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.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%Weight 40%Scale 1-3

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

A well-structured, actionable meta-skill with a real template reference and a validation checklist. The only weakness is mild redundancy around the 'hands-on use' message.

Suggestions

Consolidate the 'use the tool hands-on, don't just read docs' guidance into one place — it currently appears in Quick Start step 1, the bold summary after the code block, and the 'What NOT to Do' list.

The 'for review, run the Checklist section' aside in the description is slightly out of voice; consider whether it belongs in the description or only in the body.

Quick Start step 1 mixes two ideas (hands-on use and the WebFetch fallback) — splitting the fallback into its own step would tighten the primary sequence.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and uses token-efficient tables, but the 'use the tool hands-on' message is restated three times (Quick Start step 1, the bold summary line, and 'Do not include commands you haven't tested'), which could be tightened.	2 / 3
Actionability	Provides concrete, actionable guidance: real `ln -s` install commands for Claude Code/OpenCode/Clawdbot, a real `references/template.md` to copy, and a concrete command-organization scaffold.	3 / 3
Workflow Clarity	The 7-step numbered Quick Start gives a clear sequence and the dedicated pre-publish Checklist section supplies the validation checkpoint the rubric rewards.	3 / 3
Progressive Disclosure	SKILL.md is a ~135-line overview pointing to a single, well-signaled, one-level-deep reference (`references/template.md`) that genuinely exists on disk, matching the clear-overview anchor.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description with explicit trigger guidance and clear scope. It answers both 'what' and 'when' and uses natural trigger terms a user would actually say.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete sub-tasks — 'hands-on tool exploration, required vs. recommended sections, installation/usage structure, trigger-rich descriptions, task-grouped commands, progressive disclosure, and a pre-publish checklist' — rather than vague language.	3 / 3
Completeness	Both what ('authoring an agent skill that wraps a command-line tool') and when (explicit 'Use when…' plus 'Triggers for…') are stated, satisfying the explicit-trigger requirement.	3 / 3
Trigger Term Quality	'Triggers for CLI / command-line / terminal / shell-command tools and binary wrappers' gives good coverage of the natural terms a user would say when reaching for this skill.	3 / 3
Distinctiveness Conflict Risk	The niche — authoring skills that wrap CLI/binary tools — is specific and paired with distinctive triggers, making conflict with unrelated skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: joshuadavidthomas/agent-skills
Path: writing-cli-skills/SKILL.md
Commit: 516dee7

Reviewed: 11 days ago

Table of Contents

Discovery Implementation Validation

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.