Agent skill

UX Linter

by revfactory in revfactory/harness-100

Checklist and best practices for validating CLI tool user experience.

Apache-2.0Auto-check passedFrontend & Design

Install UX Linter

skills CLI
$ npx skills add revfactory/harness-100 --skill ux-linter -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install revfactory/harness-100 ux-linter --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .claude/skills && cp -r skills-src/en/40-cli-tool-builder/.claude/skills/ux-linter .claude/skills/ux-linter && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ux-linter
GitHub stars
1.3k
Token cost
~1.1k tokens
SKILL.md length
103 words
Files
1
Skills in repo
464
Repo updated
First seen
Licence
Apache-2.0

At a glance

Checklist and best practices for validating CLI tool user experience.

  • Works in 5 steps: Discoverability → Feedback → Error Handling → …
  • CLI UX validation
  • SKILL.md covers Target Agents, CLI UX 12-Principle Checklist, Error Message Format Standard and Output Format Guide, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

UX Linter is an agent skill from revfactory/harness-100. Checklist and best practices for validating CLI tool user experience. Use this skill for 'CLI UX validation', 'usability check', 'output format verification', 'error message review', 'interaction pattern inspection', and other CLI UX quality checks. Note: GUI usability testing and accessibility certification are outside the scope of this skill.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Frontend & Design, covering UX design, Linting and formatting and User research. The licence is Apache-2.0.

When your agent uses it

  • CLI UX validation
  • Usability check
  • Output format verification
  • Error message review

Example prompts

  • “CLI UX validation”
  • “usability check”
  • “output format verification”
  • “/ux-linter”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Discoverability
  2. Feedback
  3. Error Handling
  4. Pipe-Friendly
  5. Configuration

What it can do on your machine

Read from SKILL.md and the folder at commit 8e8d35c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json and markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

UX Linter loads about 1.1k tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 103 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~89
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from revfactory/harness-100 at commit 8e8d35c, republished under its Apache-2.0 licence (© revfactory). 103 words, ~1,067 tokens.

Download SKILL.mdSave it as .claude/skills/ux-linter/SKILL.md (or your agent's skills folder).
name
ux-linter
description
Checklist and best practices for validating CLI tool user experience. Use this skill for 'CLI UX validation', 'usability check', 'output format verification', 'error message review', 'interaction pattern inspection', and other CLI UX quality checks. Note: GUI usability testing and accessibility certification are outside the scope of this skill.

UX Linter — CLI User Experience Validation Checklist

A skill that enhances UX quality verification for the test-engineer and docs-writer.

Target Agents

  • test-engineer — Systematically performs CLI usability testing
  • docs-writer — Writes documentation from the user's perspective

CLI UX 12-Principle Checklist

1. Discoverability
[ ] Does --help provide useful information?
[ ] Is the subcommand list displayed with descriptions?
[ ] Is there a "Did you mean...?" suggestion for wrong commands?
[ ] Is there an Examples section?
2. Feedback
[ ] Is there progress indication during operations? (bar/spinner)
[ ] Is success/failure clearly distinguished?
[ ] Is estimated time shown for long operations?
[ ] Is a result summary provided?
3. Error Handling
[ ] Are error messages specific? (what went wrong and how to fix it)
[ ] Are errors and warnings distinguished?
[ ] Are errors output to stderr? (prevents stdout contamination)
[ ] Are exit codes appropriate? (0: success, non-0: failure)
4. Pipe-Friendly
[ ] Does stdout output structured data?
[ ] Can output be switched between human/machine format? (--json, --quiet)
[ ] Can input be read from stdin? (pipe)
[ ] Are colors auto-disabled when piped? (isatty check)
5. Configuration
[ ] Is the config file path displayed?
[ ] Is the priority of env vars + config file + CLI options clear?
[ ] Are defaults reasonable?
[ ] Is there a command to check current settings?

Error Message Format Standard

BAD (patterns to avoid)
Error: invalid input
Error: operation failed
Exception: NullPointerException at line 42
Error: Input file not found: data.json
  Check the path or specify with the --input option.
  Example: mytool convert --input /path/to/data.json

Error: JSON parsing failed (line 15, column 8)
  There is an unclosed brace.
  Hint: Check syntax with jsonlint data.json
Error Message Components
1. [What happened] — Problem description
2. [Why it happened] — Cause (when possible)
3. [How to fix it] — Resolution
4. [More info] — Documentation link, related commands

Output Format Guide

Table Output
NAME        STATUS    SIZE     MODIFIED
config.yml  active    2.4 KB   2025-01-15
data.json   pending   156 KB   2025-01-14
JSON Output (--json)
json
[
  {"name": "config.yml", "status": "active", "size": 2400},
  {"name": "data.json", "status": "pending", "size": 156000}
]
Progress Indicators
TTY (terminal):
  Processing... [████████░░░░░░░░] 50% (15/30 files)

Non-TTY (pipe/redirect):
  Processing 15/30 files...
  Processing 30/30 files... done.

Color Usage Guide

MeaningColorANSI
SuccessGreen\033[32m
WarningYellow\033[33m
ErrorRed\033[31m
InfoBlue\033[34m
EmphasisBold\033[1m
SecondaryGray\033[90m
Rules:
1. Disable colors when NO_COLOR environment variable is present
2. Auto-disable when piped/redirected
3. Provide --no-color option
4. Content must be meaningful without colors

Interactive Patterns

Confirmation prompt (dangerous operations):
  Are you sure you want to delete? [y/N]: _
  -> Uppercase is the default (N = default No)
  -> Skip with --force / --yes

Selection prompt:
  Select output format:
  > json
    yaml
    toml
  -> Arrow key selection (TTY only)

Dry run:
  --dry-run option for preview without actual changes

UX Validation Report Template

markdown
## CLI UX Validation Report

### 12-Principle Status
| Principle | Status | Notes |
|-----------|--------|-------|

### Error Message Quality
| Scenario | Current Message | Suggested Improvement |

### Output Format Verification
| Command | Terminal Output | Pipe Output | JSON |

© revfactory, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in en/40-cli-tool-builder/.claude/skills/ux-linter of revfactory/harness-100.

Open the folder on GitHubat commit 8e8d35c

Compare with similar skills

UX Linter next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

UX Linter compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
UX Linter this skillrevfactory/harness-1001.3k—~1.1kAutomated safety check: PassApache-2.0
Product Skillsalirezarezvani/claude-skills28k—~2.6kAutomated safety check: PassMIT
Prototypeplugin87/ux-ui-agent-skills1.6k—~614Automated safety check: PassMIT
Usability Frameworksslgoodrich/agents139—~3.5kAutomated safety check: PassCustom licence
Nova Act UsabilityLeoYeAI/openclaw-master-skills2.2k—~7.4kAutomated safety check: PassMIT
UX Research Planmohitagw15856/pm-claude-skills1.4k—~1.6kAutomated safety check: PassMIT

Similar skills

  • Product Skills

    alirezarezvani/claude-skills

    A skill your agent uses when coordinating product work across the 12 bundled product sub-skills (RICE, OKRs, UX research, design tokens, competitive teardown, analytics, experiments, discovery…

    28k GitHub stars~2.6k tokensUpdated 1 mo ago
    Frontend & DesignAuto-check passed
  • Prototype

    plugin87/ux-ui-agent-skills

    Move an idea up the fidelity ladder (content-first → wireframe → low-fi → high-fi → code) with a validation plan at each level, plus user-journey mapping and usability-testing scripts.

    1.6k GitHub stars~614 tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Usability Frameworks

    slgoodrich/agents

    Usability testing methodology, Nielsen's heuristics, and usability metrics.

    139 GitHub stars~3.5k tokensUpdated 6 mo ago
    Frontend & DesignAuto-check passed
  • Nova Act Usability

    LeoYeAI/openclaw-master-skills

    AI-orchestrated usability testing using Amazon Nova Act. An agent skill from LeoYeAI/openclaw-master-skills.

    2.2k GitHub stars~7.4k tokensUpdated 2 mo ago
    Frontend & DesignAuto-check passed
  • UX Research Plan

    mohitagw15856/pm-claude-skills

    Create a structured UX research plan for any product question or feature.

    1.4k GitHub stars~1.6k tokensUpdated today
    Frontend & DesignAuto-check passed
  • UX Heuristic

    asgard-ai-platform/skills

    Conduct heuristic evaluation of user interfaces using Nielsen's 10 usability principles.

    242 GitHub stars~1.4k tokensUpdated 4 mo ago
    Frontend & DesignAuto-check passed

More from revfactory/harness-100

All 464 skills in this repo
  • Anti Bot Analyzer

    revfactory/harness-100

    A skill for analyzing website anti-bot defense mechanisms and developing legitimate evasion strategies.

    1.3k GitHub stars~1.1k tokensUpdated 6 mo ago
    Auto-check passed
  • API Error Design Patterns

    revfactory/harness-100

    Reference for designing how an API reports failures: structured error codes, response shapes, client-friendly messages, an error catalog and retry or fallback advice.

    1.3k GitHub stars~1.6k tokensUpdated 6 mo ago
    Auto-check passed
  • API Security Checklist

    revfactory/harness-100

    Walks a backend-dev agent through OWASP API Top 10 checks, authentication and authorization patterns, and defense code during API design.

    1.3k GitHub stars~1.7k tokensUpdated 6 mo ago
    Auto-check passed
  • Arg Parser Generator

    revfactory/harness-100

    Methodology for systematically designing and generating CLI tool argument parser structures.

    1.3k GitHub stars~1.2k tokensUpdated 6 mo ago
    Auto-check passed
  • Audience Segmentation

    revfactory/harness-100

    Audience segmentation skill used by the analyst and curator agents.

    1.3k GitHub stars~1.3k tokensUpdated 6 mo ago
    Auto-check passed
  • Audio Storytelling

    revfactory/harness-100

    Audio storytelling skill used by the podcast scriptwriter and show note editor.

    1.3k GitHub stars~1.6k tokensUpdated 6 mo ago
    Auto-check passed

Questions about UX Linter

What does UX Linter do?

Checklist and best practices for validating CLI tool user experience. UX Linter is an agent skill from revfactory/harness-100. Checklist and best practices for validating CLI tool user experience.

When should I use UX Linter?

UX Linter fits situations like: CLI UX validation; usability check; output format verification; error message review.

How do I install UX Linter in Claude Code?

Run `npx skills add revfactory/harness-100 --skill ux-linter -a claude-code`. Or copy the skill folder (en/40-cli-tool-builder/.claude/skills/ux-linter in revfactory/harness-100) into .claude/skills/ux-linter in your project. Claude Code loads it when a task matches its description.

How do I install UX Linter in Codex?

Run `npx skills add revfactory/harness-100 --skill ux-linter -a codex`. Or copy the skill folder (en/40-cli-tool-builder/.claude/skills/ux-linter in revfactory/harness-100) into .agents/skills/ux-linter in your project. Codex loads it when a task matches its description.

Can I use UX Linter in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add revfactory/harness-100 --skill ux-linter -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ux-linter, .gemini/skills/ux-linter, .github/skills/ux-linter and .opencode/skills/ux-linter in your project.

What does UX Linter need to run?

SKILL.md names no scripts, command-line tools or credentials: UX Linter is instructions for the agent only.

Does UX Linter access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is UX Linter safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does UX Linter use?

UX Linter is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does UX Linter use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to UX Linter?

Skills that share tags, products or a category with UX Linter: Product Skills (alirezarezvani/claude-skills, 28k stars), Prototype (plugin87/ux-ui-agent-skills, 1.6k stars), Usability Frameworks (slgoodrich/agents, 139 stars) and Nova Act Usability (LeoYeAI/openclaw-master-skills, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains UX Linter?

revfactory (a GitHub user) maintains it in revfactory/harness-100, which has 1,295 GitHub stars. The repository holds 464 skills in this directory. The repository was last updated on March 22, 2026.

Source: revfactory/harness-100 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.