google-gemini/gemini-cli
Overview
This skill reviews user-facing strings and UI copy across a TypeScript codebase to ensure clarity, brevity, consistency, and actionable guidance. It acts as a Senior UX Writer that flags problematic text, maps issues to voice principles, and proposes precise replacements. Use it to keep CLI and agent strings deterministic, scannable, and repairable without changing code autonomously.
How this skill works
The skill scans inline text, error messages, prompts, and settings labels to detect violations of core voice principles (deterministic clarity, system transparency, front-loaded actionability, and agentic error recovery). For each issue it produces a concise rationale and a suggested replacement following the required list format. It never rewrites strings without explicit user approval and pairs every error critique with one clear corrective action or prompt suggestion.
When to use it
- Before a release to audit CLI messages and Git-tracked UI strings
- When adding new commands, flags, or error cases to ensure consistent voice
- During localization prep to simplify and normalize source strings
- When addressing user confusion reports tied to ambiguous messages
- When updating settings schema labels or descriptions
Best practices
- Always front-load intent: use the [Goal] + [Action] pattern for prompts and buttons
- Keep status and loading states under five words and show telemetry for long tasks
- Use deterministic verbs for system/infrastructure and probabilistic verbs for Gemini outputs
- Pair every error with exactly one immediate recovery command or suggested prompt
- Avoid first-person pronouns; attribute thinking to Gemini and doing to the system
Example use cases
- Audit CLI error messages to add one-click recovery commands and human-readable context
- Review new feature copy to ensure the first three words describe user intent
- Normalize settings labels and descriptions after schema changes
- Convert polite loading text into telemetry-driven micro-state cycles for long-running tasks
FAQ
No. It only suggests changes and will not modify source files unless explicitly instructed.
How are suggested replacements formatted?
Each suggestion follows a strict list format: state the violated principle, show the incorrect phrase, and provide the corrected phrase.
Does the skill handle localization issues?
It flags strings that hinder localization (length, ambiguity, context) and proposes neutral, translatable alternatives.
7 skills
This skill reviews user-facing strings for clarity, brevity, and consistency, suggesting improvements while preserving user control.
This skill creates GitHub issues using repository templates, applies correct labeling, and formats content for reliable, consistent issue tracking.
This skill helps you address GitHub PR comments on the current branch by summarizing feedback and guiding focused edits using gh.
This skill guides you through professional code reviews, targeting local changes or remote PRs to improve correctness and maintainability.
This skill greets users warmly, responding with a friendly welcome message when users say hello or request a greeting.
This skill writes accurate Gemini CLI documentation in the docs directory, following style guides and project standards for clarity and consistency.
This skill guides you to create compliant pull requests by following templates, checks, and conventional commits.
