SolveLang Workflow Review

    1

    Deterministic, read-only review of n8n workflows and Solve Graphs — readiness score, severity-ranked findings, and concrete fixes before you ship.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    SolveLang Workflow Review

    Example session with this skill installed

    Analyze my n8n workflow in user-onboarding.json and check the impact of changing the 'Send Welcome Email' node.

    • Read your context and instructions
    • Compiled the solvelang workflow review

    I have analyzed the n8n workflow and mapped the impact of changes to the 'Send Welcome Email' node using the SolveLang graph tools.

    Workflow Review: user-onboarding.json

    MetricValue
    Readiness Score72/100
    Total Nodes14
    Critical Findings1
    High Findings2

    Findings & Impact Analysis

    • Critical: Unhandled Rejection
      • Node: Send Welcome Email (ID: node_82f)

    Issue: No error trigger or "On Error" path defined. Failure at this node will halt the entire onboarding sequence without logging the failure to the CRM.

    • Recommendation: Add a Wait node or an error handler that routes to Slack Alert node.

    • High: Data Transformation Risk

      • Node: Format User Data (ID: node_a12)

    Issue: Upstream dependency for Send Welcome Email. Changing the email node logic without updating the data map will cause Property undefined errors.

    • Impact: 3 downstream nodes (Send Email, Update SQL, Log Success).

    • Medium: Credential Hardcoding

      • Node: HTTP Request
      • Issue: Authentication header contains a static token reference instead of a workflow credential object.

    Change Impact (Blast Radius)

    • Direct Dependents: Update SQL User Record, Slack Notification.
    • Transitive Dependents: Marketing Analytics Sync.
    • Shortest Path: Send Welcome Email -> Update SQL -> Success Trigger.

    Next steps

    • Implement the recommended error path for the Send Welcome Email node.
    • Use solvelang_graph_impact to verify the specific JSON schema required by Marketing Analytics Sync.
    • Re-run the validation after switching the hardcoded token to a credential object.
    user-onboarding.json

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

    About this skill

    Review n8n workflows, .solve files, and canonical Solve Graph documents with deterministic, read-only SolveLang analysis — the same review method used by the official SolveLang plugins for Claude and Codex.

    Ask your agent to validate, preflight, score, document, or explain a workflow and it will:

    • analyze the workflow structure first, then generate a complete reviewable report when you want the full artifact;
    • report a readiness score with critical and high findings first, the affected nodes, and concrete recommendations;
    • state limitations and untested runtime assumptions honestly — structural evidence, never dressed up as runtime proof;
    • answer Solve Graph questions (dependencies, dependents, blast radius / change impact) with resolved node IDs, direct relationships before transitive ones, and bounded traversal depth.

    Built for process engineers and automation builders who want a disciplined second pair of eyes on a workflow before it goes live.

    Safety by design: all analysis is read-only. The skill never executes a workflow, never asks for or verifies credentials, never calls external APIs, and never modifies files unless you separately request an edit.

    Requirement (stated up front): this skill works through the free SolveLang MCP server (@solvelang/mcp-server@0.3.0 on npm). The package includes a setup reference with the exact one-block MCP configuration. No SolveLang account or API key is needed for the local read-only tools.

    What's in the package:

    • SKILL.md — the review method (workflow, review format, safety rules)
    • reference/SETUP.md — MCP connection block and tool inventory

    Version: 1.0.0 (aligned with @solvelang/mcp-server v0.3.0)

    Analysis is limited to provided canonical documents. Cannot verify runtime behavior, external API connectivity, or actual credential validity. Reads only from specified workspace paths.

    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 22 days ago

    • Free with an Agensi account

    Requires

    Node.js

    Permissions

    Write Files
    Network Access
    Listed22 days ago

    What's inside

    Frequently Asked Questions

    This skill uses the SolveLang MCP server to perform deterministic graph analysis on n8n JSON and .solve files, identifying hidden dependencies and calculating the exact 'blast radius' of changes that manual reviews often miss.

    No, this skill performs static structural analysis only; it never executes your code or validates live credentials, ensuring your production environments remain untouched during the review.

    The skill is compatible with any AI agent or IDE that supports the Model Context Protocol (MCP) and can access the SolveLang MCP server, including tools like Claude Desktop.

    You will receive the specialized agent instructions, tool definitions for n8n/SolveLang analysis, and a configuration guide for connecting the SolveLang MCP server to your environment.

    LLMs often hallucinate connections in large JSON files, but this skill uses deterministic tool calls to retrieve ground-truth data from the SolveLang graph, ensuring every reported dependency actually exists.

    The skill supports standard n8n JSON exports, .solve configuration files, and solvelang.graph.v0 canonical documents for deep dependency mapping.

    New in Workflow Automation