juanandresgs

observatory

juanandresgs3/7/2026

Self-improving flywheel that analyzes agent traces, surfaces improvement signals, and proposes targeted system enhancements.

prd

juanandresgs2/26/2026

Write structured feature specifications with problem statements, user journeys, use cases, functional requirements, and success metrics. Use when describing a problem space, developing a PRD, defining...

decide

juanandresgs2/26/2026

Generate an interactive decision configurator from research or plan analysis. Presents options as explorable cards with trade-offs, costs, effort estimates, and filtering. Integrates with Planner to c...

rewind

juanandresgs2/22/2026

List and restore to a named checkpoint from the current session. Use when the agent has gone off track and you need to recover to a previous good state.

diagnose

juanandresgs2/22/2026

Validate hook integrity, state file consistency, and system health for the ~/.claude configuration.

deep-research

juanandresgs2/21/2026

Multi-model deep research with comparative assessment (OpenAI + Perplexity + Gemini). Queries 3 deep research providers in parallel and produces a comparative synthesis.