Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Uzzo Workflow

    1

    A structured workflow for project scaffolding, scope definition, story generation, and TDD-based implementation.

    Free

    Security scanned
    Uzzo Workflow

    Uzzo Workflow

    Example session with this skill installed

    Analyze my scope.md and generate INVEST-compliant user stories for the AUTH domain. Use global IDs starting from the last known story.

    • Read your context and instructions
    • Compiled the uzzo workflow

    I have analyzed stories/scope.md and users.md. I identified 3 new vertical slices for the AUTH domain. Global IDs have been incremented starting from US-000012.

    Generated User Stories

    IDTitleSummaryStatus
    AUTH/US-000013User Password ResetAs a User, I want to reset my password via email...BACKLOG
    AUTH/US-000014JWT Token RefreshAs an API Client, I want to refresh my session...BACKLOG
    AUTH/US-000015Multi-factor EnrollmentAs a Secure User, I want to link a TOTP device...BACKLOG

    Files created

    • uzz/stories/AUTH/US-000013/US-000013.md
    • uzz/stories/AUTH/US-000014/US-000014.md
    • uzz/stories/AUTH/US-000015/US-000015.md

    Next steps

    1. Review the BDD criteria in uzz/stories/AUTH/US-000013/US-000013.md.
    2. Update uzz/stories/index.md to prioritize these stories for the next sprint.
    3. Run implement-user-story for AUTH/US-000013 to begin TDD.

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

    About this skill

    Managing project requirements and technical implementation often results in fragmented documentation and scope creep. This suite of skills enforces a structured, vertical development workflow from initial scaffolding to test-driven implementation. It provides a standardized framework for capturing scope, generating INVEST-compliant user stories, and executing code changes within a unified knowledge base.

    What it does

    • Project Scaffolding: Initializes a structured uzz/ directory for documentation, skills, and stories.
    • Scope Enforcement: Conducts interrogative reviews to define strict boundaries and technical constraints.
    • Story Decomposition: Breaks functional domains into small, vertical user stories with BDD/Gherkin acceptance criteria.
    • TDD Implementation: Executes a red-green-refactor cycle to implement stories while maintaining an active decision log.
    • KB Management: Organizes technical documentation and project metadata using a standardized markdown structure.

    How it works

    1. Initialize: Use uzzo-init to scaffold the project structure and seed core workflow articles.
    2. Define: Run scope-definition-reviewer to build a system profile and separate in-scope tasks from future enhancements.
    3. Generate: Trigger user-story-generator to transform the scope into actionable, unique-ID stories.
    4. Build: Invoke implement-user-story to follow a systematic test-driven pipeline for a specific story ID.

    Frameworks & tools

    The skills are environment-agnostic, requiring only markdown support and basic shell access for file operations and test execution. They integrate with any development toolchain including Maven, Node.js, Go, or Rust by reading existing project metadata.

    Why this beats prompting it yourself

    Manual prompting often misses cross-domain dependencies and fails to maintain a single source of truth. This package uses a persistent folder-based state and strict INVEST validation to ensure stories are actually small enough to execute without manual intervention.

    Use cases

    • Starting a new greenfield project with a clean, structured documentation root.
    • Slicing a monolithic PRD into 1-3 day vertical development tasks.
    • Enforcing TDD and architectural standards across a multi-agent or multi-developer team.
    • Rescuing a project with poorly defined boundaries and ambiguous requirements.

    Known limitations

    Does not support direct inspection of compiled binaries or jars. Requires manual confirmation when proposed story updates conflict with existing files.

    Requires manual confirmation for file conflicts. Cannot decompile binaries. Best used with markdown-capable agents.

    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

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed today

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listedtoday

    What's inside

    Frequently Asked Questions

    It solves 'context drift' and scope creep by forcing a structured directory-based state. Unlike raw prompting, it uses a persistent knowledge base and INVEST-compliant decomposition to ensure your project doesn't outgrow the agent's context window.

    The package includes a suite of specialized skill definitions for scaffolding, scope auditing, story generation, and TDD execution, along with a standardized folder template. You receive the complete workflow logic ready to be imported into your AI agent environment.

    This skill is environment-agnostic and works with any AI agent capable of file system operations and Markdown processing. It is designed to sit alongside your existing tech stack, whether you are developing in Node.js, Python, Go, or Rust.

    Setup is immediate; once the skill is imported, you simply run the initialization command to generate the `uzz/` directory structure. From there, the workflow guides you through an interrogative process to define your project boundaries.

    The skill enforces a Red-Green-Refactor cycle where code is only written to satisfy specific BDD/Gherkin acceptance criteria defined in your stories. It maintains an active decision log to ensure every architectural change is mapped back to an authorized project requirement.

    The system requires manual confirmation if a proposed story implementation conflicts with existing project files to prevent accidental overwrites. Additionally, it cannot directly inspect compiled binaries, so it relies on source code and metadata for its analysis.

    New in Agents & Orchestration