Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Missing article reviewer

    1

    A high-detection editorial tool that identifies missing, incorrect, or superfluous articles in technical prose.

    Free

    1 useSecurity scanned

    About this skill

    Technical documentation often suffers from "telegraphic speech" where articles like "a", "an", and "the" are omitted, making prose sound robotic or unprofessional. AI models frequently overlook these errors because they mentally auto-correct text while reading. This skill implements a strict Noun-First Review Protocol to catch missing or incorrect determiners that standard linters miss.

    What it does

    • Noun-First Validation scans every singular countable noun to ensure it has a mandatory determiner.
    • Phonic Acronym Check verifies "a" vs "an" usage based on the actual vowel sound of technical acronyms like SQL, API, or URL.
    • Proper Noun Cleaning identifies and removes superfluous articles before brand names and programming languages.
    • Specificity Analysis flags incorrect usage of "the" for generic concepts or "a" for specific UI elements.
    • Contextual Auditing provides the exact heading and verbatim sentence for every identified error to ensure easy search and replace.

    How it works

    1. Submit Prose by providing technical documentation, README files, or UI copy for review.
    2. Protocol Execution triggers three distinct scans focusing on singular nouns, technical phonics, and proper noun usage.
    3. Categorized Reporting generates a structured audit grouped by error type with specific fix rationales.
    4. Statistical Summary outputs a final table tallying total errors across all four categories.

    Frameworks & tools

    This tool is designed for technical writers and developers working with Markdown, documentation-as-code, and UI strings. It ignores code blocks but audits inline backticks.

    Why this beats prompting it yourself

    Generic prompts often fail to see what isn't there, as LLMs naturally fill in missing articles during processing. This skill forces a "Zero-Trust" scanning logic that treats every noun as a potential failure point, catching "Click button" style errors that generic instructions ignore.

    Use cases

    • Reviewing README files for open-source projects to ensure professional English.
    • Auditing UI microcopy and button labels for consistency.
    • Checking technical blog posts for ESL-related article mismatches.
    • Validating documentation containing heavy use of acronyms like AWS, SQL, and HTTP.

    Known limitations

    Does not check grammar within triple-backtick code blocks. Focuses exclusively on articles and determiners rather than general syntax or spelling.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Technical Documentation.

    Ignores content inside triple backticks. Focuses strictly on articles (a, an, the) and determiners, not general grammar or spelling.

    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 buying a skill.

    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 to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 27 days ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed27 days ago

    What's inside

    Frequently Asked Questions

    While generic AI models often 'auto-correct' errors in their head, this skill uses a 'Zero-Trust' protocol that treats every noun as a potential error, catching the 'telegraphic speech' (e.g., 'Click button' instead of 'Click the button') that standard prompts miss.

    Yes, the skill includes a Phonic Acronym Check specifically designed to handle technical terms like 'a SQL server' vs 'an SQL server' based on how the acronym is actually pronounced.

    The skill is optimized for Markdown files, READMEs, and UI strings; it is designed to ignore code blocks while still auditing the prose and inline backticks surrounding your code.

    You will receive the full 'Noun-First Review Protocol' skill configuration, including the three-scan logic for nouns, phonics, and proper noun usage, ready for deployment in your preferred AI agent environment.

    The skill provides a structured audit report that gives you the exact heading and the verbatim sentence for every error, making it simple to find and fix the text in your source files.

    This skill focuses exclusively on the accuracy of articles (a, an, the) and determiners; it is a specialized tool meant to be used alongside, rather than instead of, a general spell-checker.

    New in Technical Documentation

    Free