--- title: "Radix Skills" path: "/developers/ai-agents/radix-skills" version: "1.0.0" author: "Hydrate" createdAt: "2026-08-06T11:11:53.037Z" updatedAt: "2026-08-06T11:11:53.037Z" --- # Radix Skills | **Type** | Agent skill package | | **Author** | [xstelea](https://github.com/xstelea) | | **Skills** | 1 (`radix`) | | **Reference Files** | 40 (~534 KB) | | **Requires** | Local `radix-web3.js` + `radixdlt-scrypto` checkouts | | **Registry** | [skills.sh](https://www.skills.sh/xstelea/radix-skills/radix) | | **Licence** | None declared | | **Published** | 21 June 2026 | | **Repository** | [GitHub](https://github.com/xstelea/radix-skills) | ## Introduction [radix-skills](https://github.com/xstelea/radix-skills) is an installable **agent skill** that gives an AI coding agent a routed set of Radix reference material and instructs it to check what it reads against local copies of the Radix source. The repository publishes a single skill, `radix`, whose stated purpose is to let an agent "build or debug Radix code from local source checkouts rather than memory or web snippets". It is the work of [xstelea](https://github.com/xstelea), who also maintains [Radix Context](/developers/ai-agents/radix-context), [Hookah](/developers/tools/hookah) and the [Awesome Radix MCP Servers](https://github.com/xstelea/awesome-radix-mcp-servers) index, and who described himself in the [Radix DLT Official Telegram](https://t.me/radix_dlt/997291) on 6 August 2026 as previously "lead of the dApp engineering team", having "put all my accumulated radix knowledge into that skill". A skill differs from a context pack in what it does at load time. [Radix Context](/developers/ai-agents/radix-context) copies 23 documents into a project and leaves the agent to find them. A skill is a described capability the agent selects on its own: the [skills.sh](https://www.skills.sh/xstelea/radix-skills/radix) listing carries a description that tells the agent when the skill applies, and the skill body then routes to the one or two guides that fit the task instead of loading everything. The two projects are complementary rather than successive — radix-skills names radix-context in its own research strategy as an optional "candidate map for topics and vocabulary". ## What It Contains The skill ships **40 reference files totalling roughly 534 KB**, of which 38 are topic guides named `guide-*.md`. Each guide states the source paths it is drawn from, a mental model, an example, and usage notes for one area of Radix work. The coverage is wide enough to be worth listing: - **Transactions** — [manifest syntax](/developers/transactions/01-manifest-language) and instructions, the [V1/V2 lifecycle](/developers/transactions/02-transaction-lifecycle), [Radix Engine Toolkit](/developers/transactions/04-radix-engine-toolkit) call sites, the Rust `radix-transactions` crate, [subintents and pre-authorisations](/contents/tech/core-concepts/subintents-and-pre-authorizations), receipts and events, and [costing and fees](/developers/transactions/03-transaction-fees). - **Ledger primitives** — resources and vaults, metadata, native pools, packages and components, [access rules](/developers/scrypto/03-authorization-and-badges), role assignment, access controllers, account lockers, royalties, and [SBOR](https://docs.radixdlt.com/docs/sbor). - **Client and wallet** — the [Gateway API](https://docs.radixdlt.com/docs/network-gateway), transaction streaming with state-version checkpointing, the [Radix Wallet](/developers/frontend/01-radix-dapp-toolkit) connect flow, and [ROLA](/developers/frontend/03-rola-authentication) challenge generation and verification. - **Staking** — [validator](/contents/tech/core-concepts/staking) behaviour, consensus-manager reads, liquid stake units, claim NFTs, unstaking and owner-badge operations. - **Tooling** — the `rdx` CLI, the Rust `scrypto` and `resim` binaries, `rtmc`/`rtmd` manifest conversion, Effect service patterns, TypeScript configuration, dependency and supply-chain hygiene, testing, and error diagnostics. - **Payments** — a guide to [x402](https://x402.org/) payment middleware, facilitator validation and settlement, which the wiki covers separately at [AI Agents & x402 Payments](/developers/ai-agents/ai-agents-and-x402). Alongside the guides the repository carries a 40 KB Python validation script, `validate-radix-skill.py`, that checks the guides against the source repositories they cite, and an [openai.yaml](https://github.com/xstelea/radix-skills/blob/main/radix/agents/openai.yaml) agent descriptor. ## Installation and Prerequisites The skill installs from the [skills.sh](https://www.skills.sh/xstelea/radix-skills/radix) registry, an open-source skill index published by Vercel Labs, which detects the coding agent in use: `npx skills add xstelea/radix-skills --skill radix` Installation alone is not enough to use it as designed. The skill's prerequisite step requires two source checkouts at the root of the repository being worked on: ``` ./.repos/radix-web3.js ./.repos/radixdlt-scrypto ``` A bundled script, `prepare-radix-sources.sh`, clones both, adds them to `.gitignore`, and installs the [rdx-cli](https://www.npmjs.com/package/rdx-cli) npm package globally when the `rdx` binary is missing. The script is written to fail rather than report success when `git` or `npm` is unavailable, when an existing checkout points at the wrong `remote.origin.url`, or when `rdx-cli` installs but `rdx` is not on `PATH`. The skill's own setup notes say a failed setup means "Radix-specific work is not source-backed yet". One consequence is recorded in the repository's own [architecture decision record](https://github.com/xstelea/radix-skills/blob/main/docs/adr/0001-use-local-source-checkouts.md), which chose local clones over submodules or vendoring: existing clones are never updated automatically, so a stale checkout will silently ground the agent in old source until someone refreshes it deliberately. ## Design: Routing, Not Recall The skill's research strategy is explicit about the order of authority, and it puts its own prose last. An agent is told to load the one matching guide, inspect similar code already in the user's repository, optionally consult [radix-context](/developers/ai-agents/radix-context) as a vocabulary map, and then **verify every context-derived fact against the source paths the guide names** before using it in code. Public web documentation is reserved for questions local source cannot answer. Cloned repositories are read-only: the skill forbids importing application code from `.repos`. That ordering is a direct response to the failure mode these packages exist to fix. A model asked to write [Scrypto](/developers/scrypto/01-fundamentals) or a [transaction manifest](/contents/tech/core-protocols/transaction-manifests) from memory tends to produce plausible code against an API version that no longer exists, because Radix's surface has changed substantially across [Babylon](/contents/tech/releases/radix-mainnet-babylon) and its protocol updates while the public corpus the model trained on did not. Pinning the answer to a checkout on disk makes the failure visible instead of silent — a missing or mismatched clone is an error the setup script raises, whereas a confidently wrong API call is not. ## Provenance and Caveats The 6 August 2026 announcement was a repost, not a release. The repository has been public since **21 June 2026** and its entire history is [two commits made that day](https://github.com/xstelea/radix-skills/commits/main), with no code changes in the seven weeks between publication and the announcement that drew the community's attention. The [skills.sh](https://www.skills.sh/xstelea/radix-skills/radix) listing recorded **six installs** and the GitHub repository zero stars and one fork on the day it was announced — useful context for anyone reading the reaction as evidence of adoption. Three points a prospective user should check for themselves: - **No licence is declared.** The repository carries no `LICENSE` file. By [GitHub's own stated default](https://docs.github.com/en/site-policy/github-terms/github-terms-of-service), publishing a repository without a licence grants other users no rights to reproduce, distribute or create derivative works beyond viewing and forking it — whatever the one-line install command implies. This is unlike the author's [Hookah](https://github.com/xstelea/hookah), which is MIT-licensed. - **One of the two source anchors is not official.** `radixdlt/radixdlt-scrypto` is the [canonical Scrypto repository](https://github.com/radixdlt/radixdlt-scrypto), but [radix-web3.js](https://github.com/xstelea/radix-web3.js) is the author's own library — itself unlicensed — rather than a [radixdlt](https://github.com/radixdlt) org project. Guidance about "the Radix codebase" therefore means the official engine plus one third-party TypeScript client, and the majority of the guides describe that client's package layout. - **The registry's automated audits are not unanimous.** skills.sh reports three scans of the skill: Gen Agent Trust Hub pass, Socket pass, and [Snyk](https://snyk.io/) *warn*. A skill is instructions an agent will act on, and the setup script installs a global npm package and edits `.gitignore`, so the contents are worth reading before installing. ## External Links - [radix-skills – GitHub Repository](https://github.com/xstelea/radix-skills) - [radix skill – skills.sh listing](https://www.skills.sh/xstelea/radix-skills/radix) - [xstelea/radix-web3.js – required source checkout](https://github.com/xstelea/radix-web3.js) - [radixdlt/radixdlt-scrypto – required source checkout](https://github.com/radixdlt/radixdlt-scrypto) - [rdx-cli on npm](https://www.npmjs.com/package/rdx-cli) - [Announcement in Radix DLT Official Telegram (6 August 2026)](https://t.me/radix_dlt/997273)