nano-core

Map of the Tailscale network (tailnet) and how to reach, operate, and deploy to remote machines over it via SSH. Use for any cross-machine task — remote install, deploy, restart, log-check, or file transfer.

Operate nano-core coding delegation. Use for /coder or /coding execution, /coder-plan or /coder_plan planning, natural-language coding approval prompts, delegated runs, run IDs, progress, cancellation, and final-result handling; not for direct coding or automatic delegation.

Diagnose nano-core runtime failures. Use for provider/model errors, Pi launch or skill-discovery failures, Telegram/WhatsApp routing, singleton locks, service state, IPC, SQLite state, scheduler behavior, or per-group logs; not for installation or feature work.

Install or onboard nano-core on a host. Use for first-time installation, prerequisites, runtime selection, provider/channel configuration, daemon setup, upgrades, or doctor checks; not for diagnosing an already-running incident.

Understand and operate nano-core itself. Use for questions about nano-core architecture, behavior, configuration, capabilities, skills, installation, troubleshooting, Telegram administration, or coding delegation; route focused work to the matching nano-core skill.

Configure and operate nano-core through Telegram. Use for bot enablement, main/admin chat claims, trigger routing, command authorization, delivery modes, media intake, polling conflicts, and Telegram-first operation; not for WhatsApp-only or general runtime incidents.

Set up and run an autonomous experiment loop for any optimization target. Gathers what to optimize, then starts the loop immediately. Use when asked to "run autoresearch", "optimize X in a loop", "set up autoresearch for X", or "start experiments".

Finalize an autoresearch session into clean, reviewable branches. Use when asked to "finalize autoresearch", "clean up experiments", or "prepare autoresearch for review".

Kimi-K2.5 Writing Skill.

Autonomous "night shift" loop agent for research, testing, documentation, and background tasks using sessions_spawn, exec, Git, and message tools.

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

Manage Trello boards, lists, and cards via the Trello REST API.

Add Gmail integration to nano-core. Can be configured as a tool (agent reads/sends emails when triggered from WhatsApp) or as a full channel (emails can trigger the agent, schedule tasks, and receive replies). Guides through GCP OAuth setup and implements the integration.

Add voice message transcription to nano-core using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

Normalize nano-core to Docker-first runtime defaults. Use when user asks for Docker parity, cross-platform setup, or to disable host runtime mode.

Add new capabilities or modify nano-core behavior. Use when user wants to add channels (Telegram, Slack, email input), change triggers, add integrations, modify the router, or make any other customizations. This is an interactive skill that asks questions to understand what the user wants.

Debug nano-core agent runtime issues (Docker default, host opt-in). Use when agent execution fails, runtime checks fail, or onboarding/startup is blocked.

Run initial nano-core setup. Use when user wants to install dependencies, authenticate WhatsApp, register their main channel, or start the background services. Triggers on "setup", "install", "configure nano-core", or first-time setup requests.

X (Twitter) integration for nano-core. Post tweets, like, reply, retweet, and quote. Use for setup, testing, or troubleshooting X functionality. Triggers on "setup x", "x integration", "twitter", "post tweet", "tweet".

Comprehensive AppleScript expertise for enterprise-grade macOS automation including multi-display management, URL scheme handling, deep linking, and complex workflow orchestration

The 'Awwwards Singularity' - Transforms websites into breathtaking digital experiences through cinematic motion, 3D graphics, and avant-garde typography. Eradicates boring, template-based web design.

Free OSINT reconnaissance to discover, validate, and build outreach-ready contact lists for businesses by region/industry. Uses DuckDuckGo, LinkedIn (free tier), and public records only. Generates structured CSVs for manual CRM import.

CLI Coding Agents.

Guides the agent through a short, repeatable debug loop: capture the failure, isolate the scope, draft a patch plan, and log the decision so the next agent can continue without rereading the entire repo.

Complete Discord server interaction via Discord bot API for posting messages, uploading/downloading images and files, editing/deleting messages, reading channel content, responding to mentions, and full server integration. Use when users need to (1) Post AI-generated images or content to Discord channels, (2) Download images from Discord for processing, (3) Automate Discord notifications and updates, (4) Manage bot messages (edit/delete), (5) Read channel messages and attachments, (6) Respond to bot mentions or tags, (7) List and interact with server channels, or (8) any other Discord server integration tasks.

Generate professional software documentation with rigorous research, Kimi K2.5 structured thinking, and Gemini 3 Flash modern design generation. Creates stunning docs that elevate your projects.

Complete DreamHost website management via SFTP/SSH for React JS deployments, multi-site routing, file operations, and content management. Use when users need to: (1) Deploy React applications to DreamHost hosting, (2) Configure routing for multiple React/static sites within a domain (subdomains or subdirectories), (3) Upload, edit, or delete website files, (4) Deploy static websites or blog content, (5) Backup or restore website directories, (6) Manage business website content and files, or execute server commands for any DreamHost website management tasks.

Gemini CLI for one-shot Q&A, summaries, and generation.

Search the web and X (Twitter) using xAI's Grok API with real-time access, citations, and image understanding

Adapted from Hugging Face's dataset creator skill for FF-Terminal, this skill provides comprehensive tools for creating, managing, and publishing datasets on the Hugging Face Hub. Specialized for agricultural and farm-related data including sensor readings, crop yields, weather data, soil measurements, and farming operations data. Supports multiple dataset formats and provides quality assurance features for data integrity.

Adapted from Hugging Face's evaluation manager skill for FF-Terminal, this skill provides comprehensive tools for managing evaluation results of machine learning models used in agricultural contexts. It supports tracking crop prediction models, yield forecasting systems, disease detection models, and other agricultural ML applications. Includes integration with model cards, benchmark comparisons, and performance tracking over time.

This skill enables publishing and managing research papers on the Hugging Face Hub. It supports creating paper pages, linking papers to models and datasets, claiming authorship, and managing paper metadata. The skill helps researchers share their work with the ML community and integrate papers with reproducible code and models.

Private LLM and vision via LM Studio. Auto-loads models. For text chat, code, image analysis. Default: mistralai/ministral-3-3b

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

This skill enables training and fine-tuning of language models using TRL (Transformer Reinforcement Learning). It supports various training methods including supervised fine-tuning, reinforcement learning from human feedback (RLHF), and parameter-efficient fine-tuning (PEFT). The skill integrates with Hugging Face Jobs infrastructure for scalable training.

Edit PDFs with natural-language instructions using the nano-pdf CLI.

Lightweight research playbook optimized for the FF-Terminal agent. Keeps citation tracking, evidence grading, and summary drafting predictable even when multiple investigations run in parallel.

Mobile-first responsive design with modern CSS Grid, Flexbox, and accessibility

Execute and orchestrate external CLI-based agents to delegate subtasks, obtain specialized outputs, or compose multi-agent workflows. Use this skill when: (1) A task requires capabilities from specialized external agents (math, weather, data processing, API clients, etc.), (2) You need to parallelize work across multiple agent instances, (3) Building multi-stage pipelines where different agents handle different processing stages, (4) Delegating to domain-specific agents for better results, (5) Running untrusted third-party agents safely with sandboxing, or (6) Orchestrating async/background agent execution for long-running tasks. Requires bash tool access and target CLI agents available in PATH.

Open satellite imagery using deeplinks with coordinates and zoom levels via bash `open` command. Capture screenshots at multiple zoom levels for land analysis, building inventory, structure identification, and agricultural planning. Use when user needs satellite imagery, aerial view, farm analysis, land survey, building detection, structure inventory, property boundaries, coordinates lookup, or OSINT of any location. Triggers on requests for overhead views, map screenshots, or geographic reconnaissance.