create-cli

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

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/create-cli/SKILL.md

Quality

Content

90%Weight 40%Scale 1-5

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

The body is a tight, highly actionable CLI design playbook with a copy-paste spec skeleton and concrete defaults, well-structured with an offloaded reference file. Its main gaps are a missing explicit validation checkpoint in the workflow and a non-bundle-relative reference path.

Dimension	Reasoning	Score
Conciseness	The body is lean throughout—tight bullets, no explaining of basic CLI concepts, and every section (Clarify, Deliverables, Default Conventions, Templates) earns its tokens.	5 / 5
Actionability	It provides a copy-paste "CLI spec skeleton" template plus concrete default conventions (e.g. "-h/--help always shows help", "--no-input disables prompts"), giving fully actionable, specific guidance for an instruction-only skill.	5 / 5
Workflow Clarity	A clear sequence exists ("Do This First" → "Clarify (fast)" → "Deliverables"), but there is no explicit validation/checkpoint step for the produced spec; since this is design work rather than destructive/batch ops, the 3-cap does not apply.	4 / 5
Progressive Disclosure	Detailed guidelines are offloaded to a real one-level reference (references/cli-guidelines.md) with a clear signal to read it, but the body cites the path as "agent-scripts/skills/create-cli/references/cli-guidelines.md" rather than the bundle-relative location, a minor navigation gap.	4 / 5
	Total	18 / 20 Passed

Description

66%Weight 40%Scale 1-5

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 concise and specific about the CLI design domain with good natural trigger terms, but it omits any explicit "when to use" guidance, which limits completeness. Distinctiveness is strong for the CLI-design niche.

Suggestions

Add a "Use when..." clause naming concrete triggers, e.g. "Use when designing or specifying a command-line interface's arguments, flags, help, output, or error behavior."

Include common synonyms like "command-line", "subcommands", and "options" to broaden trigger-term coverage.

Consider a brief verb-led framing (e.g. "Designs CLI surface area...") to make the action explicit in third person.

Dimension	Reasoning	Score
Specificity	Names the CLI domain and lists several concrete facets ("args, flags, help, output, errors, config, dry-run"), giving specific coverage with only minor gaps.	4 / 5
Completeness	The description gives a clear "what" (CLI UX/spec across listed facets) but has no "Use when..." clause or equivalent trigger guidance, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Natural CLI terms like "args", "flags", "help", "errors", and "dry-run" are terms users would say, though synonyms like "command-line" or "options" are absent.	4 / 5
Distinctiveness Conflict Risk	"CLI UX/spec" carves a distinct design niche unlikely to fire for unrelated skills, with only minor overlap risk against general build/design skills.	4 / 5
	Total	15 / 20 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: 2784a38

Reviewed: 22 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.