What problem does it solve?
It prevents messy, fragile agent workflows by standardizing how to chain multiple skills with clear contracts, optional dependencies, and user confirmation for risky phases.
Core Features & Use Cases
- Chaining patterns: Build multi-step slash command workflows where outputs feed subsequent skills (or run in parallel when independent).
- Scope resolution: Prefer project-scoped skills over personal ones using Cursor/Cline discovery order to avoid surprises.
- Graceful degradation: Automatically detect sibling/optional skills and skip them when absent instead of failing the whole workflow.
- HITL gates: Insert human-in-the-loop prompts before expensive, irreversible, or scope-expanding steps.
- Error handling & contracts: Pass parameters explicitly and ensure one phase’s failure doesn’t corrupt earlier artifacts.
- Decision guidance: Decide whether to create a new skill vs extend an existing one to reduce skill sprawl.
Quick Start
Ask the agent to design a slash command workflow that composes web-research-kb-refresh, technology-consolidation-analysis, and an optional consolidation-dashboard with a HITL confirmation before refreshing the knowledge base.