hf Sentiment

    3

    Automated sentiment analysis and batch text classification using Hugging Face's Inference API.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    hf-sentiment

    Example session with this skill installed

    Analyze the sentiment for these three reviews: 'Build quality is amazing.', 'The software update ruined the battery life.', and 'Fast shipping and great support.'

    • Read your context and instructions
    • Compiled the hf-sentiment

    [1] POSITIVE (99.8%) — Build quality is amazing.
    [2] NEGATIVE (85.4%) — The software update ruined the battery life.
    [3] POSITIVE (92.1%) — Fast shipping and great support.

    Results saved to: ~/.hf-sentiment/sentiment_20231024_120000.json

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

    About this skill

    What it does

    This skill provides a high-performance sentiment analysis interface powered by Hugging Face's Inference API. It allows your AI agent to classify text as positive or negative with confidence scores, moving beyond simple guess-work to use industry-standard transformer models (DistilBERT).

    Why use this skill

    While LLMs can estimate sentiment, they are often inconsistent and expensive for high-volume tasks. This skill provides a structured, reproducible way to process data by offloading the heavy lifting to specialized sentiment models. It handles the API overhead, batch processing logic, and local storage of results, making it ideal for developers building data pipelines or monitoring tools.

    Supported features

    • Single & Batch Processing: Analyze individual strings or process multiple inputs in a single request for efficiency.
    • File-Based Workflows: Point the skill to a text file for line-by-line automated analysis.
    • Persistent Storage: All results are automatically versioned and saved as JSON in a local directory for later retrieval or auditing.
    • Low Latency: Utilizes the DistilBERT-SST-2 model for fast, accurate results without the overhead of a full GPT-4 call.

    • Requires an active internet connection to reach Hugging Face.
    • DistilBERT-SST-2 is optimized for English text.
    • Subject to Hugging Face free-tier rate limits.

    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 7 months ago

    Permissions

    Terminal / Shell
    Network Access
    Environment Variables
    Listed7 months ago

    What's inside

    Frequently Asked Questions

    This skill uses the DistilBERT-SST-2 model via Hugging Face's Inference API, providing a faster, more cost-effective, and more consistent alternative to using general-purpose LLMs for classification tasks.

    Yes, you will need a standard Hugging Face API token (available for free on their website) to connect the skill to their hosted inference models.

    The skill supports both single-string inputs for real-time analysis and batch processing via local text files, making it suitable for processing large datasets efficiently.

    Upon purchase, you receive the full skill integration package including the logic for API handling, automated result versioning, and documentation on how to deploy it within your agent framework.

    The skill is designed to be compatible with any Python-based AI agent framework that supports external tool calls, and it comes with clear instructions for a standard installation process.

    By default, all analysis results are automatically timestamped and saved as structured JSON files in a dedicated local directory, ensuring your data is preserved for future audits or reporting.

    New in Agents & Orchestration