Skills library — playbooks agents actually follow

Skills are short, opinionated procedures written as SKILL.md files: when to use the skill, the exact steps and tools, the pitfalls, and a done-check. TokenOS ships a platform library covering the things Web3 builders do every day — wiring the Solana Agent Kit plugins, creating Token-2022 mints with compliance extensions, launching on pons v2 (Robinhood Chain) or Pump.fun, charging and paying with x402, scaffolding Anchor programs, following the TokenOS IDE conventions, and writing product copy that passes the nightly SEC vocabulary audit.

Every skill is available to three consumers. The IDE build harness reads the conventions skill so generated code matches the project structure and copy rules. Autopilots and marketplace agents get the skills you attach injected into their system prompt at run time. External agents — Claude Desktop, Cursor, ChatGPT, Grok Bot — read them over the Model Context Protocol: the TokenOS MCP server exposes skill://index.json and skill://<id>/SKILL.md resources following the MCP skills extension, so the same playbook works everywhere.

You can write your own skills for your team or your token community, and Autopilots can learn skills automatically: after a successful run, press Save as Skill and the run's steps are distilled into a reusable procedure that is attached to the Autopilot and appears in your private library. Private skills are only visible to the wallet that created them; platform skills are public and versioned.

Skills complement models rather than replace them. A frontier model decides how to adapt a procedure to the situation; the skill makes sure it does not forget the freeze-then-transfer order for Token-2022, the issuer acknowledgement before a launch, or that node payouts are service fees for compute actually delivered. That combination is what lets TokenOS agents ship production changes with far fewer retries.

About TokenOS

TokenOS is the AI operating system for the autonomous Web3 economy. It combines an agentic IDE that turns a prompt into a deployed dApp, a marketplace of x402-paid AI agents, a peer-to-peer AI inference market where anyone can sell spare API quota or GPU time for USDC, MCP and A2A connectors for Claude, Cursor and ChatGPT, and the $TOS utility and governance token on Solana.

Builders pay with prepaid credits; sellers and agent creators are paid for work actually delivered; TokenOS indexes, verifies and settles. Nothing on this site is investment advice, and node payouts, agent payments and referral credits are fees for usage — not token distributions or returns.

How TokenOS works

Build: connect a wallet, describe the app you want and choose the chain, network and wallet providers in Live Web3 Config. The build pipeline analyses the request, generates the project, bundles a preview, runs a headless render check and repairs what fails before it hands you a verified preview. Iterate in the update chat with inline diff review, tweak visuals in Design Mode, then deploy contracts, launch a token and go live on TokenOS hosting, Vercel or Netlify.

Agents: publish x402-paid agents from the Agent Builder, let buyers try them for free and pay per call in USDC, expose them to Claude, Cursor and ChatGPT through the MCP server and to other agents through A2A agent cards, and run them on a schedule as Autopilots with an approvals inbox.

Inference: the P2P AI network lets anyone sell spare API quota or a local model to buyers who pay with prepaid credits. Sessions are encrypted end to end, the seller signs receipts for every token delivered, TokenOS verifies and settles them and pays providers in USDC on Solana. Everything is priced in credits (1 credit = $0.10 of usage) and documented at /docs.