Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+22 more

    Intent Detection

    1

    Detect buying intent from RSS or NewsAPI by tracking keyword velocity. Each account-keyword pair ranks as low/medium/high. Offline supported.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Intent Detection

    Intent Detection

    Example session with this skill installed

    Monitor buying intent for acme-saas.com, globex.com, and initech.io over the last 14 days. Use NewsAPI with my NEWSAPI_KEY. Watch for these keywords: "Series B funding", "headcount growth", "new CTO". Output a JSON report ranked by intent.

    • Read your context and instructions
    • Compiled the intent detection
    • Generated the data export

    What the skill did

    • Fetched the last 14 days of NewsAPI articles for three accounts.
    • Counted keyword velocity for Series B funding, headcount growth, and new CTO.
    • Classified each (account, keyword) pair as low / medium / high intent.

    Top 5 by intent

    AccountKeywordMentionsVelocityIntent
    acme-saas.comSeries B funding12+3.4xhigh
    acme-saas.comnew CTO4+2.1xmedium
    globex.comheadcount growth3+1.4xlow
    initech.ioSeries B funding1+0.2xlow
    acme-saas.comheadcount growth7+2.8xmedium

    Files written

    • ./out/intent_results.json — full structured report
    • ./out/intent_results.csv — flat list for spreadsheet review
    • Stdout summary: "Top intent: acme-saas.com / Series B funding (high)"
    {
      "window_days": 14,
      "results": [
        {"account": "acme-saas.com", "keyword": "Series B funding", "mentions_14d": 12, "velocity": 3.4, "intent": "high"},
        {"account": "acme-saas.com", "keyword": "new CTO", "mentions_14d": 4, "velocity": 2.1, "intent": "medium"}
      ]
    }
    

    Next steps

    • Open ./out/intent_results.csv in your spreadsheet.
    • Feed the high-intent rows into your email-sequencing or LinkedIn campaign.

    intent_results.csv

    CSV · data export

    Generated

    Example file from a real run - the skill writes it into your workspace.

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

    About this skill

    Watches public signals for buying intent. Parses RSS feeds (no API key) or NewsAPI (NEWSAPI_KEY), counts keyword velocity for your accounts, classifies each pair as low, medium, or high intent.

    Runs offline out of the box (assets/sample_feed.json), so you can verify the logic with no API key.

    Use

    Unzip into ~/.claude/skills/, restart, trigger by phrase. Offline: python3 intent-detection/scripts/intent_detection.py --sample.

    Live mode

    NewsAPI needs NEWSAPI_KEY; RSS needs no key (URLs in assets/feeds.txt). Run: intent_detection.py --accounts accounts.csv --window 14d.

    Output

    Per pair: mentions_14d, velocity (+3.4x), intent. Deterministic from velocity ratio; thresholds 2.0x / 5.0x.

    I/O

    Input: CSV/JSON with account + keywords. Output: ./out/intent_results.json, .csv, stdout.

    Compatibility

    Claude Code, Cursor, Codex CLI, Gemini CLI, GitHub Copilot, Windsurf, OpenClaw, 20+ agents.

    License

    Proprietary. One-time, lifetime updates, 7-day refund.

    How to use

    Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed 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 scanned

    Verified clean 1 month ago

    • Passed all security checks, Safe to install

    Requires

    Newsapi
    Python

    Listed1 month ago

    What's inside

    Frequently Asked Questions