CtrlK
BlogDocsLog inGet started
Tessl Logo

wagneripjr/human-cli

Design and evaluate command-line tools for human users: naming and grammar, interactive prompts, colour and progress output, error messages, and a 0-21 usability rubric

72

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Overview
Quality
Evals
Security
Files

Quality

Content

78%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 content is a lean, well-organized overview that pushes detail into clearly signaled one-level-deep references and provides concrete templates for help/error output and conventions. Its main weakness is mild redundancy across the Gates/Mistakes/Rules tables and template-style rather than copy-paste-runnable code.

Suggestions

Consolidate overlapping rules: keep each convention in one place (Hard Gates OR Common Mistakes OR Rules) and cross-reference rather than restating color-only-indicator and flag-bypass rules three times.

Add per-phase verification steps (e.g. 'Phase 1 done: confirm grammar is uniform and depth ≤ 3 before Phase 2') so checkpoints gate each phase, not just the whole build.

Provide at least one fully copy-paste-runnable code snippet (e.g. a minimal argument parser or TTY-detection snippet) in a reference file to lift actionability from templates to executable examples.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence — no primer on what a CLI is — but the same rules recur across Hard Gates, Common Mistakes, and Rules tables (e.g. color-only indicators, flag-bypass), adding minor redundancy that could be trimmed.

4 / 5

Actionability

Concrete, executable patterns abound — the G1 help and G2 error format blocks, exit codes (130/143), exact XDG paths, and 'time mycli --version' — but these are templates to follow rather than fully copy-paste runnable scripts, keeping it just below the top anchor.

4 / 5

Workflow Clarity

A clear Phase 1–7 sequence with Hard Gates as enforced checkpoints and an explicit 'evaluate after building' feedback loop is present, but the gates are cross-cutting constraints rather than per-phase verify-this-step checkpoints between phases.

4 / 5

Progressive Disclosure

SKILL.md is a well-structured overview with a Quick Decision Guide mapping needs to eight real one-level-deep reference files, each phase ending in a clearly signaled 'Load references/X.md' pointer; no nested references exist in the bundle.

5 / 5

Total

17

/

20

Passed

Description

100%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 a strong, comprehensive trigger-rich statement that clearly delineates both capabilities and activation conditions, with explicit boundaries against adjacent skills. It is at the top of every dimension with no significant gaps.

DimensionReasoningScore

Specificity

Lists many concrete actions with specific thresholds — 'structures commands with memorable naming', 'optimizes startup to under 500ms', 'scores CLI human-friendliness on a 0-21 rubric across 7 axes' — giving comprehensive, not merely broad, coverage.

5 / 5

Completeness

Explicitly answers both what (the enumerated design/evaluation actions) and when (the 'Triggers on' list plus 'NOT for' boundaries), satisfying the top anchor with concrete trigger phrases.

5 / 5

Trigger Term Quality

An explicit 'Triggers on' list supplies natural phrases users would say ('CLI UX', 'human-friendly CLI', 'progress bar', 'design a CLI', 'evaluate CLI UX') with good synonym coverage.

5 / 5

Distinctiveness Conflict Risk

A clear human-CLI niche with explicit exclusion boundaries ('NOT for agent/machine CLI consumption', 'NOT for TUI/full-screen apps', 'NOT for GUI apps') minimizes conflict with sibling skills.

5 / 5

Total

20

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents