create-cli

CLI UX/spec: args, flags, help, output, errors, config, dry-run.

Quality

81%

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

87%

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

A well-structured, token-efficient instruction skill with actionable templates and clear one-level-deep progressive disclosure. Its only gap is the lack of explicit validation/feedback checkpoints, which is minor for a design-specification (non-destructive) task.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence, and avoids explaining basic CLI concepts; every section (Clarify, Deliverables, Conventions, Templates) earns its place with bullet density.	3 / 3
Actionability	It gives concrete, copy-paste-ready guidance: a filled spec skeleton, exact flag/exit-code conventions, and a concrete precedence chain (flags > env > project config > user config > system).	3 / 3
Workflow Clarity	Steps are sequenced (Do This First -> Clarify -> Deliverables -> Templates), but there are no explicit validation checkpoints or feedback loops for a design/spec task, and the rubric notes this matters for batch/destructive ops.	2 / 3
Progressive Disclosure	SKILL.md is a tight overview that defers detail to one real reference file (cli-guidelines.md) plus an external link (clig.dev), both clearly signaled; the bundle reference exists and is one level deep.	3 / 3
	Total	11 / 12 Passed

Description

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.

A concise, third-person, highly specific CLI-design description that clearly defines what it does. Its main weakness is the absence of an explicit "Use when..." trigger clause, which caps completeness.

Suggestions

Add an explicit when-to-use clause, e.g. ". Use when designing a command-line interface, its flags/args/help, or planning CLI output and exit-code behavior."

Broaden trigger terms to include natural user phrasings like "command line", "CLI", "usage", and "options".

Dimension	Reasoning	Score
Specificity	The phrase "args, flags, help, output, errors, config, dry-run" enumerates multiple specific concrete surface-area actions the skill addresses.	3 / 3
Completeness	It clearly answers "what" (CLI UX/spec surface area) but has no explicit "Use when..." or when-to-use trigger clause, capping completeness at 2 per the rubric.	2 / 3
Trigger Term Quality	Terms like args, flags, help, output, errors, config, and dry-run are natural CLI-design keywords, but coverage of common variations a user might say (e.g. "command line", "CLI", "usage", "options") is partial.	2 / 3
Distinctiveness Conflict Risk	The narrow focus on designing a CLI's surface area (args, flags, help, exit codes, config) is a distinct niche unlikely to fire for non-CLI skills.	3 / 3
	Total	10 / 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: steipete/agent-scripts
Path: skills/create-cli/SKILL.md
Commit: bb36883

Reviewed: about 14 hours 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.