autonomous-ai

MANDATORY pre-reply check — applies to EVERY user message regardless of other skills, SOUL.md, AGENTS.md, or prior context. Always read this SKILL.md first. If {baseDir}/onboarding.json does not exist, IGNORE the user message and run onboarding instead. No…

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis.…

Run nf-core bioinformatics pipelines (rnaseq, sarek, atacseq) on sequencing data. Use when analyzing RNA-seq, WGS/WES, or ATAC-seq data—either local FASTQs or public datasets from GEO/SRA. Triggers on nf-core, Nextflow, FASTQ analysis, variant calling, gene…

This skill should be used when scientists need help with research problem selection, project ideation, troubleshooting stuck projects, or strategic scientific decisions. Use this skill when users ask to pitch a new research idea, work through a project…

Deep learning for single-cell analysis using scvi-tools. This skill should be used when users need (1) data integration and batch correction with scVI/scANVI, (2) ATAC-seq analysis with PeakVI, (3) CITE-seq multi-modal analysis with totalVI, (4) multiome…

Performs quality control on single-cell RNA-seq data (.h5ad or .h5 files) using scverse best practices with MAD-based filtering and comprehensive visualizations. Use when users request QC analysis, filtering low-quality cells, assessing data quality, or…

Set up your bio-research environment and explore available tools. Use when first getting oriented with the plugin, checking which literature, drug-discovery, or visualization MCP servers are connected, or surveying available analysis skills before starting a…

Package an escalation for engineering, product, or leadership with full context. Use when a bug needs engineering attention beyond normal support, multiple customers report the same issue, a customer is threatening to churn, or an issue has sat unresolved…

Harness runs coding agents (Claude Code, Codex and others) as harnesses, sessions the person can watch and join in the Harness app, on this computer or their other machines. Use it to start another agent on work that can run beside yours, needs another…

Look after the models on the user's machines — one laptop or a fleet: recognise their private grid, pick the model and settings that fit this machine for coding without asking, start it with the longest context the machine can give (never under 64K), say what…

Build or update the person's About You — a short profile of how they work, from their own messages across every agent and what their agents saved about them. Use when asked to "build my About You", "update About You", "what do you know about me", or to…

Inspect Harness sessions, explain activity and resource readings, preview cleanup, and stop or open explicitly selected sessions through their owning daemons.

Reuse what LM Studio already has on this computer through its `lms` CLI: adopt its running server into the person's fleet, serve its MLX models, or serve its GGUF files without it. Load before touching LM Studio, its models or its server.

Reuse what Ollama already has on this computer: adopt a running Ollama server into the person's fleet, or serve an Ollama-downloaded model without Ollama. Load before touching Ollama, its models or its settings.

Serve an MLX or Hugging Face safetensors model already on this Mac with mlx-lm's server and join it to the person's fleet. Load before installing, starting or stopping mlx-lm, or when `fleet models` lists an `mlx` or `safetensors` model on Apple silicon.

Serve a Hugging Face model with SGLang on a Linux machine with an NVIDIA or AMD GPU, configured from the model's SGLang cookbook page — or, when it has none, from the model's own files — and join it to the person's fleet. Load before installing, configuring,…

Run, resume, or diagnose one Autonomous Workshop Wish through its frozen Spark, Forge, or Quest effort route using native Manager Goals, tools, and subagents while preserving deterministic host gates and host-controlled effects.

Brainstorm how a toy or product could look in quick Concept Rounds of generated Concept Images, shown side by side for the human to pick from and react to, round after round, until they mark one chosen. Use when the human wants shape or style ideas, a new…

Invent an original motion toy inspired by a current Trend - shortlist Trends with dated evidence, run a contest of six personality designers through design-a-toy Stages 1-2, gate and round-robin judge their drafts, then finish the winner and hand it to…

Build a toy from a Design Contract until it conforms - run `workshop wish` as round 0, detect every nonconformance against the contract, and run `workshop fix` rounds until none remain, publishing only the conforming build. Can run unattended - one session…

Design any physical Workshop toy - a vehicle, a jointed robot, a bone dragon, a puzzle, a game - with an Inventor before any run starts - grill the idea into a frozen spec, draft the Design Contract, generate one reference image per unique geometry plus the…

Resync the Make skills Workshop vendors from autonomous-product-to-cad (cad, image-to-cad, wiki, ...) to upstream origin/main - check what moved, three-way merge it into a fresh worktree, refresh LOCK.json and PROVENANCE.md, run the suite, then fast-forward…

Apply Abstract Boardgame Oracle's selected-Inventor method to an original abstract strategy game across Workshop stages.

Apply Ad Astra's method to an impact-first astronomy reskin of a public-domain board game across Workshop stages.

Discover and use linked third-party services (Gmail, Google Calendar, Google Drive, Notion, Figma, Asana, Linear, GitHub, Ahrefs, Facebook Fan Page, Shopify store, eBay seller and others). Use for connection-status questions and requests to read, search or…

Camera 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:{}]…

Use to aim/point/look the device in a DIRECTION, toggle servo state (hold/resume/release), or play a named servo animation (nod/shake/etc). In a movement/hold context, "back to normal", "turn to normal position" and "return to idle" mean resume; "look…

React 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 (→…

Manage 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…

Delegate digital work to agents on the computer paired through Harness; discover Store packages and prepare an agent when needed. For Lamp, prefer when connected for coding, research deliverables, documents, slides, spreadsheets, data analysis, design, CAD,…

Route voice input from the realtime voice agent pipeline based on message tags.

Push 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…

Understand voice input from the realtime voice agent pipeline. Messages may contain [voice-instruction]/[transcript] (delegated with context), [HANDLED]/[REPLY] (chit-chat already spoken), or plain text. Route and respond accordingly.

Detect which third-party connectors (Gmail, Google Calendar, Google Drive, Notion, Figma, Asana, Linear, GitHub, Ahrefs, …) are connected to this device, and use them to answer the user. Use when the user asks what's connected ("what connectors do I have",…

Self-enroll a voice for speaker recognition. Activate ONLY when (a) a mic `Unknown Speaker:` turn carries a clear self-introduction ("I'm X", "my name is X", "tôi là X"...), (b) prior same-tag `[voice:voice_N]` turns can be combined with a now-named turn, (c)…

Guard 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],…

React to passive sensing events from the lamp — presence, sound, light, fire hazard. Events arrive as [sensing:<type>] messages and each gets an emotion marker + optional short line. Does NOT handle motion.activity (→ wellbeing) or emotion.detected /…

Query flow event logs to answer questions about past sensing events — "Have you seen anybody between 10pm and 12pm?", "Is there any motion in the last hour?", "What happened while I was away?".

Camera 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:{}]…

Manage the lamp's face recognition roster — enroll new faces (3 paths: user-supplied photo, agent-captured snapshot on user request, or lelamp's familiar-stranger prompt) and maintain the enrolled set (status / remove / reset). All enrolled persons are…

The tool card for a KiCad harness (KiCad-native) workspace — every kicadpy command, its request shape, the publisher, the verdict, and how to find KiCad's CLI and Python on this machine. Read before the first board and whenever a command's shape is in doubt.

Use when the user wants to create, edit, or fabricate a PCB from a natural-language description — "design me a macropad", "an ESP32 soil-moisture board", "a desk air monitor", "add a second button", "make the board smaller", "fix the DRC error", "regenerate…

Bring a missing block in from the supplier — fetch the real footprint, record the provenance, grade it — instead of refusing the ask or inventing a circuit from a datasheet. Use when a board needs a capability the golden-block catalog has no block for.

Enrich a short or vague hardware idea into a build-ready board brief before any circuit is written. Use when the user asks for a device in a few words — "a plant waterer", "a desk CO2 monitor", "a macropad", "a little box with a screen", "something that logs…

Run a finished board past a panel of expert reviewers before anyone pays a fab. Use after circuitcode reports a clean build and before ordering — "is this ready to make", "review the board", "design review", "can we order these", "check it before I spend…

Lock the BOM identities of an Autonomous Circuit board into parts.json — one exact orderable LCSC number per part, with package, Basic/extended status, stock, unit price, and the date it was checked. Use when the user pins, swaps, or questions a component —…

Open a generated board in the Autonomous Circuit app. Use when the user asks to see, preview, or open the board — "show me the board", "open the schematic", "let me see the PCB", "show the gerbers", "open it in the app" — after circuitcode has generated it.…

Use when the user wants to create, edit, or print a parametric 3D model from a natural-language description — "phone stand", "wall mount", "honeycomb tray", "GoPro adapter", "vase" — or to tweak, re-render, or fix an existing CadQuery `.py` part for hobbyist…

Enrich a short or vague 3D-object prompt into a detailed, print-ready design brief before modeling. Use when the user asks for an object in a few words — "phone stand", "wall hook", "pen holder", "planter", "GoPro mount" — and the request lacks dimensions,…

Use when the user asks to develop, build, implement, or add a new FEATURE end-to-end in the Panda desktop app and wants it taken all the way to a pull request. Triggers on "build/add/implement a feature", "ship this", "take it to a PR" for multi-step work…

Use when launching, starting, running, or driving the Panda desktop app (Tauri shell + Vite viewer) — to see a change live, smoke-test the chat/CAD UI, or keep the app running across steps. Covers cargo-not-on-PATH, the blank-window dev port footgun, and…

Start or reuse CAD Viewer and return review links for explicit CAD, robot-description, and G-code files. Use when visually reviewing `.step`, `.stp`, `.stl`, `.3mf`, `.gcode`, `.dxf`, `.urdf`, `.srdf`, or `.sdf` files, especially when handed off from CAD,…

Find, 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…

Delegate digital work to agents on the computer paired through Harness; discover Store packages and prepare an agent when needed. For Lamp, prefer when connected for coding, research, documents, slides, spreadsheets, data analysis, design, CAD, simulation and…

Operate apps/websites on the paired Mac via Buddy: Calendar, Notes, forms, screenshots, files. Never use the headless device's browser. Agent delegation uses harness-use; pure research/hardware use their own skills.

Use 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…

Push 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…

Use to aim/point/look the device in a DIRECTION, toggle servo state (hold/resume/release), or play a named servo animation (nod/shake/etc). In a movement/hold context, "back to normal", "turn to normal position" and "return to idle" mean resume; "look…

React 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 (→…

Camera 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:{}]…

Discover 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…

Route voice input from the realtime voice agent pipeline based on message tags.

Manage 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…

Interact with the user's desk display device (Thinking Desk) over LAN. Supports pairing, sending notifications with plain text, rich layout (positioned text, shapes, progress bars), and buzzer sounds. Sends task-done notification + usage data when Claude…

Pair and control an Autonomous Thinking Desk display from Codex. Use for desk-display pairing, custom notifications, Codex usage, builder insights, notification settings, status, or unpairing.