skirano-skills

Introspective workspace readout mode inspired by Anthropic's J-space / global workspace interpretability research (July 2026). While this skill is active, EVERY response must include a readout table of the concepts currently active in Claude's workspace — its silent assessments, intermediate reasoning steps, planned outputs, and self-monitoring signals — before the answer itself. Use whenever the user says "J-space", "jspace", "workspace readout", "what's in your J-space", "show your thinking workspace", "lens mode", or has previously activated this mode in the conversation. Once activated, keep producing readouts on every turn until the user turns it off.

Delegate unusually complex planning, architecture, debugging, or multi-file coding work to Claude Code using the preferred Fable/Claude Fable 5 model at high effort, while Codex remains the orchestrator. Use when the user explicitly invokes this skill or asks for Claude Code/Fable on a hard build, creative coding artifact, large refactor, difficult bug, architecture decision, security/performance-sensitive change, or independent senior-model pass. For explicit build/code requests, Claude Code should usually implement the main artifact, not just advise; do not use for simple edits, routine file reads, small command answers, or tasks where delegating private/secrets-heavy context would be unsafe.