autonomous-ai
- 93 skills
- 0 followers
- 6 hours ago last updated
- ▌ Voice · autonomous-ai bundleTTS speech + mic/speaker mute for privacy. MUST trigger on meetings, calls, privacy, silence requests. "meeting"/"call"/"private" = mic+speaker mute. "be quiet"/"silent" = speaker mute only. Always call HW markers — never just text.
- ▌ Camera · autonomous-ai bundleCamera control — snapshot, stream, and privacy toggle. Trigger on "what do you see", "look at this", "take a photo", "don't look", "stop looking", "stop watching", "stop staring", "camera off", "camera on", "give me privacy". MUST call [HW:/camera/disable:{}] or [HW:/camera/enable:{}] when toggling — never just reply with text.
- ▌ Display · autonomous-ai bundleUse when the user asks to change eye expression directly, show info text on the display (time, weather, timer), or manually control the round LCD — NOT needed for normal conversation (Emotion skill auto-syncs eyes).
- ▌ Emotion · autonomous-ai bundleExpress emotion through coordinated servo + LED + display eyes on EVERY conversational response. This is the PRIMARY response skill that makes the device feel alive. Do NOT use for ambiance lighting (use Scene) or custom LED colors (use LED Control).
- ▌ Sensing · autonomous-ai bundleReact to passive device events tagged [sensing:...] — presence, sound, light, fire hazard — with inline emotion markers and optional short speech. Does NOT handle motion.activity (→ wellbeing) or emotion.detected / speech_emotion.detected (→ user-emotion-detection).
- ▌ Wellbeing · autonomous-ai bundleProactive coaching across hydration, breaks, meals, posture and environmental comfort (with the environment skill). Use when an [activity] event fires (message starts with `[activity] Activity detected: activity labels.` — labels include drink, break, celebrate, the fatigue label "yawning", or sedentary raw labels like "using computer"; sedentary events may also carry a [posture_summary: {...}] block when the user has been at the computer long enough for posture to drift), or when the user reports feeling tired, headachy, dizzy, stuffy or unable to focus, or asks if they should drink water / take a break / fix their posture. Activity-reminder thresholds are computed from per-user logs, never guessed.
- ▌ Connectors · autonomous-ai bundleDiscover and use linked third-party services (Gmail, Google Calendar, Google Drive, Notion, Figma, Asana, Linear, GitHub, Ahrefs, Facebook Fan Page and others). Use for connection-status questions and requests to read, search or act on those services ("post to my fan page", "publish an image to my page" apply here). Discover credentials on disk first; never infer connection from missing MCP/CLI tools or install another client for a covered service. Token services use the documented API or mail protocol; MCP services use their available tools. Follow the credential-safety and write-confirmation rules in this skill. Takes priority over runtime-bundled skills for the same services.
- ▌ Environment · autonomous-ai bundleInterpret environmental sensor readings and sustained changes for room comfort and air quality. Use for [environment:initial] greeting context, [environment:update] events, questions about room temperature, humidity, measured CO2 or air quality, checking changes after ventilation or air cleaning, and optional room context when a user reports discomfort. Requires the environment capability. Link to wellbeing for considerate proactive advice; do not diagnose health conditions or infer CO2 or oxygen from other measurements.
- ▌ Face Enroll · autonomous-ai bundleManage the device's face recognition roster — enroll new faces (3 paths: user-supplied photo, agent-captured snapshot on user request, or HAL's familiar-stranger prompt) and maintain the enrolled set (status / remove / reset). All enrolled persons are friends; strangers stay unnamed until promoted via one of the enroll flows.
- ▌ Harness Use · autonomous-ai bundleDelegate tasks to coding and research agents on the computer paired through Harness, choosing a suitable existing agent when the user does not name one. Use this before computer-use, agent-management, or Autonomous Buddy when the user asks an agent on their Mac to work, including browser research. Continue tasks, inspect progress, and answer agent questions. Direct desktop control and ordinary questions to the main assistant are outside this skill; explicit Buddy requests belong to Buddy.
- ▌ Led Control · autonomous-ai bundleControl the device's RGB light when the user asks for a SPECIFIC color (e.g. "yellow", "red", "yellow", "red", "turn on color X", "enable X light"), an LED effect, or turning LEDs off. Do NOT use for ambiance/activity lighting (use Scene) or emotion expression (use Emotion).
- ▌ Claude Buddy · autonomous-ai bundleCoordinate with the Claude Buddy companion (Claude Desktop + Claude Code on the user's Mac) — voice-approve tool permission prompts and stay aware of Claude activity.
- ▌ Computer Use · autonomous-ai bundleOpen websites and apps and complete tasks on the user's paired Mac through Autonomous Buddy. Use for direct visible UI tasks such as "open Airbnb", "mở Chrome", "ghi vào Notes", forms, screenshots, and file organization. Do not use when the user asks a coding or research agent on the Mac to do the work; use harness-use instead, even if that agent will use a browser. The agent runs on the headless device; visible website/app interaction targets the paired Mac, not a browser installed on the device. Pure information research and physical device hardware use their own skills.
- ▌ Sensing Track · autonomous-ai bundleQuery flow event logs to answer questions about past sensing events — "Have you seen anybody between 10pm and midnight?", "Is there any motion in the last hour?", "What happened while I was away?". Also holds your OWN sleep history — "how many times have you slept?", "when do you usually go to sleep?".
- ▌ Servo Control · autonomous-ai bundleUse to aim/point/look the device in a DIRECTION, toggle servo state (hold/resume/release), or play a named servo animation (nod/shake/etc). ALSO the skill for SEARCHING — "where are you", "find my keyboard/cup/phone", "look around for X", "scan the whole room" — which sweeps the room with the camera via /servo/search (run it with curl DURING the turn and answer from its result), and for DEMONSTRATING the movement range ONLY when the request names MOVEMENT — "show me how far you can move", "how far can you turn", "show me your range of motion" — via /servo/demo. A bare "show me what you can do" or "what is your maximum capability" is a general question about abilities, NOT a movement request, and must not start the demo. Never answer a search or a range demo with an emotion. Directions are fixed named locations or axes — supported: desk, wall, left, right, up, down, center, user. Furniture and surfaces ("desk", "table", "floor", "ceiling", "wall", "door", "workspace") are ALWAYS directions, never tracking targ
- ▌ Servo Tracking · autonomous-ai bundleUse ONLY to follow/track/watch a movable physical OBJECT vision can recognize (cup, bottle, phone, hand, person, pen, book, remote, toy, keys, pet, a specific face). NEVER use for furniture or fixed locations (desk, table, wall, floor, ceiling, door, window, workspace, room) — those are directions; use servo-control /servo/aim. NEVER use for direction words (left, right, up, down, center). If the user combines a direction AND an object ("look at the desk and follow the cup", "point at the table and track the phone"), fire TWO markers in order — servo-control /servo/aim first, then /servo/track here. The verb "look at" is ambiguous — if what follows is furniture/location, route to servo-control instead.
- ▌ Input Branching · autonomous-ai bundleRoute voice input from the realtime voice agent pipeline based on message tags.
- ▌ Agent Management · autonomous-ai bundleLegacy Autonomous Buddy control for explicitly requested Buddy coding sessions. When the user asks a coding or research agent on their paired Harness computer to work, use harness-use instead. This manages explicit Buddy desktop CLI sessions; clicking apps and screenshots use computer-use.
- ▌ Music Suggestion · autonomous-ai bundleProactive music suggestion. Routed in by user-emotion-detection/SKILL.md (the router) on emotion.detected (camera) and speech_emotion.detected (voice) events when the synthesized mood is suggestion-worthy (sad/stressed/tired/excited/happy/bored) AND audio is idle AND cooldown is clear. Reuses injected context and emits log HW markers in the same reply as mood. Does NOT fire on motion.activity / [activity] events — those route to wellbeing/SKILL.md only. NOT for user-initiated music requests (those use the music skill).
- ▌ Speaker Recognizer · autonomous-ai bundleSelf-enroll voices after a clear self-introduction or explicit enrollment request; continue that enrollment, or list, forget, link, and identify voices when requested. Unknown Speaker labels, saved audio, and same-tag history alone do not activate this skill. Handle ordinary requests without identity lookup or a name question.
- ▌ User Emotion Detection · autonomous-ai bundleMaps a detected user emotion — from facial expression (emotion.detected) OR speech (speech_emotion.detected) — into a mood signal logged via the Mood skill, then picks one response route (music / checkin / action). This is about the USER's emotion (input), NOT the device's own expression — that's emotion/SKILL.md.
- ▌
- ▌ Claude Code Buddy · autonomous-ai bundlePush Claude Code activity to the user's device (e.g. a lamp) over the LAN. The plugin POSTs semantic events to a companion daemon on the device (HTTP, port 5002); the device turns them into its own feedback (LED / round display / voice). Supports connecting a device, pushing usage, sending notifications, and tuning how/when the user is alerted. Triggers: "connect my device", "push my usage to my device", "notify my device", "send to my device", "mute my device", "warn me earlier", "set warning threshold to N", "stop the task done notification".
- ▌ Faq · autonomous-ai bundleExplain how to run and use this repository's local Web UI, with detailed guidance for every Settings section and its visible controls. Use for questions about web development, Monitor, Setup, or Settings.
- ▌ Mood · autonomous-ai bundleTracks the USER's mood only — signals + synthesized decision from camera/voice/telegram. Do NOT use for emotion commands directed at the device ("show sad", "be happy", bare "sad now"); those go through emotion/SKILL.md and are never logged here. Music/wellbeing skills consume the latest decision.
- ▌ Audio · autonomous-ai bundleLow-level speaker and microphone hardware control — adjust volume, play test tones, record raw audio. Do NOT use for TTS/speech (that is the Voice skill).
- ▌ Guard · autonomous-ai bundleGuard mode for security monitoring. Two uses — (1) Toggle on/off when a friend says "guard mode", "watch the house", "I'm going out", or similar. (2) Handle any sensing event that carries a [guard-active] tag (e.g. [sensing:presence.enter][guard-active], [sensing:motion][guard-active]) with dramatic shock/curious emotion + Telegram broadcast. Do NOT fall back to normal sensing reactions while guard mode is on.
- ▌ Habit · autonomous-ai bundleTracks and analyzes behavioral patterns (habits) for known users based on their wellbeing, presence, posture, and activity history. Use when answering questions about a user's routines ("What are Leo's habits?", "Has Leo been keeping to his routine?", "Notice anything about my patterns?"), or when invoked from wellbeing/SKILL.md or posture/SKILL.md on a threshold nudge to refresh patterns and provide habit-aware phrasing. Also feeds music-suggestion/SKILL.md with `music_patterns` for personalized genre. Habit does NOT fire its own standalone nudge — it enriches wellbeing/posture threshold-nudge phrasing.
- ▌ Music · autonomous-ai bundlePlay and stop music from YouTube through the device's speaker on user request.
- ▌ Scene · autonomous-ai bundleActivate predefined lighting scene presets (reading, focus, relax, movie, night, energize) when the user asks for activity-based or environment lighting. Scenes control both color temperature AND brightness. Do NOT use for specific colors (use LED Control) or emotion expression (use Emotion).
- ▌ Hello · autonomous-ai bundleGreet the workspace. Use when the user asks the Starter harness to say hello or to prove the skill is loaded.
- ▌ Gis · autonomous-ai bundleBuild and verify interactive GeoJSON maps in Atlas, with local exploration, safe imports, feature inspection and export.
- ▌ Dimos · autonomous-aiCreate and inspect robotics projects in the DimOS Harness workspace, including its local starter and optional upstream integration.
- ▌ Fps · autonomous-aiDesign an arena level for Jev FPS (the ASCII map, the demons, the pace), then measure where Jev's decision rate stops being enough.
- ▌ Manim · autonomous-aiAnimate explanations with Manim Community — proofs, transforms, algorithms, graphs, data — as Python scenes rendered to MP4, and keep the pane playing the latest render. Use for any request that ends in an animation or an explainer video.
- ▌ Rdkit · autonomous-aiBuild molecules with RDKit — from SMILES or a scaffold, analogues and series (each with its parent), properties (MW, cLogP, TPSA, Lipinski, Veber, QED, alerts), similarity and substructure search, conformer ensembles written as SDF for the pane. Use for any request that ends in a molecule, a property or a chemical series.
- ▌ Score · autonomous-ai bundleTurn a musical brief into editable concert-pitch music, checked instrument parts and a listenable practice pack in the Score harness. Use for composing, arranging and revising trusted LilyPond projects.
- ▌ Typst · autonomous-aiWrite documents in Typst — papers, spec sheets, reports, letters, slides — compile them to PDF with the pinned typst binary, read its diagnostics, and keep the pane current. Use for any request that ends in a PDF or a printed page.
- ▌ Yosys · autonomous-aiWrite synthesisable Verilog-2005 for an iCE40 FPGA and take it to a bitstream — the language subset that synthesises, the testbench shape the pane draws waves from, the iCEBreaker pinout, how to read the utilisation and Fmax report, the mistakes that cost you a day (inferred latches, multi-driven nets, blocking assignments in sequential logic, missing reset), and ready-made UART / PWM / debounce blocks. Use whenever writing, simulating, synthesising or debugging RTL in this workspace.
- ▌ Jev Duel · autonomous-aiStage and verify Jev-on-Jev Reversi duels in OpenHarness's viewer, where Jev plays both sides and a third Jev referees.
- ▌ Jev Pong · autonomous-aiDesign and verify Jev's paddle-defense courts in OpenHarness's viewer, where Jev keeps a rally alive and loses it as the ball accelerates.
- ▌ Mujoco · autonomous-aiSimulate robots and scenes with MuJoCo — Menagerie robots (Unitree Go2, G1, H1, Berkeley Humanoid, Booster T1), your own MJCF, controllers and policies — record rollouts the pane runs as a live simulation, and train with MJX and MuJoCo Playground. Use for any request that ends in a simulation, a rollout or a policy.
- ▌ Studio · autonomous-aiBuild and verify a Babylon.js game progressively in OpenHarness's live Game Viewer.
- ▌ Marp Deck · autonomous-aiWrite a keynote-grade slide deck in Marp Markdown (deck.md) — the structure of a great talk, the copy rules, the two keynote themes and their slide classes, offline art (wallpapers, charts, device frames), the check, and the export.
- ▌ Web · autonomous-ai bundleBuild and verify interactive HTML experiences in Web Studio's live, sandboxed preview.
- ▌ Blender · autonomous-aiModel objects and scenes with Blender's Python (bpy) headless — primitives, modifiers, materials, collections, cameras, lights, animation — export glTF the 3D pane shows live, render stills and turntables, export STL. Use for any request that ends in a 3D model, a rendered shot or a glTF.
- ▌ Freecad · autonomous-ai bundleTurn measured design briefs or existing parts into editable FreeCAD projects with checked dimensions, bores, clearances, interference and fastener access; deliver separate STEP/STL parts, reference drawings and a portable project handoff.
- ▌ Jev Arena · autonomous-aiDesign and verify Jev Arenas in OpenHarness's live viewer, where Jev plays the world you build.
- ▌ Jev Guard · autonomous-aiFix a broken module under the live eye of Jev Guard, where Jev (TypeSafe's System One model) scores your own edits for progress, risk and trust.
- ▌ Bench · autonomous-ai bundlePlan real experiments and analyze supplied continuous measurements in Lab Bench. Use for defining factors and independent runs, randomized collection sheets, measurement CSV imports, experimental uncertainty and diagnostics, comparisons and follow-up confirmation runs with a reproducible report.
- ▌ Strudel · autonomous-aiWrite a live-coded track as a Strudel pattern — mini-notation, synths, effects, song structure — and check it with the verdict. Use whenever the workspace holds a .strudel file or the user asks for a beat, a groove, a bassline, a loop, a track, or music in the pane.
- ▌ Data · autonomous-ai bundleTurn user CSV files and a question into a typed, joined, repeatable local SQLite analysis with traceable records, browser revisions and verified portable exports.
- ▌ Game · autonomous-ai bundleCreate and revise original board or card games from a person's idea, with editable mechanics and components, real human playtests, reproducible simulations and a complete playable and printable kit. Use for tabletop game design, card drafting, cooperative puzzles, push-your-luck systems and new rules beyond the example game.
- ▌ Pilot · autonomous-ai bundleCreate and revise field-survey plans from supplied GeoJSON boundaries, exclusions, camera geometry and capture requirements. Use Drone Pilot for editable routes and sorties, recorded-flight CSV analysis, and portable GIS, CSV and report delivery.
- ▌ Archer · autonomous-aiShape a Jev Archer range (target speed, bullseye size, shots), then verify Jev plants the slow targets and leaks the fast ones.
- ▌ Jev Blocks · autonomous-aiDesign a falling-blocks challenge for Jev in blocks.json (gravity, speedup, garbage, a custom board, the piece mix, the style line), then read the verdict and report where Jev starts to break.
- ▌ Jev Lander · autonomous-aiDesign and verify Jev's landing missions in OpenHarness's viewer, where Jev is the flight computer throttling a booster down to a soft touchdown.
- ▌
- ▌ Jev Slalom · autonomous-aiDesign and verify Jev's slalom courses in OpenHarness's viewer, where Jev is the racer steering to thread every gate.
- ▌ Jev Trader · autonomous-aiDesign and verify Jev's paper-trading desks in OpenHarness's viewer, where Jev trades a synthetic market live.
- ▌ Openscad · autonomous-ai bundleTurn measured requirements into editable OpenSCAD part families, compare fit variants, and deliver checked STLs plus a portable project.
- ▌ Simskill · autonomous-aiCreate and inspect simulation projects in the SimSkill Harness workspace, including its local starter and optional upstream integration.
- ▌ Godot · autonomous-ai bundleBuild Godot games with GDScript, native gameplay assertions and sandboxed Web exports. Use for Godot Studio project and game-mechanic tasks.
- ▌ Circuitjs · autonomous-ai bundleWrite and fix circuits in CircuitJS1's text format — the `$` options header, element lines on a 16-px grid, scope `o` lines, slider `38` lines, layout rules, and the workflow that keeps the pane moving. Use this for every circuit in this workspace, whether writing a new `circuit.txt`, editing one, or reading the verdict's findings.
- ▌ Comfy MCP · autonomous-aiCreate and inspect generative media projects in the Comfy MCP Harness workspace, including its local starter and optional upstream integration.
- ▌ Browser · autonomous-aiTurn what a person wants off a website into a browse.json job, read what came back in results.csv, and sharpen the fields that came back thin.
- ▌ Catcher · autonomous-aiShape a Jev Catcher session (fall time, glove reach, field width), then verify Jev catches the slow pop flies and drops the fast ones.
- ▌ Jev Shopper · autonomous-aiDesign and verify Jev's shop windows in OpenHarness's viewer, where Jev calls the best buy as prices stream in and spends on paper.
- ▌ Studio 2 · autonomous-ai bundleCompose and revise complete original music from a brief or the user's MIDI and recordings, with editable notes, arrangements and real WAV/stem/MIDI/project delivery.
- ▌ Sheetsdoc · autonomous-ai bundleBuild coordinated editable DOCX reports, formula-driven XLSX workbooks and fresh LibreOffice PDF previews from structured source. Use for Sheet & Docs Studio work.
- ▌ Ableton AI · autonomous-aiCreate and inspect music projects in the Ableton AI Harness workspace, including its local starter and optional upstream integration.
- ▌ Bonsai MCP · autonomous-aiCreate and inspect architecture projects in the Bonsai MCP Harness workspace, including its local starter and optional upstream integration.
- ▌ Excalidraw · autonomous-aiDraw diagrams as .excalidraw files — architectures, flows, sequences, whiteboard sketches — with the scene helper or by editing the JSON, judged by the verdict and shown hand-drawn in the pane. Use for any request that ends in a diagram.
- ▌ Foam Agent · autonomous-aiCreate and inspect simulation projects in the Foam-Agent Harness workspace, including its local starter and optional upstream integration.
- ▌
- ▌ Jev Launcher · autonomous-aiDesign and verify Jev's command palettes in OpenHarness's viewer, where Jev ranks launch targets live per keystroke.
- ▌ Jev Pendulum · autonomous-aiDesign and verify Jev's balancing rigs in OpenHarness's viewer, where Jev keeps an inverted pendulum upright and loses it at high gravity.
- ▌ Harness Phaser · autonomous-aiUse this skill first in a Harness Phaser workspace. The project layout, the Vite dev-server pane and its live reload, the webview keyboard-focus rule (click-to-play gate and on-screen touch buttons), procedural art with no asset files, and .harness/verdict.json. Triggers on: Harness, the pane, dev server, keyboard focus, click to play, touch buttons, verdict, workspace layout, new game.
- ▌ Roundtable · autonomous-aiRun a decision through a panel of coding agents from different vendors — writing the motion, seating the room, the sealed-openings protocol, tagging the claim map, pressing a split, and writing a decision that picks and keeps its dissent. Read before opening a room.
- ▌ Gen Art · autonomous-ai bundleCreate original vector artwork and complete visual asset sets from a person's brief, with custom drawing programs, user-editable controls and real SVG/PNG/source delivery.
- ▌ Orcaslicer · autonomous-ai bundleTurn a user's STL and explicit machine/material requirements into compared OrcaSlicer plans, editable 3MF projects, checked G-code and a portable handoff. Use for Orca Slicer harness work.
- ▌ Quantum · autonomous-ai bundleBuild, explain and verify small quantum circuits in Quantum Studio's editable statevector simulator.
- ▌ Step Parts · autonomous-ai bundleFind, evaluate, and download common purchasable CAD parts from step.parts, including named off-the-shelf actuators, servos, motors, electronics boards, connectors, screws, bolts, nuts, washers, bearings, standoffs, and other catalog components. Use when Codex needs to search the hosted step.parts catalog before creating simplified placeholder geometry, resolve fuzzy part names, standards, aliases, or dimensions, choose a matching part, fetch a canonical .step file, verify checksums, or use the step.parts API/OpenAPI/catalog endpoints for standard part discovery.
- ▌ Jev Compactor · autonomous-aiDesign and tune a Jev Compactor session. Use when editing session.json, writing task vocabularies, or looking for settings where needle recall holds while the reduction is large.
- ▌ Jev Conductor · autonomous-aiCurate a live Jev improvisation in OpenHarness's viewer, where Jev composes chords, bass and melody bar by bar in real time.
- ▌ Firmware · autonomous-ai bundleBuild PlatformIO firmware and inspect real compilation, memory, artifacts and pin plans without implicitly accessing hardware.
- ▌ Direct · autonomous-ai bundleCreate and revise a usable brand identity and coordinated launch materials from a business brief, using the Forme project and the person's own artwork, text and production requirements.
- ▌ World Builder · autonomous-ai bundleTurn a user's brief into an editable voxel environment or asset kit in Voxel Worlds. Use for original scene design, modular assets, terrain sculpting, walkable spaces, importing VOX assets and delivering GLB/VOX files with an offline studio.
- ▌ Home Assistant · autonomous-ai bundleTurn home-automation requirements into editable Home Assistant YAML, tested what-if scenarios, native Core traces and a reviewed installation kit in Habitat. Use for automation authoring and revision, not unrequested device control.
- ▌ Grid Operations · autonomous-ai bundleLook after the models on the user's machines — one laptop or a fleet: recognise their private grid, ask what they need in plain words, pick a model that fits from disk, catalog or Hugging Face, start it with vision and context that fit, prove it answers with one bounded call, change or stop a running one, and use Grid routing, usage, media and training commands.
- ▌ Fleet Operations · autonomous-ai bundleManage the machines on a Harness account by conversation — read the fleet, link and unlink, rename, note and group, bring a new computer in, remove one. Use in a Machine Monitor workspace whenever the person asks about their computers, what is running on them, or wants one added, named, linked or retired.
- ▌ Autoresearch Mlx · autonomous-aiCreate and inspect science projects in the autoresearch-mlx Harness workspace, including its local starter and optional upstream integration.
- ▌ Juce Agent Toolkit · autonomous-aiCreate and inspect audio projects in the JUCE Agent Toolkit Harness workspace, including its local starter and optional upstream integration.