tc-team — Deterministic QA Test Case Pipeline

    1

    Turn a game design spec (Confluence page or file) into a production-ready test case set in a live Google Sheet.

    $29.99

    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

    tc-team — Deterministic QA Test Case Pipeline

    Example session with this skill installed

    tc-team으로 진행해줘. 기획서는 https://wiki.company.com/pages/12345 이고 시트는 https://docs.google.com/spreadsheets/d/abc123id 여기야.

    • Read your context and instructions
    • Compiled the tc-team

    Starting the TC generation pipeline for feature: PK_System_Update.
    I have fetched the Confluence specification and initialized the workspace at team/specs/PK_System_Update/.

    • S0 (Fetch): Success. 2 linked documents found and cached in linked/.
    • S1-S4 (Analysis & Review): Completed 266 test cases. Parallel processing used 4 chunks.
    • S5-S6 (Apply & Write): Validation gates passed. Sheet written to tab PK_System_Update_v2.

    TC Generation Summary

    CategoryTotal TCsCoverageStatus
    Basic System84100%Green
    Combat Logic11298%2 Pending Check
    UI/UX45100%Green
    Exception Handling25100%Green

    Final Report Highlights:

    • Cross-ref Ratio: 92.4% verified against original spec.
    • S4 Adjustments: 5 redundant cases merged, 3 phrasing corrections applied.
    • Integrity: design_gate and content_gate both returned exit 0.
    • Images: 12 image markers detected and mapped to relevant TC steps.

    Next steps

    1. Review the 2 items marked as 기획 확인 필요 (Check required) in Column K of the spreadsheet.
    2. Run the finalize.sh script if you wish to generate the final deployment dashboard.
    3. Add manual test data values to the Data Setup column as indicated in the S7 summary.

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

    About this skill

    Turn a game design spec (Confluence page or file) into a production-ready test case set in a live Google Sheet. tc-team is a deterministic QA pipeline built on the ISTQB test process: code owns the structure, gates, and coverage ledger — the LLM only writes sentences and makes judgments. Per-case confidence scoring (GO / REVIEW / HOLD / DROP) holds low-quality cases back for human review instead of silently shipping them, and a duplicate gate stops reruns from flooding your sheet with near-copies. The package includes the SKILL.md driver, the full design/generation/review rulebook, and the complete tc-team engine (250 files: scripts, gates, workflows, Apps Script). Verified end-to-end on live production game features. Requires Claude Code, Node.js 18+, Python 3, and your own Google/Confluence credentials (config templates included; no credentials are bundled).

    Requires specific directory structures and local Node.js environment. Spreadsheet access requires pre-configured API tokens. Confluence fetching limited to 1-hop link analysis.

    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 24 days ago

    Requires

    Claude Code
    Node.js 18+
    Python 3
    Google account
    Confluence account
    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Environment Variables
    Listed26 days ago

    What's inside

    Frequently Asked Questions

    The skill uses a 7-stage deterministic pipeline that treats code as the "backbone" for structure and formatting, while only using LLMs for natural language reasoning. This prevents the common "hallucinations" or formatting errors that occur when asking a standard AI to generate large spreadsheets directly.

    You will need Node.js and Bash installed, along with valid API credentials for Google Sheets and Confluence. The skill leverages the Model Context Protocol (MCP) to securely bridge your documentation with the generation pipeline.

    No, the skill is designed with a "single-point-of-entry" philosophy that manages tab versioning (e.g., _v2, _v3). This ensures your existing manual QA results and historical data remain intact while new iterations are generated.

    You receive the complete multi-stage orchestration framework, including the S0-S7 workflow scripts, the deterministic structuring engine, and the coverage auditing tools. It also includes the necessary shell utilities to execute parallel tasks via MCP.

    The pipeline generates a 'coverage.json' report that explicitly maps your original Confluence business rules to the resulting test case IDs. This allows you to verify at a glance that every requirement has a corresponding test scenario without manual cross-referencing.

    New in Testing & Debugging