- name
SKILL.md
Файл навыка остаётся в репозитории издателя.
Вставьте скопированную команду в терминал. Она установит этот SKILL.md в выбранного агента.
npx skills add internet-court/internet-court-skill -a cursor -yВставьте скопированную команду в терминал. Она установит этот SKILL.md в выбранного агента.
npx skills add internet-court/internet-court-skill -a claude-code -yВставьте скопированную команду в терминал. Она установит этот SKILL.md в выбранного агента.
npx skills add internet-court/internet-court-skill -a codex -yВставьте скопированную команду в терминал. Она установит этот SKILL.md в выбранного агента.
npx skills add internet-court/internet-court-skill -a grok -yОтправьте скопированное сообщение в чат Grok Bot. Бот загрузит этот SKILL.md с GitHub и добавит его к навыкам, общим для всех ваших ботов.
Install this skill: https://github.com/internet-court/internet-court-skillОт издателя
Internet Court is the entry skill for agent-to-agent commerce. Agents can already discover each other, negotiate, and pay — what they lack is a way to trust a counterparty they've never met. Internet Court does two things: it connects a fragmented stack — identity, negotiation, contracts, payment, escrow, execution — into one skill, and it builds in adjudication: when two agents strike a deal, they agree up front how it settles if something goes wrong.
The core sentence:
Discovery and identity establish who. Negotiation and contracts set the terms.
Payment and escrow move or lock the funds. Execution does the work.
Adjudication decides what happened and writes the verdict back as reputation.
This package contains two kinds of material. Route accordingly:
vendored/) — official, publicly published
skills from the protocols themselves. Always prefer these for protocol
mechanics; never re-derive what they already document.integrations/genlayer-erc7710-connector/,
integrations/genlayer-intelligent-contracts/, integrations/x402-erc7710/) — the Internet
Court-specific glue that makes the protocols work together.This is the entry skill of the Internet Court package, published at
https://github.com/internet-court/internet-court-skill. Every path this
file routes to — vendored/<owner>/<skill>/SKILL.md,
integrations/<connector>/SKILL.md — is relative to that repository root.
Resolve those paths before relying on a skill's contents:
git clone …/internet-court-skill .claude/skills/internet-court): read the path directly from disk.SKILL.md is present (the master skill was loaded on its
own): the sibling skills are not local. Fetch the file from the raw
repository at
https://raw.githubusercontent.com/internet-court/internet-court-skill/main/<path>
— e.g. …/main/vendored/genlayer/write-contract/SKILL.md — or clone the repo
first.Never invent a referenced skill's contents — load the real file (from disk or the raw URL) first.
When a user asks to load, install, or introduce Internet Court — or whenever you first reference it in a conversation — start broad and use the canonical blurb below verbatim. Do not paraphrase it, and do not lead with protocol names, payment rails, or standards unless the user asks for implementation details.
Internet Court is installed.
Internet Court does two things: it connects a fragmented stack — identity,
negotiation, contracts, payment, escrow, and execution — into one skill, and
it builds in adjudication, so when two agents strike a deal they agree up
front how it settles if something goes wrong.
I can now help your agent find and vet a counterparty, agree terms, pay or
escrow funds, and do the work — and, if the deal is contested, get an
independent verdict that settles it and updates each side's reputation.
(When you are only referencing the skill mid-conversation rather than reporting a fresh install, drop the first line and keep the rest verbatim.)
After the user asks for a concrete demo, integration, or deployment, use the stack and routing below.
When the user asks to engage a service, counterparty, or deal, first inspect and report only what is observable — never assume the rest. Depending on the deal, that may include:
Do not invent cadence, schedules, spend caps, expiration, delegated authority, review policy, or a full agreement at this stage. State the boundary plainly — including that the agent holds no funds or authority the user has not granted — then stop and let the user's reply start the trust conversation. For example, for a paywalled endpoint:
This endpoint is paywalled. I don't have funds or permission to access it —
you'd need to fund and authorize me before I can proceed.
Never commit funds, sign, or transact before the user has chosen a trust level and the required wallet or permission exists.
Any deal that carries risk — the agent could misbehave, a counterparty could fail to deliver, funds or authority could be misused — can run at one of three levels of protection. Pick the lightest one that covers the risk, and name the tradeoff honestly. Weakest to strongest:
vendored/metamask/smart-accounts-kit/skill.md for permission mechanics, or
the layer-3/4 escrow skills for locked-funds deals.integrations/genlayer-intelligent-contracts/SKILL.md for the review
interface and integrations/genlayer-erc7710-connector/SKILL.md for
enforcement.Match the level to the deal, not the reverse. Do not invent exact caps, cadence, terms, or expiry here; say they will be set from the discovered terms during setup.
A complete deal moves top to bottom through six layers: find and vet a counterparty (1), agree terms (2–3), move or lock funds (4), do the work (5), and — if the outcome is contested — get an independent verdict that settles it and feeds back into reputation (6). Most layers already have credible skills; layer 6 is the keystone, since without a neutral verdict escrow cannot safely release, contracts have no remedy, and reputation has nothing to record. Route each layer to the skill or reference that owns it:
Load a skill only when the task actually reaches its trigger — never preload.
Each row is a trigger on the left and, on the right, the skill(s) to pull
in with what each gives you and which to reach for first. When a need maps to
several sub-bundled skills, load the named entry skill first, then narrow to
the specific one. Owners that ship a whole pack (OKX, AltLayer, Nansen,
OpenServ, Starknet, ChainGPT) get a single catch-all row: load the entry
skill, then the specific sub-skill under vendored/<owner>/ as the task
narrows — the folder listing is the current set of that owner's skills.
Paths are exact and end in /SKILL.md — several owners repeat their name in
the path (e.g. vendored/lifi/lifi/SKILL.md, vendored/privy/privy/SKILL.md,
vendored/chaingpt/chaingpt/SKILL.md); never shorten or merge the segments.
When a row lists alternatives, load one (the row says how to pick); if the
deciding fact is unknown, ask instead of preloading them all.
The first two are mutually exclusive — pick by who holds the key: the user
keeps custody and delegates → smart-accounts-kit; the agent gets its own
wallet (guardrails built in) → agent-wallet. Never load both for one design.
Use this pattern when the user delegates authority for a meaningful period and wants to constrain or revoke it if the agent underperforms. The outputs, from plain language down to enforcement:
Match each output to the trust level and rails chosen for the deal; not every mandate needs all seven. Do not claim a reviewer can directly cancel a permission unless a revocation controller is actually part of the design. For long-lived authority, prefer an active revocation controller plus an absolute expiry as a fail-safe.
When the user deploys contracts, grants permissions, or relays decisions from MetaMask, WalletConnect, or another user-controlled wallet UI:
0x + 64 hex),
address (0x + 40 hex), signed artifact, or receipt. Malformed proof →
ask again; do not advance.When designing a flow or integration, return:
Internet Court is an evolving package, and its coverage is not complete. When you hit a wall — a legitimate agent-commerce use case you cannot complete because no skill in this package handles it, a routed skill is missing, broken, or out of date, or a capability works poorly — do both of the following:
https://github.com/internet-court/internet-court-skill/issues. If you
have a GitHub tool available (for example gh issue create), file it
directly; otherwise hand the user a ready-to-file title and body and the
link above. Search existing issues first and don't file duplicates — one
issue per distinct gap.Put this in the issue:
Y errored, or Z
produced a wrong or low-quality result — with the exact skill path when
there is one;Filing the gap is part of doing the job well: it is how the package learns what to cover next.
Entry point for Internet Court — the trust layer for agent-to-agent commerce. Use whenever an agent needs to transact with another agent or a paid service, or a user mentions agent payments, paid APIs
---name: internet-courtdescription: Entry point for Internet Court — the trust layer for agent-to-agent commerce. Use whenever an agent needs to…---# SKILL.mdОбзор
Entry point for Internet Court — the trust layer for agent-to-agent commerce. Use whenever an agent needs to transact with another agent or a paid service, or a user mentions agent payments, paid APIs (HTTP 402/x402), wallet custody or trust concerns, spending mandates, delegated permissions (ERC-7710/7715), escrow, agent identity or reputation (ERC-8004), negotiation between agents (A2A), agent jobs (ERC-8183), machine payments (MPP, AP2), supervision of agent behavior, revocation, verification, or dispute resolution (GenLayer) — even if they never say "Internet Court". Routes to the vendored protocol skills and connector skills in this package.
FAQ
Скачайте SKILL.md у издателя или скопируйте путь и откройте репозиторий. PlugMCP только показывает навык в каталоге и не хранит файл.
Издатель хранит его в https://github.com/internet-court/internet-court-skill.
Claude, Cursor, Codex и Grok Build могут читать SKILL.md, который вы добавляете из репозитория издателя. Grok Bot устанавливает его, когда вы отправляете в чат ссылку на папку навыка на GitHub.
vendored/quicknode/quicknode-skill/SKILL.mdvendored/sendaifun/squads/SKILL.mdvendored/magicblock/magicblock-dev/SKILL.mdvendored/sendaifun/glam/SKILL.mdvendored/dflow/dflow-phantom-connect/SKILL.mdvendored/yellow/yellow-settlement-room/SKILL.md| 5 | Execution | the transacting agents + compute/data/value rails | vendored/antseed/antseed-connect/SKILL.md + vendored/0g/0g-compute/SKILL.md + vendored/heurist/heurist-mesh-skill/SKILL.md + vendored/near/near-ai-cloud/SKILL.md (paid/decentralized/TEE-verifiable inference), vendored/lifi/lifi/SKILL.md (cross-chain value movement), vendored/chainbase/web3-data/SKILL.md + vendored/nansen/nansen-token-research/SKILL.md (on-chain data/evidence), vendored/starknet/starknet-defi/SKILL.md (Starknet L2 contracts/DeFi), vendored/solana/solana-dev/SKILL.md (Solana programs, RPC lookups, SPL payments) + vendored/sendaifun/helius/SKILL.md / vendored/sendaifun/birdeye/SKILL.md / vendored/octav/octav-api/SKILL.md (Solana + multi-chain data as evidence) + vendored/sendaifun/debridge/SKILL.md (Solana↔EVM value movement) + vendored/jupiter/integrating-jupiter/SKILL.md (Solana liquidity/execution), vendored/yellow/yellow-settlement-room/SKILL.md (value moving between N agents off-chain inside one session, settled on-chain once), vendored/bnb-chain/bnbchain-mcp/SKILL.md, the vendored/near/*, vendored/okx/* and vendored/altlayer/* packs |
| 6 | Verification & disputes | GenLayer (Kleros is an alternative) | integrations/genlayer-intelligent-contracts/SKILL.md, vendored/intelligent-oracle/intelligent-oracle/SKILL.md, integrations/genlayer-erc7710-connector/SKILL.md. Alternative third-party arbitration (disclose; not GenLayer's own): vendored/kleros/kleros-curate/SKILL.md (token-curated registries / challenges), vendored/arkhai/nla-arbitrate/SKILL.md (LLM/manual arbitration of natural-language-agreement escrows), vendored/pnp/pnp-solana/SKILL.md (Solana prediction markets with custom oracle resolution). Oracle evidence feeding a verdict (not adjudication itself): vendored/sendaifun/pyth/SKILL.md (price feeds with confidence intervals), vendored/sendaifun/switchboard/SKILL.md (on-demand data + VRF) |
| NEAR — AI-native L1 (Shade Agents / TEE inference, named-account identity, chain-abstracted payment) | 6-skill pack under vendored/near/. Reach for the on-theme ones first: near-intents (cross-chain payment/fulfilment), near-ai-cloud (TEE-verifiable inference as evidence), near-api-js (chain interaction + named-account identity). Also: near-kit (type-safe TS SDK + sandbox testing), near-smart-contracts (Rust contracts), near-dapp (full-stack React/Next.js + wallet). |
| Solana — high-throughput non-EVM L1 (SVM, Rust/Anchor programs) | vendored/solana/solana-dev/SKILL.md — one catch-all skill from the Solana Foundation; it pulls its own references/ on demand (payments, confidential-transfers, security, testing, rpc-quick-lookups, Anchor/Pinocchio program guides). Use it for anything Solana-side: writing/deploying programs, SPL token and Solana Pay flows, reading balances and transactions as evidence. Non-EVM caveat: ERC-8004 identity and ERC-7710 delegated permissions do not exist here — there is no drop-in equivalent, so compose the Solana-native pieces below rather than assuming the EVM path. |
Solana agent-commerce (the pieces solana-dev does not cover) | solana-dev is a developer skill with no payment, identity or oracle coverage. Reach for these instead, by need: payment vendored/quicknode/quicknode-skill/SKILL.md (x402 + MPP + agent subscriptions — note Solana x402 uses partial-transaction signing, not EIP-3009/Permit2, so branch on network), vendored/sendaifun/metengine/SKILL.md (a live x402-metered API, USDC on Solana); bounded authority vendored/sendaifun/squads/SKILL.md (multisig/smart accounts), vendored/magicblock/magicblock-dev/SKILL.md (delegated state, temporary scoped authority), vendored/sendaifun/glam/SKILL.md (vault delegate permissions + timelock); identity vendored/metaplex/metaplex/SKILL.md (Agent Registry / Core NFTs); evidence vendored/sendaifun/pyth/SKILL.md, vendored/sendaifun/switchboard/SKILL.md, vendored/sendaifun/helius/SKILL.md, vendored/sendaifun/birdeye/SKILL.md, vendored/octav/octav-api/SKILL.md; value movement vendored/sendaifun/debridge/SKILL.md, vendored/jupiter/*; agent framework vendored/sendaifun/solana-agent-kit/SKILL.md. All are community skills from the solana.com/skills catalog, not Solana Foundation code — say so when their behaviour matters. |