Skill UI

Autonomous experiment loop that optimizes any file by a measurable metric. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Ideal for optimizing code speed, reducing bundle size, improving test pass rates, enhancing prompts, or boosting content quality through iterative measured attempts.

This skill manages and schedules recurring, autonomous experiments. It allows users to set an experiment to run continuously at predefined intervals (e.g., every 10 minutes, daily, or weekly) using cron scheduling logic. It handles the full lifecycle, including execution, result review, strategy refinement, and state persistence.

Autonomous multi-round research review loop. Runs a reviewer, implements fixes, and re-reviews until a policy-approved positive assessment or max rounds is reached. Supports Codex and Copilot CLI backends with optional human checkpoints, difficulty levels, and HTML rendering.

Register ICANN domains via a REST API with crypto payments so AI agents can autonomously check availability, pay in USDC/USDT/ETH/BTC, and retrieve DNS management credentials.

A professional-grade 'Living Pipeline' that integrates advanced AI reasoning into the SDLC. It provides autonomous guardrails for system security, cloud cost management (FinOps), and Kubernetes compliance. It audits Linux Kernel patches for memory vulnerabilities, detects cost drifts in Terraform plans, and generates hardened K8s manifests from natural language policies.

The Safety Guard skill is designed to prevent destructive actions when working in production systems or when autonomous agents are executing tasks. It offers three protection modes (Careful, Freeze, and Guard) to monitor dangerous commands, lock specific directories, and ensure code changes are confined to intended areas, enhancing system stability and security.

AgentFlow transforms your existing Kanban board (Asana, GitHub, Linear) into a self-managing, autonomous AI development pipeline. It orchestrates multiple AI agents through defined stages (Backlog to Done), enforcing deterministic quality gates, performing adversarial reviews, and tracking costs—all visible within your existing project management UI. It provides crash-proof execution and full observability for complex software development lifecycles.

Guides a project planning agent through researching, decomposing, and documenting multi-commit development plans before coding, enforcing autonomous research protocols and template-driven plan outputs for structured PR execution.

This skill orchestrates the entire development lifecycle for approved software tasks. It operates in autonomous or manual modes, rigorously applying Test-Driven Development (TDD). It automatically gathers all necessary context (specs, requirements, design, and historical learnings), validates the repository state, and dispatches specialized sub-agents to implement tasks one by one, ensuring high code quality, adherence to design, and process traceability.

Provides a comprehensive, production-ready standard 3-tier reference architecture for Oracle Cloud Infrastructure (OCI). The design covers essential components like VCN, public/private subnets, Internet Gateway, NAT Gateway, Service Gateway, and Autonomous Database. It includes deployment steps using Terraform and OCI SDK Python code, making it ideal for designing new cloud environments or migrating existing patterns from other major cloud providers.

This comprehensive guide details the end-to-end process of migrating data and connecting to Oracle Cloud Infrastructure's Autonomous Database (ADB). It walks through provisioning the ADB using the Python SDK, securely downloading the necessary mTLS wallet, establishing a connection using `python-oracledb`, and executing compatibility-aware data migration via Data Pump.

Shipwright is an autonomous, multi-phase agent designed to convert simple, plain-English requirements into fully functional, tested, and deployment-ready applications. It supports modern full-stack frameworks like Next.js/Supabase, SvelteKit, and Astro. Use this tool when you need to scaffold a complete project, add complex features, or generate an entire SaaS dashboard merely by describing it.