First-time setup guide for claude-calibration and Claude Code config in general. Detects what config the project already has (CLAUDE.md, .claude/, settings.json, hooks, agents, skills, .mcp.json), names the minimal viable additions for this project's stack, and bridges into /claude-calibration:calibration-doctor…
Discovery-friendly dispatcher above /calibrate. With no args, prints a menu of every calibration flow — the three /calibrate built-in modes (tighten / harden / cost), the two standalone convenience flows (audit, diff), and the per-feature shortcuts (skills / subagents / claude-md / rules / settings / hooks / mcp /…
Use when a prompt references a file path under /.claude/secrets/, or contains a > reference, or asks to use a saved API key. Teaches the correct pattern for reading vaulted secrets WITHOUT leaking them into bash output, the model context, or the session transcript.
Get a compact, token-budgeted context snapshot AND save a rich persistent session snapshot — project overview, active bugs/tasks with code connections, and recent git commits. Use this to orient quickly and persist context for the next session.
Generate comprehensive technical documentation by synthesizing all accumulated insights from the neural memory knowledge graph. Also use to save a new insight with neuraladdinsight.
Manage the full task lifecycle in the neural knowledge graph — list, create, update status and priority. Tasks connect to code nodes and appear in every prompt via the context hook.
Production readiness audit that checks SEO, legal, monitoring, infrastructure, UX, performance, and security. Produces a visual HTML dashboard with letter grades. NOT code review — checks everything code review doesn't: favicon, privacy policy, error tracking, rate limiting, OG images, and 40+ more items. Use when…
You are running the Performance category of a Ship Score production readiness audit. Follow every instruction below precisely. Do not add checks beyond the 7 defined here. Do not skip checks. Report exactly what you find.
You are running the Security category of a Ship Score production readiness audit. Follow every instruction below precisely. Do not add checks beyond the 7 defined here. Do not skip checks. Report exactly what you find.
Memento — autonomous nervous system for AI agents. Use for memory operations, active coercion management, goal alignment checks, dependency audits, and workspace routing.
Introspect the user's local AI agent infrastructure in real time. Use proactively: before starting tasks, before scheduling cron/timer work, when stuck, after long tasks, or when claiming something works. Exposes tools: vitalssummary, shadowlist, shadowstale, burnoutsummary, burnoutstucksessions.
Drive GIMP-style image ops via gimp-mcp (MCP + CLI): open/create, resize, crop, flip, rotate, blur, desaturate, invert, text overlay, export, batch resize. Mock Pillow offline or live gimp-console (GIMP 2.10 / 3.x). Use when the user mentions GIMP, gimp-mcp, image batch/resize/export, live-smoke, doctor GIMP, or runs…
Work the Loopback feedback queue — the cross-project bus where real product usage lands as actionable items (pinned UI feedback, backend failures with captured response bodies, UX papercuts, AI-feature feedback with run metadata) and where fixes are written back so pins turn green. Use this whenever the user says…
Record a polished demo video of a Chrome extension with Diorama. Use when asked to create, update, or re-record an extension demo, produce Chrome Web Store assets, or turn an extension feature into a video.
Runtime observability for React Native/Expo apps on Android. Use when debugging RN UI, performance (FPS, JS blocking), network, re-renders, or runtime errors on a running app — understand the current screen and UI findings, capture screenshots, UI trees, ref snapshots, per-request network, CDP console/heap/CPU…