Who Reads Your Words

    1

    Audience-aware writing for documentation, PRs, reports, email, and UI copy.

    Free

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    About this skill

    Keep outward-facing text focused on its actual readers. Who Reads Your Words establishes the audience, channel, purpose, and shared context before drafting or reviewing a document. It helps keep editing instructions, rejected ideas, and task chatter out of the finished artifact.

    Includes four writing modes: current state, change, decision, and direct conversation. A Python linter checks Markdown and plain text for common audience-boundary problems, with configurable warning and error thresholds. Its findings support editorial judgment and do not automatically rewrite or delete content.

    Free and MIT licensed. Includes Codex skill metadata, audience-contract guidance, the linter, and its tests.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Read Files
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill prevents internal jargon, task chatter, and 'behind-the-scenes' editing notes from leaking into public-facing documents by establishing a clear audience contract before drafting begins.

    The skill is designed for any AI agent that supports Python execution and Markdown processing, including platforms compatible with Codex skill metadata.

    The Python linter analyzes your Markdown or plain text against your defined audience profile, flagging boundary issues as warnings or errors based on your custom thresholds.

    The package includes the core skill metadata, comprehensive audience-contract guidance, the Python linter tool with its test suite, and the MIT license documentation.

    Yes, because it is MIT licensed, you can fully customize the four writing modes and the linter's warning thresholds to match your team's specific brand voice or technical requirements.

    New in Technical Documentation

    Free