NeuroSkill-com

Skill index and overview — lists all available NeuroSkill skills, tools, and explains how skill loading works.

NeuroSkill activity tracking — file interactions, terminal commands, focus sessions, meetings, clipboard, productivity scoring, weekly digest, brain awareness, and multi-monitor awareness. Tracks files, terminal commands (50+ categories), dev loops, zone switches, EEG-correlated struggle prediction, and task type detection. Use when asking about coding activity, file history, productivity, meetings, terminal usage, dev workflow, or brain state.

NeuroSkill Do Not Disturb automation — EEG-driven focus detection that activates OS-level DND and optional grayscale display when sustained attention exceeds a threshold. Shows rolling average, sample window, and OS state. Supports force-override on/off. Use when managing focus-based DND automation, grayscale mode, or checking DND status.

Meditation protocols — guided, unguided, mantra, visualization, loving-kindness, body scan, open awareness, and EEG-biofeedback meditation with real-time neural tracking.

Mindfulness protocols — present-moment awareness, informal mindfulness, mindful eating, mindful listening, RAIN, STOP, noting practice, and EEG-tracked mindfulness with real-time neural feedback.

NeuroSkill `label`, `search-labels`, and `interactive` commands — creating EEG text annotations, semantic vector search over labels, and cross-modal 5-layer graph search combining text, EEG similarity, and screenshot discovery with 3D visualization. Use when annotating EEG moments or searching for past states by description.

NeuroSkill built-in LLM inference server — on-device OpenAI-compatible chat with llama.cpp, model catalog management (add/download/select/delete GGUF models), vision support (mmproj), streaming WebSocket and HTTP chat, automatic tool calling (bash, read, write, edit, web_search, web_fetch), GenParams tuning, and persistent chat history. Use when managing local LLM models, chatting, or integrating with the OpenAI-compatible API.

NeuroSkill screenshot search commands — `search-images` for OCR text and CLIP vision search, `screenshots-around` for temporal proximity, `screenshots-for-eeg` for finding what was on screen during EEG sessions, and `eeg-for-screenshots` for discovering brain state near matching screenshots. Cross-modal EEG↔screenshot bridging. Use when searching for past screen content, correlating screen activity with brain states, or exploring screenshot history.

NeuroSkill EXG data reference — all metric fields including band powers, EXG ratios and indices, core scores, complexity measures, PPG/HRV fields, motion and artifact markers, sleep stage codes, EXG correlate indices, and consciousness metrics. Use when looking up what a specific metric means or its value range.

NeuroSkill `label`, `search-labels`, and `interactive` commands — creating EXG text annotations, semantic vector search over labels, and cross-modal 4-layer graph search combining text and EXG similarity. Use when annotating EXG moments or searching for past states by description.

Full guided-protocol repertoire for neuroloop — 70+ mind-body practices organised by EXG metric signal. Covers attention, stress, emotions, relaxation, sleep, somatic, consciousness, cognitive performance, motor, neck, eyes, morning routines, workout/gym, hydration, bathroom breaks, emotions, music, social-media addiction, and dietary protocols. Loaded on-demand when protocol context is detected.

NeuroSkill use-case recipes and scripting patterns — shell snippets for focus and productivity monitoring, stress and anxiety tracking, sleep quality analysis, ADHD/cognitive-load queries, meditation tracking, cross-modal graph search, A/B session comparison, time-range queries, and automation with cron/Python/Node.js/HTTP. Use when looking for practical examples or building automation pipelines.

NeuroSkill `search` and `compare` commands — ANN search for neurally similar EXG moments across all history, and A/B session comparison with metric deltas, trend directions, and UMAP enqueuing. Use when finding similar past brain states or comparing two recording sessions.

NeuroSkill `session` and `sessions` commands — per-session metric breakdowns with first/second-half trends, session listing across all days, and Unix timestamp helpers. Use when analysing a specific recording session or listing all available sessions.

NeuroSkill `sleep` and `umap` commands — EXG-based sleep stage classification (Wake/N1/N2/N3/REM) with efficiency and bout analysis, and 3D UMAP projection of session embeddings for spatial comparison. Use when analysing sleep quality or visualising neural state separation between sessions.

NeuroSkill `status` command — full system snapshot including device state, signal quality, EXG scores, band powers, ratios, embeddings, labels, sleep summary, and recording history. Use when checking current EXG state, device connection, or session metadata.