The assistant should use this when the user has a vague concern, hunch, symptom, unknown failure, or asks what to investigate before any Detective case exists. It produces a read-only, approval-ready brief. Do not use when the user explicitly asks to…
The assistant should use this when the user asks to close, finalize, force-close, wrap up with a final conclusion, or produce final Detective case findings. It closes only after proof readiness or explicit force approval. Do not use for status-only review…
The assistant should use this when the user wants to discuss an existing Detective case, resolve a blocker, answer a targeted question, provide guidance/facts/theories, change scope, or choose between alternatives. It records guidance without running…
The assistant should use this when the user asks to continue, resume, advance, work, or run the next step for an existing Detective case id. It autonomously drives MCP OODA cycles. Do not use to create a new case (use open-case), pre-scope a vague concern…
The assistant should use this when the user explicitly asks to open/create/start a Detective MCP case, begin an OODA investigation, or approves a brainstorm brief. It creates durable case state. Do not use for vague pre-case scoping without approval (use…
The assistant should use this when the user asks to show, summarize, audit, export, or review the current Detective board/status/progress/evidence graph/blockers without changing case state. It is read-only by default. Do not use for new cases (open-case),…
Use when debugging interactive CLI, REPL, TUI, ssh, telnet, nc, watch-mode, dev server, long-running command, terminal prompt flow, or any command that may not exit. Provides a PTY-backed MCP workflow for spawning terminal sessions, sending text and keys,…
This skill should be used when a user asks to debug an interactive CLI, REPL, TUI, prompt loop, shell wizard, watch mode, long-running terminal process, or any command that hangs, waits for input, redraws incorrectly, needs multiple inputs, behaves…