AI Engineering

OwnMem recalls a repository’s local Markdown memory before code changes and helps keep that memory healthy. Use it when past debugging lessons may apply or when you need to audit or update project memory.

OwnMem installs local project memory for coding agents in a repository. Use it to set up, update, or verify OwnMem host adapters and recall guards.

OwnMem Console opens a local browser dashboard for repository memory metrics like adoption, recall latency, corpus health, and governance. Use it to inspect memory quality or enable the optional embedding lane.

OwnMem Init installs or updates OwnMem in the current repository. Use it to add local project memory for coding agents, or to refresh the installation after a version bump.

OwnMem Recall checks a repository's local memory before code changes and helps keep it current. Use it to look up past debugging lessons, project-specific conventions, or cross-session context stored in .ownmem/.

Activation Audit checks real spawn telemetry to see which OrchestKit sub-agents are being used, which never fire, and how often generic agents replace specialists. Use it before pruning the catalog or after changing agent spawn paths.

Agent Orchestration provides patterns for agent loops, multi-agent coordination, framework selection, and multi-scenario workflows. Use it when building autonomous loops, routing work across agents, or comparing orchestration frameworks.

AI UI Generation covers prompt patterns, tool selection, review checklists, token injection, and CI gates for AI-produced UI. Use it when generating components or full-stack UI with json-render, v0.app, Stitch, Bolt Cloud, or Cursor.

API Design covers REST and GraphQL contract design, versioning schemes, RFC 9457 Problem Details, and OpenAPI specs. Use it when defining endpoint shapes, deprecation windows, or standardizing error responses across services.

Auto classifies a plain-English goal and routes it to the right OrchestKit specialist skill. Use it as the default entry point for goal-shaped requests unless you are already inside another skill.

Baidu Wenku AI PPT generates slide decks from a topic or outline, choosing style, page count, scene, and color. Use it when you need to create a presentation from a brief prompt.

Bare Eval runs `claude -p --bare` for isolated evaluation, trigger testing, and LLM grading without plugin or hook interference. Use it when benchmarking prompts, scoring outputs, or checking skill matches in a clean non-interactive call.