juanandresgs/claude-ctrl

observatory

Analyze system health, surface patterns, manage improvement suggestions. Self-improvement flywheel for the hook/agent/dispatch system.

原文语言：英语

deep-research

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

原文语言：英语

context-preservation

Generate structured context summaries for session continuity across compaction

原文语言：英语

decide

Generate an interactive decision configurator from research or plan analysis. Presents options as explorable cards with trade-offs, costs, and filtering. Integrates with Planner to collect DEC-ID decisions.

原文语言：英语

prd

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 acceptance criteria, prioritizing requirements, or…

原文语言：英语

reckoning

Analyze a project's MASTER_PLAN.md to assess coherence, evolution trajectory, and intent alignment. Modes: default (full analysis), compare (delta between reckonings), operationalize (convert findings to actionable work via /decide), steer (strategic…

原文语言：英语

signal-trace

Trace systemic brittleness from symptom to root cause. Data-flow analysis of hooks, state, and dispatch paths to find where signals break, race, or carry garbage. Produces single-gate fixes, not fallback chains.

原文语言：英语