Generate new agent skills from a workflow description: SKILL.md with frontmatter, workflow, examples, and eval cases.
Create comprehensive specifications from user requests through research, critical analysis, and user alignment.
Index and installer for the judgment toolkit — six procedure skills (/refute /door /gate /drift /altitude /premortem) and three mechanical…
Use when deciding which jue-* sub-skill to invoke next, or when sequencing manuscript work from topic through rebuttal for a Journal of…
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including…
Generate a self-contained session-handoff file so work can continue in a different AI tool with zero re-explaining.
Configures law office playbooks and legal practice rules through an interactive setup interview.
Uploads lawyer-verified professional profiles to JuriSupport in review-pending status with strict web consent and privacy checks.
Execute what the user asked, without the pushback.
Investigate bugs in kaizen-agents-org, identify which project owns the failing behavior, and file a GitHub issue in the correct repository.
Decomposition playbook + anti-temptation rules for an orchestrator profile routing work through Kanban.
Comprehensive kanban board and task management via ktui CLI.
Plan and run multi-agent video production pipelines.
Pitfalls, examples, and edge cases for Hermes Kanban workers.
Build integrated IS/BS/CF financial workbooks in Excel.
Use acpx as a headless ACP CLI for agent-to-agent communication, including prompt/exec/sessions workflows, session scoping, queueing…
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows
Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.
Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.