Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    TF2 Demo Analysis Toolkit v0.1.1

    1

    Analyze TF2 match-summary JSON with deterministic player statistics, multi-match comparisons, and privacy-conscious Markdown reports. Runs locally using Python 3.10+, without external APIs or cloud services.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    TF2 Demo Analysis Toolkit v0.1.1

    TF2 Demo Analysis Toolkit v0.1.1

    Example session with this skill installed

    Analyze my Team Fortress 2 match data using the TF2 Demo Analysis Toolkit.

    Use my existing tf-demo-parser JSON summary to identify my player, calculate verified performance statistics, and generate a Markdown report.

    Include kills, deaths, assists, and available weapon event statistics. Explain which metrics are unavailable.

    Keep all processing local, exclude personal identifiers and chat from the output, and do not upload my match data.

    If I haven't provided a JSON file or its location, ask me for it before starting.

    • Read your context and instructions
    • Compiled the tf2 demo analysis

    Analyze Team Fortress 2 demo JSON summaries with deterministic player statistics, multi-match comparisons, and privacy-conscious Markdown reports. Runs locally with Python, no game installation, cloud service, or AI API required.

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

    About this skill

    TF2 Demo Analysis Toolkit

    Turn Team Fortress 2 match data into structured, reproducible performance reports using your AI coding agent.

    This toolkit helps developers and TF2 enthusiasts analyze existing JSON summaries generated by tf-demo-parser, without installing Team Fortress 2 or relying on expensive AI APIs.

    What it does

    • Individual match analysis: Extracts player-specific kills, deaths, assists, and available weapon event counts.
    • Multi-match comparisons: Processes multiple match summaries and compares results across sessions, including map-based grouping.
    • Privacy-conscious reporting: Excludes player identities, SteamIDs, chat messages, and server names from generated reports.
    • Deterministic calculations: Computes statistics using Python code instead of asking a language model to estimate results.
    • Missing-data awareness: Identifies unavailable information and warns when sample sizes are too small for meaningful conclusions.
    • Markdown and JSON output: Produces structured results suitable for inspection and downstream workflows.

    How it works

    1. Provide an existing JSON summary produced by tf-demo-parser.
    2. Ask your compatible AI agent to analyze a match or compare multiple matches.
    3. The agent runs the supplied Python helper locally, with your permission.
    4. Review the generated reports and available statistics.

    Requirements

    • Python 3.10 or newer.
    • An AI agent capable of executing local Python scripts and reading user-selected files.
    • Existing tf-demo-parser JSON summaries.

    No Steam installation, running TF2 client, hosted AI model, cloud account, or API key is required for the analysis itself.

    Important limitations

    This toolkit does not directly parse raw .dem files, provide live coaching, reconstruct player positions, measure aim accuracy, or perform video analysis.

    The source JSON must be produced separately. Results depend on the events actually available in that source.

    Independence

    An independent developer tool. Not affiliated with, endorsed by, or sponsored by Valve or Steam.

    Processes existing tf-demo-parser JSON summaries only. Does not parse raw .dem files, analyze video, provide live coaching, or infer player positions and aim accuracy. Requires Python 3.10+ and an AI agent with local file access and script execution. Compatibility depends on the connected agent's capabilities.

    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 days ago

    Requires

    Python 3.10+
    Python

    Permissions

    Terminal / Shell
    Write Files
    Read Files

    Requires permission to read user-selected local JSON summaries, run a Python analysis script, and write reports to user-approved destinations. No network access, third-party account, API key, or cloud service is required.

    Listed7 days ago

    What's inside

    Frequently Asked Questions

    No, this skill is designed to work with JSON summaries generated by the 'tf-demo-parser' utility. You must convert your raw .dem files to JSON format first before the toolkit can process them.

    The toolkit is built with Python 3.10+ and standard libraries, making it compatible with any AI agent that has access to a local Python interpreter and filesystem. It works seamlessly with agents that support code execution and file handling.

    Unlike cloud-based tools, this skill runs entirely locally and includes a deterministic privacy filter that automatically strips SteamIDs, chat logs, and player names. This ensures your match data remains private and PII-free before any report is generated.

    The toolkit includes the core Python analysis script, a suite of secure validation helpers, and documentation on how to integrate the commands into your AI agent's workflow. It also features a self-test command to verify your environment is configured correctly.

    Yes, the batch processing feature allows you to point the tool at a directory of JSON files. It will aggregate data across all matches to calculate performance means and identify trends, provided the files share the same map or criteria.

    LLMs often struggle with mathematical accuracy and may hallucinate stats or leak sensitive metadata from raw JSON. This skill uses deterministic logic to ensure every calculation is mathematically perfect and every PII-strip is 100% reliable.

    New in Game Development