Engineering workflow layer for AI coding tools with specs, review, quality gates, and traceability.为 AI 编程工具提供工程化流程、质量门禁与可追溯能力。

A Claude Code skill and CLI that converts lecture recordings into structured, traceable notes with a synced HTML viewer.

A library of verifiable AI agent skills for Claude Code, Cursor, VS Code, and Copilot to enforce formal traceability and reduce hallucinations.

Query the integration-test storage account to find why a specific skill's tests are failing. Reads blob-stored test result files and surfaces error details. TRIGGERS: why is skill failing, skill test failures, debug skill tests, skill failing tests, analyze skill failures, why are tests failing for skill, skill test errors, investigate skill issues. DO NOT USE FOR: analyzing a GitHub Actions run report or comparing test runs across runs (use analyze-test-run).

Conduct SPARK methodology analysis for new project inception. Use at the beginning of a new project, when evaluating significant features, before bootstrap-project to validate viability, or when pivoting an existing project.

Create a sprint plan for a new development cycle. Use when starting a new sprint, after completing wrapup-sprint, or when initializing Sprint 1 for a new project.

Create the foundational Architecture Decision Record (ADR) sequence for a new project. Use after bootstrap-project, when establishing decision documentation, or when standardizing ADR practices.