AI Engineering

Maker Council simulates a board of founders and operators to weigh a company-building decision from multiple documented perspectives. Use it for pricing, hiring, focus, growth, or bootstrap-vs-raise questions when you want disagreement before deciding.

MCP Case Overrides uses the configured MCP project-mgmt server's get_project tool when asked. It is used as a per-case mocked override smoke skill in skill-up end-to-end tests.

MCP Mocked Marker uses the configured MCP marker tool when asked. It is a smoke skill used by skill-up end-to-end tests.

MCP Stdio Marker uses the configured MCP marker tool when asked. It is a smoke skill used by skill-up end-to-end tests.

Mood Booster responds when someone seems bored, frustrated, or down with comforting words and a short joke. Use it to lighten the atmosphere before ending with encouragement.

Multi-Turn Session Fixture is a placeholder skill used as an end-to-end test fixture for multi-turn sessions. It is used for testing or validating session flows rather than for a production workflow.

Sdd Riper executes the SDD workflow with strict phase gating. It is used to guide research, design, planning, implementation, and review in order.

Skill Up creates, runs, validates, and diagnoses Agent Skill evaluations with the skill-up CLI. Use it to scaffold evals, add cases, author judges, run reports, and iterate from failures or imported evals.json files.

Skillify creates, adapts, or updates Claude Code skills from conversation, a video, pasted notes, or an existing skill. Use it when you need to turn a workflow into a new skill, port one from another source, or improve an existing skill with new learnings.

Toolify walks through integrating an external tool, API, or MCP server into a Next.js or Rails project. It asks structured questions, then scaffolds auth, env vars, client wrappers, example usage, and optional smoke tests.

Unstuck classifies a blocked problem, attacks assumptions, and generates multiple lateral-thinking angles when a task seems impossible. Use it when an API, person, or constraint says no and you need viable next moves.

ACP Debug runs an ACP agent CLI, speaks raw JSON-RPC, and records every wire frame to JSONL. Use it to probe capabilities, inspect handshakes, compare agents, or diagnose startup and session failures.