More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Reputation Management Playbook

    1

    Audit your ratings, ask for reviews without cheating, answer bad ones calmly, size a crisis by tier, and rebuild after a hit — with the banned tactics named.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Reputation Management Playbook

    Reputation Management Playbook

    Example session with this skill installed

    I run a bakery. We're at 4.2 stars on Google with 180 reviews, but the last month has been rough. This morning a one-star review landed: "Found a hair in my croissant and the girl at the counter just shrugged." What do I do?

    • Read your context and instructions
    • Compiled the reputation management playbook

    First, the standing: 4.2 with 180 reviews is a workable base — this is a Tier 1 complaint (one review, one platform), not a crisis. It gets a good reply today, not a statement. The "rough month" is the real signal: pull the last 30 days of reviews after this reply and group them by theme; if counter service appears twice, that's a pattern to fix at the counter, not in the replies.

    The reply (four parts — name it, own it, one concrete change, take it offline):

    A hair in your food is not something you should have to point out twice, and a shrug is not the response you deserved for it. That's on us. Starting today, everything in the pastry case gets a second check at the counter before it goes in the bag, and I've spoken with the morning team about how we handle it when something's wrong — the fix starts with listening. I'm Daniel, the owner — daniel@example.com. Come back in and breakfast is on me, and if you'd rather tell me directly what would make it right, that address reaches me personally.

    Why it's built this way: future readers see the experience named in the reviewer's own terms, an apology with no policy lecture, one change they can picture, and a named human with a direct address. It doesn't argue about whether the hair was there — that argument is unwinnable in public and every stranger reads it as evidence.

    What happens next, this week: answer any other unanswered negatives from the rough month the same way; start the honest ask at the natural moment (the receipt card and the after-purchase email, one link, no follow-ups); and put the weekly twenty-minute cadence on the calendar — read everything, answer negatives, thank two positives with specifics, log repeating themes. If the rough month's theme turns out to be the Saturday rush, the fix is staffing, and the reviews will show it within a few weeks.

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

    About this skill

    Reputation work usually fails by panic or neglect: a furious reply to one loud review, or nobody watching while the rating slides for a quarter. This playbook installs a system instead. Start with a one-page audit (rating, volume, trend, response rate on the three platforms your buyers actually read) scored on a 10-point health card. Ask for reviews honestly — at natural moments, never filtered, never bought, with the platform and FTC rules spelled out. Answer negatives with a four-part structure written for the fifty strangers reading both sides, not for the reviewer. Size any crisis against a three-tier decision table so a single complaint gets a reply and a real fire gets counsel before statements. Keep a twenty-minute weekly cadence and a monitoring tripwire so patterns surface before they trend. After a genuine hit, rebuild in three phases: stop the bleeding, refill the pool, hold the line. The tactics that get accounts banned or businesses fined are listed as hard lines, not fine print.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Marketing & SEO.

    • It will not help buy, fabricate, or gate reviews — those tactics are listed as hard lines with the reasoning, and requests for them stop there.
    • Anything alleging illegality or touching regulated topics (health, finance) routes to "get counsel before replying"; the skill drafts communications, not legal advice.
    • The audit is only as current as the numbers you pull; the playbook's first instruction is always to pull this week's, not work from memory.

    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 24 days ago

    Permissions

    No special permissions declared or detected

    Listed24 days ago
    Updated21 days ago

    What's inside

    Frequently Asked Questions

    Document the pattern first — screenshots, dates, account histories, phrasing similarities — then report it to the platform with the pattern spelled out. Keep answering each review professionally (the replies are for real readers), accelerate your honest review asks to dilute the impact, and take counsel if the attack is demonstrably defamatory.

    No. Making a remedy conditional on changing a review is on the banned list — platforms and regulators treat it as buying the rating. You can fix the problem, and after a genuine resolution you may ask once, politely, whether they'd consider updating it. Asking twice is pressure.

    The audit scores 100% of negatives answered within 48 hours as healthy, and Tier 1 complaints get a reply within 24 hours under the crisis table. Speed matters less than structure, though — a calm four-part reply tomorrow beats a defensive one in an hour.

    New in Marketing & SEO