Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    flowlint

    1

    Extract and audit UX flow diagrams directly from web and mobile source code with file-level traceability.

    Free

    10 usesSecurity scanned
    flowlint

    flowlint

    Example session with this skill installed

    Analyze the onboarding flow in this React Native project and generate a draw.io diagram. Focus on the signup guards and external OAuth steps.

    • Read your context and instructions
    • Compiled the flowlint
    • Generated the document

    I have analyzed the onboarding logic in the src/navigation/AuthStack.tsx and src/screens/auth/ directories. I found a complex signup guard involving email verification and a third-party OAuth redirect that lacked a modeled failure path.

    UX Flow Audit: Onboarding

    StepTypeSourceFinding
    Splash ScreenEntrySplash.tsx:12-
    Email InputInteractionSignUp.tsx:45UXF-NOERR-0A7D: No validation error UI
    OAuth Hand-offGuardAuthService.ts:88High: No handler for user cancellation
    Verification OTPWaitVerify.tsx:22UXF-MISS-0B22: Missing "Resend Code" link

    The full analysis and diagram files have been generated:

    • docs/ux-flows/onboarding.flow.json: The source IR file.
    • docs/ux-flows/onboarding.drawio: Editable diagram (open in app.diagrams.net).
    • docs/ux-flows/onboarding.md: Full audit report with embedded Mermaid flow.

    Next steps

    1. Review the UXF-NOERR-0A7D finding regarding the missing OAuth cancellation path in AuthService.ts.
    2. Open the .drawio file to visualize the proposed recovery branch.
    3. Run flowlint ignore for any intentional friction points identified.

    AuthStack.tsx

    PDF · document

    Generated

    Example file from a real run - the skill writes it into your workspace.

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

    About this skill

    Inheriting a codebase often means flying blind. Design docs rarely match what was actually shipped, leaving developers to guess how error states, empty screens, and edge cases are handled. This skill extracts the ground truth from your source code, generating verifiable UX maps and audits rooted in your actual implementation.

    What it does

    • Source-anchored mapping creates flow diagrams where every node links to a specific file and line number.
    • Automated UX auditing identifies friction points, unhandled errors, and dead ends directly from the logic.
    • Multi-format rendering exports flows to editable .drawio files, Mermaid diagrams, and Markdown reports.
    • Diff analysis compares current flows against proposed changes to measure the delta in steps or friction.
    • CI verification ensures your documentation stays in sync with code via automated staleness checks.

    How it works

    1. Inventory the stack by scanning for web, mobile, or native frameworks like Next.js, React Native, or Flutter.
    2. Trace the logic from entry points to goals, documenting guards, network calls, and all failure branches.
    3. Generate IR (Intermediate Representation) files in JSON format to maintain a deterministic source of truth.
    4. Render deliverables using the included Python utility to produce diagrams and finding reports.

    Frameworks & tools

    Supports Next.js, React, React Router, React Native, Expo, Flutter, SwiftUI, UIKit, and Jetpack Compose. Requires Python 3.8+ for the rendering engine.

    Why this beats prompting it yourself

    Generic prompts often hallucinate UI steps or miss obscure code branches like permission denials and timeout recovery. This skill follows a strict IR schema and use code-level evidence, ensuring the diagrams represent reality rather than a guess.

    Use cases

    • Codebase handovers to quickly visualize how complex authentication or payment flows actually work.
    • Refactoring plans to visualize the "before and after" of a proposed UX change before writing a line of code.
    • QA automation to identify every branch and error state that requires a test case.
    • Audit documentation for compliance or product reviews that stay updated via your CI pipeline.

    Known limitations

    Cannot design non-existent flows or analyze visual design elements. Dynamic runtime routing may result in incomplete maps. Requires manual identification of specific flows to be mapped.

    Cannot analyze flows not yet written or visual design. Dynamic runtime routing may cause incomplete maps. Requires Python 3.8+ for rendering engine.

    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

    10 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 25 days ago

    • Free with an Agensi account

    Requires

    Python
    Git

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files
    Listed25 days ago

    What's inside

    Frequently Asked Questions

    Unlike LLMs that guess UI logic, flowlint scans your actual codebase to create an Intermediate Representation (IR), ensuring diagrams are based on real code branches rather than hallucinations.

    The skill currently supports major web and mobile frameworks including Next.js, React Native, Flutter, and native iOS/Android (SwiftUI/Compose), though it requires Python 3.8+ to run the rendering engine.

    You receive the core logic engine, a Python-based utility for rendering diagrams (Mermaid, .drawio, Markdown), and CI/CD integration scripts for automated staleness checks.

    Yes, flowlint features a diff analysis tool that compares your current IR files against proposed code changes to visualize how a refactor will impact user friction or step counts.

    Every node in a flowlint diagram is anchored to a specific file and line number, providing direct traceability between the visual map and your source implementation.

    While flowlint excels at static analysis of complex branching, it may have limitations with dynamic runtime routing or highly obfuscated code where paths are determined at execution.

    New in Mobile Development