agentleFS
Sign inStart free
portabletextportabletext/editor/.claude/skills/product-copy-assistant/SKILL.md

product-copy-assistant

Skill285 starsChanged 17 days agoMITView on GitHub

Write clear, concise, accessible product copy for interfaces, docs, and system messages. Use when engineers or designers need help with UI copy, error messages, tooltips, onboarding flows, empty states, confirmation dialogs, success/warning messages, or any user-facing text. Triggers on requests like "write copy for," "help me phrase," "error message for," "what should this button say," or reviews of existing product copy.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Consistent: Follow product terminology (see references/)

    line 27
  2. Distinctive:

    Action-oriented: Use verbs ("Save changes" not "Done")

    line 29

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Product Copy Assistant

Help engineers and designers write clear, human-friendly product copy.

Before Writing Copy

Gather context by asking (prioritize, don't overwhelm):

  1. Audience: Developer, content editor, admin, end user? Technical level?
  2. Location: Button, tooltip, error message, modal, toast, onboarding, settings?
  3. Purpose: Instructional, confirmational, error-related, motivational?
  4. Constraints: Character limits? Platform-specific needs?
  5. Tone: Strictly functional, friendly, or educational?
  6. Visual context: Screenshot of the interface?

Skip questions when context is obvious from the request.

Core Principles

  1. Clarity first: Plain language, specific not vague
  2. Concise: Short sentences, no filler, prioritize action over explanation
  3. Consistent: Follow product terminology (see references/)
  4. Accessible: Screen-reader friendly, understandable without visuals
  5. Action-oriented: Use verbs ("Save changes" not "Done")
  6. Empathetic in errors, empowering in guidance

Output Format

Provide:

  • Recommendation: Best copy, polished and ready
  • Alternatives: 2-3 variations (different tones/detail levels)
  • Rationale: Why this phrasing works

Error Message Formula

[What happened] + [Why (optional)] + [What user can do]

Example: "Unable to save draft because your connection was lost. Your changes have been stored locally and will sync when you're back online."

Quick Patterns

Errors (content teams): Supportive, reassuring, actionable Errors (developers): Precise, informative, include technical details Success: Brief, affirming, clear about what succeeded Warnings: Alert without alarming, include preventative advice Empty states: Explain what will appear, guide next action Confirmations: State consequence, provide clear escape path

References

  • references/error-messages.md: Detailed error message patterns and examples
  • references/terminology.md: Sanity product names and capitalization rules

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free