Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Negative Keyword Hunter

    1

    Find irrelevant paid-search queries and recommend carefully scoped negative keywords with evidence.

    $9.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Negative Keyword Hunter

    Negative Keyword Hunter

    Example session with this skill installed

    Audit these mock search terms for a premium office chair campaign: “chair repair”, “free chair plans”, “ergonomic office chair”, “chair for sale”, “office chair back pain cure”. Recommend negatives carefully.

    • Read your context and instructions
    • Compiled the negative keyword hunter

    ## Negative Keyword Hunter: practical plan ## Search-term review | Query | Intent signal | Recommendation | Reason / caution | |---|---|---|---| | chair repair | Repair service or parts | Consider exact/phrase negative | Likely mismatched if campaign sells new chairs; verify product line | | free chair plans | DIY information | Consider phrase negative | Weak purchase intent, unless free guides are part of strategy | | ergonomic office chair | Product research/purchase | Keep and evaluate | Core relevant intent; monitor economics | | chair for sale | Broad purchase intent | Keep initially | Could be relevant despite generic wording | | office chair back pain cure | Medical outcome claim | Do not promise a cure; review query and ad language | May be relevant comfort research but claims need care | ### Decision method Classify actual terms by relevance, intent, conversion quality and cost. Add negatives only when the mismatch is clear or the economics justify exclusion. Use exact negatives for ambiguous phrases; prefer broader phrase negatives only when many observed queries show the same irrelevant intent. ### Validation steps Check campaign type, match behavior, geographic settings, product availability and conversion tracking. Review search-term volume and potential blocking of useful variants before applying changes. ### Monitoring After changes, inspect impression share, qualified clicks, orders and spend for at least one comparable period. Keep a dated change log and rollback path. Avoid broad negative lists copied from another account; they can block valuable demand. Escalate medical claims for policy review and revise creative to describe verified product attributes only. ### Measurement and review Record the baseline, source, date range, denominator and owner. Use one primary measure plus quality guardrails; compare like-for-like cohorts and disclose missing data. Treat estimates as scenarios, not observed outcomes. ### Risks and controls Check relevance, consent, disclosure, workload and downside before scaling. Keep an evidence trail, obtain human review for material commitments, and pause if trust, quality or compliance signals deteriorate. ### Next steps 1. Confirm the goal, audience and available capacity. 2. Gather the minimum evidence for a first test. 3. Assign an owner, budget and review date. 4. Run a small pilot, record outcomes and decide whether to iterate, expand or stop.

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

    About this skill

    Create a practical, evidence-led Negative Keyword Hunter workflow. Find irrelevant paid-search queries and recommend carefully scoped negative keywords with evidence. Distinguish observations from assumptions, request missing inputs, give actionable recommendations with owners and measurable outcomes, and flag uncertainty. Avoid fabricated metrics, unsupported guarantees, deceptive tactics and unnecessary personal data.

    Does not guarantee ROAS. Requires business context for accuracy. Manual review required for high-impact exclusions. Scope limited by data provided.

    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

    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 1 month ago

    Permissions

    No special permissions declared or detected

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    The skill uses a multi-stage safety stack to cross-reference proposed negatives against your historical conversion data, ensuring high-intent long-tail traffic remains active while blocking wasteful terms.

    You will need your recent search-term reports, conversion data, and existing negative lists in CSV or Excel format to provide the agent with the necessary performance context.

    This skill is optimized for use with advanced LLMs like GPT-4 or Claude 3.5 Sonnet, as it requires high-reasoning capabilities to perform N-gram analysis and intent classification.

    Yes, the /hunt command generates prioritized lists that include specific match-type recommendations (Broad, Phrase, or Exact) and suggests the optimal account level for each exclusion.

    You receive the complete 24-step master workflow, the full suite of operational commands like /hunt and /intake, and a structured guide for integrating CRM data into the analysis.