Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Copy Gate: Six-Layer Copy Review

    1

    The skill tells the agent to rewrite from the top finding and re-run.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Copy Gate: Six-Layer Copy Review

    Copy Gate: Six-Layer Copy Review

    Example session with this skill installed

    Here's the LinkedIn launch post the marketing agent wrote (post.txt). Run it through the copy gate for LinkedIn and tell me whether it's ready to go out.

    • Read your context and instructions
    • Compiled the copy gate

    I ran copy-gate with --task linkedin on post.txt. Gate score: 21/100. Not ready.

    {
      "task": "linkedin",
      "detectedArchetype": "hero",
      "gateScore": 21,
      "weights": { "jung": 30, "freud": 20, "sales": 25, "seo": 0, "aiseo": 5, "platform": 25 },
      "scores": {
        "jung":     { "score": 15, "notes": ["◔ Light hero archetype presence (1 signal)",
                                             "◔ Surface only — doesn't name what they're avoiding"] },
        "freud":    { "score": 15, "notes": ["◔ One id-level cue — could go deeper"] },
        "sales":    { "score": 20, "notes": ["✓ Opens with a hook pattern",
    
                                         "✗ No numeric specificity · adds friction to belief",
                                         "◔ No stakes named — reader has no urgency",
                                         "✗ No proof — every claim survives without backing",
                                         "✗ No clear CTA · sales-class copy needs a next step"] },
    
        "aiseo":    { "score": 13, "notes": ["✗ No lists or tables · LLMs will struggle to cite extractable facts"] },
        "platform": { "score": 35, "notes": ["◔ Short for LinkedIn — leaves engagement on the table",
                                             "✗ Not enough line breaks — LinkedIn copy without breaks dies"] }
      },
    

    "findings (order)": ["Jung: FAILS", "Sales 101: FAILS", "Freud: FAILS",
    "Platform: WEAK · needs rewrite", "AI-SEO: FAILS"]
    }

    Fix in this order

    1. Voice (weight 30): say who this is for and what problem they're stuck with, not "we are excited".
    2. Sales (weight 25): add one concrete number, one piece of proof (a user quote or a before/after), and a single clear next step instead of "check it out sometime".
    3. Platform (weight 25): break it into short lines and give it a bit more length.
      I'll redraft with those changes and re-run the gate to compare scores.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Agent Trust: a consistent quality gate for agent-written copy

    Agents write a lot of copy, and it tends to sound the same: excited, vague and without proof. Copy Gate checks a draft against the same rules every time, weighted for where the copy will appear, and tells the agent what to fix first.

    What it does

    Scores the draft on six layers, each 0–100, weighted by task:

    • Jung: archetype voice (hero, sage, caregiver, ruler, etc., auto-detected or set)
    • Freud: motive and emotional pull
    • Sales 101: hook, specifics, stakes, proof, call to action
    • SEO: keyword focus and meta-description fit
    • AI-SEO / GEO: lists, tables and attributions that AI search engines can cite
    • Platform: length and layout for the channel

    Tasks: sales-page, blog-post, linkedin, twitter, email, landing, readme, tool-ux, client-deliverable, dev-docs.

    When an agent should use it

    • You ask it to review or improve a sales page, post, email, landing page or README
    • As a quality gate before any copy is published
    • To compare two drafts of the same piece

    What it outputs

    JSON: task, detected archetype, gate score (0–100), layer weights, per-layer score with notes, and findings sorted by weight × shortfall, so the first finding is the one worth fixing first. The skill tells the agent to rewrite from the top finding and re-run.

    Limitations

    • Scores are rule-based heuristics, not a prediction of clicks, sales or rankings. Use them to compare drafts and catch obvious gaps.
    • Tuned for English.
    • It does not produce a verdict receipt hash (unlike the verifier skills); its output is the score breakdown.
    • The exit code is 0 for every score, so agents should read gateScore and findings.

    Open source, packaged skill

    Original work by Simon Gant. The core logic is public under the MIT licence (copy-gate). This listing is the packaged, tested agent skill: SKILL.md workflow, CLI and docs. Requires Node.js 18+, zero dependencies, no network, no API keys.

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

    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

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed today

    Software
    Node.js 18+

    Permissions

    Runs one local Node.js script (`node scripts/copy-gate.js`) through the agent's shell tool. Reads only the draft file you pass it. No network access, no file writes, no environment variables read. Pure compute.

    Listedtoday

    What's inside

    Frequently Asked Questions

    No. The score is a rule-based heuristic for comparing drafts and catching gaps, not a prediction of results.

    The script scores and ranks fixes; the skill workflow has your agent rewrite from the top finding and re-run to check the score moved.

    Sales page, blog post, LinkedIn, Twitter/X, email, landing page, README, tool UX, client deliverable and developer docs.

    No. It's rule-based and runs offline, so the same draft always gets the same score.

    The core logic is MIT open source. You are paying for the packaged, tested agent skill and workflow.

    New in Social Media