creating a new CLI skill, and for review run through the Checklist section), with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'CLI', 'CLI skill', and 'CLI tools' which users might naturally say, but misses common variations like 'command line', 'terminal', 'shell command', 'wrapper', or 'command-line interface'. | 2 / 3 |
Distinctiveness Conflict Risk | The niche is quite specific — writing skills that wrap CLI tools — which is unlikely to conflict with other skills. The combination of 'CLI skill' creation and 'Checklist' review makes it distinctly identifiable. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a competent meta-skill for writing CLI tool skills, with good structural advice and a useful checklist. Its main weaknesses are the lack of a concrete, complete example of a finished CLI skill (showing the principles in action), the missing referenced template file, and the absence of a validation/testing step in the workflow before publishing. The content is reasonably concise but has some redundancy between sections.
Suggestions
Include a short but complete example of a well-written CLI skill (even 20-30 lines) demonstrating the principles — this would significantly boost actionability by showing rather than telling.
Add a validation step to the workflow: e.g., 'Load the skill in your agent and test that trigger phrases activate it correctly' before the checklist/publishing step.
Provide the referenced `references/template.md` file in the bundle, or inline a minimal template skeleton directly in the skill to ensure the reference is actionable.
Consolidate the 'What NOT to Do' section into the checklist or inline as brief warnings next to relevant sections to reduce redundancy.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but has some redundancy — the 'What NOT to Do' section partially overlaps with guidance already implied elsewhere, and the 'Reading docs is no substitute for hands-on use' line repeats the sentiment from step 1. The checklist also partially restates content from the Sections tables. However, most content earns its place. | 2 / 3 |
Actionability | Provides concrete guidance on structure, organization, and checklist items, plus a bash snippet for symlinking. However, the skill is about writing CLI skills and the examples are somewhat generic — there's no complete before/after example of a well-written CLI skill section, and the template is referenced but not provided in the bundle. The YAML frontmatter example is good but the 'Organizing Commands' section shows only headers without actual command examples. | 2 / 3 |
Workflow Clarity | The Quick Start provides a clear numbered sequence (install → explore → create), and the checklist provides a validation mechanism at the end. However, there's no explicit feedback loop or intermediate validation step — e.g., no 'test your skill by loading it and verifying trigger phrases work' step between writing and publishing. The workflow from exploration to finished skill could be more explicitly sequenced. | 2 / 3 |
Progressive Disclosure | The skill explicitly teaches progressive disclosure and references `references/template.md`, which is good practice. However, no bundle files are provided, so the referenced template doesn't actually exist. The skill itself is well-structured with clear sections, but the missing template file undermines the reference architecture it advocates. | 2 / 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.
40067f1
Table of Contents
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.