CtrlK
BlogDocsLog inGet started
Tessl Logo

writing-cli-skills

Use when authoring an agent skill that wraps a command-line tool — covers hands-on tool exploration, required vs. recommended sections, installation/usage structure, trigger-rich descriptions, task-grouped commands, progressive disclosure, and a pre-publish checklist. Triggers for CLI / command-line / terminal / shell-command tools and binary wrappers; for review, run the Checklist section.

68

Quality

81%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a solid meta-skill for authoring CLI tool skills, with clear workflow sequencing, a useful pre-publish checklist, and good structural guidance. Its main weaknesses are the missing referenced template file (undermining progressive disclosure) and the lack of a complete worked example showing a finished CLI skill, which would significantly boost actionability. Some minor verbosity could be trimmed.

Suggestions

Add a complete, concrete example of a finished CLI skill (even a short one) to demonstrate all the guidance in action — this would significantly improve actionability.

Provide the referenced `references/template.md` file as a bundle asset, since the skill explicitly directs users to it.

Trim the 'What NOT to Do' section and the explanatory sentence about hands-on use — these restate what's already implied by the Quick Start workflow.

DimensionReasoningScore

Conciseness

Generally efficient but has some unnecessary padding — the 'What NOT to Do' section restates things that could be inferred, and some explanatory sentences like 'Reading docs is no substitute for hands-on use' are somewhat redundant given the already-clear workflow. The tables and structure help, but the overall content could be tightened.

2 / 3

Actionability

Provides concrete guidance on structure, organization, and checklists, but the actual executable examples are generic placeholders (e.g., `my-tool --help`). The skill is meta-instructional (teaching how to write skills), so code examples are inherently illustrative, but the YAML and markdown examples are concrete and useful. Missing a complete worked example of a finished CLI skill.

2 / 3

Workflow Clarity

The Quick Start provides a clear numbered sequence (install → explore → create), the Checklist section serves as an explicit validation checkpoint before publishing, and the Sections tables clearly delineate required vs recommended components. The workflow is well-sequenced for a meta-skill about authoring.

3 / 3

Progressive Disclosure

The skill references `references/template.md` as a starting point and shows a recommended directory structure with references/, but no bundle files are provided, meaning the referenced template doesn't actually exist. The skill itself is well-organized with clear sections, but the missing bundle file undermines the progressive disclosure promise.

2 / 3

Total

9

/

12

Passed

Description

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 description that clearly defines a specific niche (authoring agent skills for CLI tools), lists concrete deliverables and structural elements, and provides explicit trigger terms covering natural user language variations. The 'Use when' clause is front-loaded and the trigger terms are explicitly enumerated, making it easy for Claude to match this skill appropriately.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: hands-on tool exploration, required vs. recommended sections, installation/usage structure, trigger-rich descriptions, task-grouped commands, progressive disclosure, and a pre-publish checklist. These are detailed, actionable elements of the skill.

3 / 3

Completeness

Clearly answers both 'what' (authoring agent skills wrapping CLI tools, covering exploration, sections, structure, descriptions, commands, disclosure, checklist) and 'when' (explicit 'Use when authoring an agent skill that wraps a command-line tool' and 'Triggers for CLI / command-line / terminal / shell-command tools').

3 / 3

Trigger Term Quality

Includes strong natural trigger terms users would say: 'CLI', 'command-line', 'terminal', 'shell-command', 'binary wrappers', 'agent skill', 'checklist'. These cover common variations of how users would refer to this task.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive niche: specifically about authoring agent skills for CLI tool wrappers. This is unlikely to conflict with general coding skills, general documentation skills, or other skill types due to its precise scope.

3 / 3

Total

12

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
joshuadavidthomas/agent-skills
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.