AI Engineering

A memory manager that lets AI agents view, search, add, edit, prune, or clear Hyperflow project memory stored in .hyperflow/memory/, without touching source code.

Rapidly onboard projects to Windsurf with optimized Cascade AI configuration, including rules setup, project context, and team defaults. Use when setting up new projects for AI-assisted development.

Creates or refreshes an AGENTS.md file by tracing every claim to real source code functions, tables, and exports. Use for Carbon packages and ERP modules to provide up-to-date, verifiable AI agent context.

Executes an approved implementation plan task by task, running verifications and committing after each task. Ideal for turning a plan file into a fully implemented, tested, and committed feature.

Audit the codebase for bugs, security, performance, and tech debt, then produce self-contained implementation plans for other agents to execute.

Creates a detailed implementation plan from a finalized spec, providing exact file paths, commands, and verification steps so an AI agent can execute each task mechanically. Use after a spec's open questions are resolved or when 'plan the implementation' is requested.

Automates the iterative development of a single, tightly-scoped work item (bug, tweak, small feature) by running a doer→gate→judge cycle unattended, producing a gated pull request as the only human supervision point.

Creates or refreshes an AGENTS.md for Carbon packages or ERP modules by reading source code, grounding every claim in real functions, tables, and exports. Ideal when adding modules or performing freshness audits.

Orchestrates the complete feature lifecycle from research and spec writing to plan, build, test, and self-review. Supports autonomous and approval-based modes with structured run records.

Rust coding conventions for Carbon's cargo workspace, emphasizing safe async/FFI patterns, ownership choices, error handling, and performance profiling when working with OpenCASCADE and FCL bridges.

Set up and troubleshoot Liferay MCP server, including CLI restart ordering, connection issues, and error diagnosis. Use when enabling MCP or handling tool call errors.

Searches public repositories for SKILL.md files to discover, classify, and extract reusable processes, plugin ideas, and procedural knowledge for AI agent workflows.