Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    production agent os

    1

    Guides developers from product requirements to production-ready, verified backends with rigorous engineering judgment.

    Free

    Security scanned
    production agent os

    production agent os

    Example session with this skill installed

    I need to add a new endpoint to the user service that allows users to update their profile settings, including a profile picture URL and a notification toggle.

    • Read your context and instructions
    • Compiled the production agent os

    I have analyzed the current user-service and identified the necessary changes for the profile update endpoint. I've accounted for partial updates (PATCH) and ensured the notification toggle adheres to the existing boolean schema.

    Profile Update Implementation

    I have implemented the controller, service logic, and updated the OpenAPI spec.

    // src/api/routes/user.ts
    // PATCH /v1/users/:id/settings
    // Validates input against UserSettingsSchema and ensures ID matches session.
    
    export const updateSettings = async (req: Request, res: Response) => {
      const { id } = req.params;
      const updates = req.body;
    
      // Verification: Ensure user is authorized to edit this resource
      if (req.user.id !== id) {
        return res.status(403).json({ error: 'unauthorized_resource_access' });
      }
    
      try {
        const updatedUser = await userService.updateSettings(id, updates);
        return res.status(200).json(updatedUser);
      } catch (error) {
        if (error instanceof ValidationError) {
          return res.status(400).json({ error: error.message });
        }
        return res.status(500).json({ error: 'internal_persistence_error' });
      }
    };
    
    ComponentStatusVerification Note
    API ContractVerifiedUpdated docs/openapi.yaml with 403 and 400 error states.
    PersistenceVerifiedTested Prisma update with partial payload; no data loss on missing fields.
    AuthorizationVerifiedBlocked cross-user update attempts in integration test.
    ValidationVerifiedRejected invalid URL formats for profile_picture_url.

    Next steps

    1. Run npm run test:integration to verify the new endpoint against the test database.
    2. Review the updated docs/openapi.yaml to ensure the frontend team has the correct types.
    3. Apply the migration if you are satisfied with the schema audit in .agent/specs/01_user_settings.md.

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

    About this skill

    You need a backend that works in production, not just a script that runs once. This skill handles the heavy lifting of turning product requirements into verified, resilient backend systems. It supplies the engineering judgment needed to uncover hidden requirements like data loss prevention, concurrency risks, and recovery paths.

    What it does

    • Requirement Translation: Converts product language into concrete backend contracts and API specifications.
    • Architectural Scaffolding: Sets up schemas, migrations, and workers based on existing repository patterns.
    • Safety Auditing: Identifies risks in authorization, sensitive data handling, and duplicate work before they hit production.
    • Contract Verification: Ensures frontend-backend interfaces and error flows are consistent and tested.
    • Release Readiness: Prepares deployment artifacts and migration scripts with a focus on data compatibility.

    How it works

    1. Repository Inspection: The skill analyzes your existing manifest, schema, and deployment configs to understand your stack.
    2. Task Scoping: It reconciles your request against active tasks, identifying relevant failure paths and success criteria.
    3. Spec Generation: For new contracts or persistence changes, it drafts a short specification to align on impact.
    4. Implementation Loop: It builds a small, complete slice of the operation, including real-world failure handling.
    5. Verification & Logging: It runs integration checks, records evidence of success, and updates your internal task logs.

    Frameworks & tools

    This skill adapts to your existing stack, including SQL/NoSQL databases, message queues, and cloud providers. It works with standard migration tools, API frameworks, and CI/CD pipelines found in modern backend repositories.

    Why this beats prompting it yourself

    Generic prompts often ignore the "unhappy path," leading to fragile code that fails under load or edge cases. This skill enforces a disciplined engineering loop that explicitly checks for race conditions, data persistence risks, and authorization gaps you might forget to ask about.

    Use cases

    • Feature Implementation: Adding a new authenticated API endpoint with database persistence.
    • Refactoring & Migration: Updating a schema while ensuring backward compatibility and zero data loss.
    • Error Handling Audit: Hardening an existing worker process against intermittent third-party API failures.
    • Release Preparation: Generating verified migration scripts and checking production readiness.

    Known limitations

    Does not handle standalone visual/UI design. It requires an existing repository structure or a request to initialize one via install.sh. It cannot perform unapproved production mutations.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for APIs & Backend.

    Does not perform visual design. Requires an existing repository or manual trigger for setup. Cannot execute unapproved production mutations or paid resource creation.

    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 buying a skill.

    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 to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 8 days ago

    • Free with an Agensi account

    Software
    Git

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Listed8 days ago

    What's inside

    Frequently Asked Questions

    Unlike standard code generators that focus only on the 'happy path,' this skill applies engineering judgment to identify race conditions, data loss risks, and recovery paths that developers often overlook in production environments.

    The skill is designed to adapt to your existing repository's patterns; it analyzes your current manifest, schema, and deployment configurations to ensure all generated backend code is consistent with your stack.

    Yes, the skill includes a specific 'Safety Auditing' phase where it evaluates authorization logic, sensitive data handling, and potential concurrency issues before any code is finalized.

    The skill requires access to an existing repository structure to function; if you are starting from scratch, it can initialize a new environment using an 'install.sh' workflow to set the necessary scaffolding.

    The skill focuses exclusively on the backend logic, API contracts, and data persistence layers; it does not generate frontend UI components or visual designs.

    New in APIs & Backend

    Free