Skill UI

This skill enables non-interactive execution of Qwen Code for coding tasks within the Code Mate environment. It involves setting the working directory, verifying tool availability, and running specific commands with JSON output format. Users should delegate coding work to Qwen Code using this method. Authentication and permissions must be configured properly, avoiding credential exposure. It supports restricted approval behavior and limits tool calls for safety.

This skill enables launching OpenAI's Codex CLI as an isolated subagent for bounded coding, review, or verification tasks. It runs non-interactively in a sandbox, streaming progress while keeping context separate. Ideal for parallel work, independent verification, and self-contained coding tasks with clear success criteria. Users must ensure authentication and handle file ownership explicitly.

Design and review a secure REST API gateway for ComfyUI servers, covering workflow management, job queuing, webhooks, caching, authentication, rate limiting, and image delivery via URL or base64.

Builds Monte Carlo Connection Auth Rules (ctp_config) by fetching live connector schemas and transform steps, then generating Jinja2 mapper configs for credential transformation.

Manage container registries such as Docker Hub, Amazon ECR, Azure ACR, and Google Artifact Registry. Covers authentication, image push and pull, retention and lifecycle policies, cross-account access, and image scanning for secure DevOps workflows.

Resume interrupted project work by reconciling a saved handoff with current repository evidence: separate completed work, pending edits, superseded assumptions and blockers, then state the next verifiable action within existing authorization.

This skill enables expert-level development using Convex, an open-source reactive backend platform. It covers schema design, TypeScript functions, real-time subscriptions, authentication, file storage, and deployment workflows. Ideal for building new projects or integrating Convex into existing React, Next.js, or Vue applications. Supports queries, mutations, and actions with strict security constraints.

Build reactive, type-safe backends with Convex using schema validation, real-time queries, mutations, actions, authentication, and deployment workflows.

Perform dynamic application security testing using tools like OWASP ZAP, Burp Suite, and Nikto to identify runtime vulnerabilities in deployed applications. Supports authentication testing, API security validation, and CI/CD integration for automated security scans. Requires authorized scope and explicit permission before execution.

Authorized security assessment of PostgreSQL, MySQL, MSSQL, MongoDB, and Redis: exposure and TLS review, account role and grantee analysis, dangerous configuration checks (file_priv, xp_cmdshell, COPY PROGRAM, UDF), NoSQL injection, and audit log posture.

This skill enables deploying applications and websites to the Vercel platform. It handles various deployment scenarios including linked and unlinked projects, git integration, and team selection. The assistant checks project state, authenticates CLI, and executes preview or production deployments based on user requests. It ensures best practices like using preview branches for testing before production.

Estimate whether a document's prose was written by AI using an external detection API. Returns an uncalibrated probability, stylistic tells, and honest abstention on non-prose. Built for triage of essays, CVs, submissions, and articles, never as proof of authorship or misconduct.