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

91

1.09x
Quality

91%

Does it follow best practices?

Impact

91%

1.09x

Average score across 3 eval scenarios

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 body is a well-structured overview that routes to eight real reference files, enforces design invariants via Hard Gates with concrete templates, and sequences build-then-evaluate clearly. Slight conciseness redundancy and delegation of executable detail to references keep actionability and conciseness at 4 rather than 5.

Suggestions

Collapse the overlap between the Quick Decision Guide table and the per-phase 'Load references/...' lines so each routing pointer appears once.

Add 1-2 concrete inline code snippets (e.g., a TTY-detection or NO_COLOR branch) in the overview so core actionability is present without requiring a reference load.

DimensionReasoningScore

Conciseness

The body is dense and directive — tables for the Quick Decision Guide, Hard Gates, and Common Mistakes rather than prose — and avoids explaining concepts Claude already knows. Minor redundancy between the Quick Decision Guide and the phase sections keeps it just below a 5.

4 / 5

Actionability

Provides concrete, copy-paste-ready templates (the G1 help-format and G2 error-format blocks) and specific thresholds ('under 500ms', '>1 second', exit 130/143). Deeper executable detail is delegated to references, which leaves minor gaps in the overview itself.

4 / 5

Workflow Clarity

Phases 1-7 are clearly sequenced, the Hard Gates act as halting checkpoints, and Rule 7 ('Evaluate after building... prioritize lowest-scoring axes') provides a feedback loop. This is a design skill rather than a destructive/batch operation, so the missing validate-fix-retry loop is not disqualifying.

4 / 5

Progressive Disclosure

A clear overview with a need→reference routing table, each phase ending in 'Load references/X.md for ...', all eight referenced files verified present, and references kept one level deep — easy to navigate with no nesting.

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 comprehensive, specific, and well-scoped: it enumerates concrete capabilities, supplies natural trigger phrases, and sharply delimits its niche with explicit 'NOT for' boundaries. Voice is appropriately third-person imperative throughout.

DimensionReasoningScore

Specificity

Lists many concrete actions — 'structures commands with memorable naming and consistent grammar', 'adds interactive prompts with flag bypasses', 'implements color-coded output with spinners and progress bars', 'enforces XDG config paths', 'optimizes startup to under 500ms', 'scores CLI human-friendliness on a 0-21 rubric' — giving comprehensive, specific coverage rather than vague verbs.

5 / 5

Completeness

Explicitly answers both 'what' (the enumerated design/evaluation capabilities) and 'when' ('Use when designing, building, reviewing, or evaluating command-line tools' plus the 'Triggers on' list) with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes a broad set of natural phrases users would actually say — 'CLI UX', 'human-friendly CLI', 'CLI design', 'CLI colors', 'progress bar', 'CLI help text', 'CLI usability', 'design a CLI', 'evaluate CLI UX' — covering synonyms and variations.

5 / 5

Distinctiveness Conflict Risk

Clear niche (human-facing CLIs) with explicit boundaries — 'NOT for agent/machine CLI consumption (use agent-cli)', 'NOT for TUI/full-screen apps', 'NOT for GUI apps' — minimizing overlap 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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents