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 writing CLI tool skills, with a clear workflow from exploration to publication and a useful pre-publish checklist. Its main weaknesses are the lack of a concrete worked example (showing a real CLI tool being turned into a skill) and the missing bundle files that it references. The content is reasonably concise but could be tightened in places.

Suggestions

Add a concrete worked example showing a real CLI tool (e.g., jq or curl) being documented as a skill, with before/after snippets of the SKILL.md output.

Provide the referenced `references/template.md` file as a bundle file so the progressive disclosure actually works.

Tighten the Quick Start bash block — the symlink commands for three different tools add noise; consider showing just one with a note about others.

DimensionReasoningScore

Conciseness

Generally efficient but has some unnecessary padding. The 'What NOT to Do' section and the repeated emphasis on hands-on use could be tighter. The checklist includes items (like uninstall, troubleshooting) that feel like filler for many tools. However, it avoids explaining concepts Claude already knows.

2 / 3

Actionability

Provides concrete structural guidance (section tables, directory layout, YAML examples, checklist) but the actual 'how to write' instructions are more advisory than executable. The bash commands in Quick Start are generic placeholders rather than a real worked example. Missing a concrete before/after example of transforming a CLI tool into a complete skill.

2 / 3

Workflow Clarity

The workflow is clearly sequenced: install and explore the tool → run help on subcommands → try operations → copy template → fill in sections → delete unused sections → run checklist before publishing. The checklist at the end serves as an explicit validation checkpoint. For a meta-skill about writing skills, this is a well-structured process.

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, so the template reference is a dead link. The skill itself is well-organized with clear sections, but the missing bundle 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 its niche (authoring agent skills for CLI tool wrappers), lists specific concrete deliverables and concepts it covers, and provides explicit trigger terms covering natural variations. The 'Use when' clause is front-loaded and the trigger terms section at the end reinforces discoverability.

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 concepts.

3 / 3

Completeness

Clearly answers both 'what' (authoring agent skills that wrap CLI tools, covering exploration, sections, structure, descriptions, commands, progressive 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 tools', 'binary wrappers', 'agent skill', 'checklist'. These cover common variations of how users would describe this need.

3 / 3

Distinctiveness Conflict Risk

Occupies a very clear niche: writing skill files specifically for CLI tool wrappers. The combination of 'agent skill authoring' + 'CLI/command-line tool wrapping' is highly distinctive and unlikely to conflict with general coding or documentation skills.

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.