Skip to content
Back to search

ethskills

MarketplaceWorks with Claude CodeGitHub

The missing knowledge between AI agents and production Ethereum.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/austintgriffith-ethskills/badge.svg)](/listings/austintgriffith-ethskills)

HTML

<a href="/listings/austintgriffith-ethskills"><img src="/api/listings/austintgriffith-ethskills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 21 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. {
  2. "name": "ethskills",
  3. "owner": {
  4. "name": "Austin Griffith"
  5. },
  6. "metadata": {
  7. "version": "1.0.0",
  8. "description": "Ethereum development skills — corrects LLM blind spots on gas costs, L2s, DeFi protocols, security, and the current tool landscape."
  9. },
  10. "plugins": [
  11. {
  12. "name": "ethskills",
  13. "source": "./",
  14. "version": "1.0.0",
  15. "description": "Ethereum development skills — corrects LLM blind spots on gas costs, L2s, DeFi protocols, security, and the current tool landscape.",
  16. "author": {
  17. "name": "Austin Griffith"
  18. }
  19. }
  20. ]
  21. }
README.md · README · 81 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <img width="759" height="198" alt="image" src="https://github.com/user-attachments/assets/19afbd29-29cd-4b9a-bb67-c914cc5d9576" />
  2. LLMs think gas is 30 gwei. It's far lower — and they quote it from memory. They've never heard of ERC-8004 or x402. They hallucinate contract addresses. This site fixes that.
  3. ## How It Works
  4. Each skill is a markdown file. Give any URL to your AI agent — it reads it and instantly corrects its Ethereum knowledge.
  5. ```
  6. https://ethskills.com/SKILL.md ← table of contents
  7. https://ethskills.com/gas/SKILL.md ← just gas & costs
  8. https://ethskills.com/why/SKILL.md ← why ethereum
  9. https://ethskills.com/crops/SKILL.md ← CROPS architecture review
  10. ```
  11. ### Add the top-level SKILL.md to your agent's context
  12. The agent will look up the specific skills when needed.
  13. Just prompt your agent with this:
  14. ```
  15. Install the https://github.com/austintgriffith/ethskills/blob/master/SKILL.md skill
  16. ```
  17. ### Claude Code Plugin
  18. Install directly from GitHub — no clone required:
  19. ```bash
  20. /plugin marketplace add austintgriffith/ethskills
  21. /plugin install ethskills@ethskills
  22. ```
  23. ## Terminology
  24. **Say "onchain" not "on-chain."** The Ethereum community writes it as one word — no hyphen. LLMs default to "on-chain" but that's not how builders talk. Use "onchain" in all writing, documentation, and generated content.
  25. ## Skills
  26. | Skill | What LLMs Get Wrong |
  27. |-------|-------------------|
  28. | [Why Ethereum](why/SKILL.md) | Pectra/Fusaka shipped, gas is cheap now, AI agent angle |
  29. | [Ship](ship/SKILL.md) | Start coding before planning architecture, over-engineer with 5+ contracts when 1-2 will do, skip chain selection and the CROPS gate |
  30. | [CROPS Review](crops/SKILL.md) | Miss custody, privacy, exit paths, censorship resistance, and centralization risks in otherwise working apps/contracts |
  31. | [Protocol](protocol/SKILL.md) | Answer fork status from memory, read EIP status as fork inclusion, give unscheduled features ship dates |
  32. | [Gas & Costs](gas/SKILL.md) | Quote gas costs from memory, mix up wei and gwei, forget the L1 data fee on L2s |
  33. | [Wallets](wallets/SKILL.md) | EIP-7702 is live, signer authority limits, burned keys |
  34. | [Layer 2s](l2s/SKILL.md) | Think Base is still OP Stack, Polygon zkEVM still runs, Superchain interop is live |
  35. | [Standards](standards/SKILL.md) | Don't know ERC-8004, EIP-7702 status, EIP-3009 for x402 |
  36. | [Tools](tools/SKILL.md) | Don't know x402, Blockscout MCP, current tool landscape |
  37. | [Money Legos](building-blocks/SKILL.md) | Assume a protocol is live or dominant from headlines, skip fork-testing the composed flow |
  38. | [Orchestration](orchestration/SKILL.md) | Don't know SE2 three-phase build system |
  39. | [Contract Addresses](addresses/SKILL.md) | Hallucinate addresses — these are checked onchain. Assume the same address across chains, pick bridged over native |
  40. | [Concepts](concepts/SKILL.md) | Nothing is automatic, incentive design, randomness pitfalls |
  41. | [Security](security/SKILL.md) | Token decimals, reentrancy, oracle manipulation, vault inflation, pre-deploy checklist |
  42. | [Testing](testing/SKILL.md) | Test getters and OpenZeppelin internals, skip fuzz and fork tests on integrations, mock external protocols instead of forking |
  43. | [Indexing](indexing/SKILL.md) | Loop over blocks to read history, try to query historical state via raw RPC, ignore events as the primary read API |
  44. | [Frontend UX](frontend-ux/SKILL.md) | Onchain button rules, one-action-at-a-time approval flow, Address components, USD values |
  45. | [Frontend Playbook](frontend-playbook/SKILL.md) | Fork mode, fork demos, IPFS static export, ENS content hash |
  46. | [QA](qa/SKILL.md) | Treat "deploys without errors" as shipping, leave SE2 default branding, miss approve-button double-fire, mobile deep links |
  47. | [Audit](audit/SKILL.md) | Call one generic review pass an audit, miss systematic checklist coverage across AMM/lending/oracle/proxy/governance domains |
  48. ## Security Guardrails
  49. Skills teach restraint, not just capability. Every skill that touches keys, credentials, or funds includes explicit safety rules — because LLMs optimize for speed and will hardcode a private key into `git add .` if you let them. Coverage includes wallet keys, API keys, RPC URLs, and the common SE2 `scaffold.config.ts` trap.
  50. ## Methodology
  51. We test stock LLMs, find what they get wrong, and write corrections. Content is verified against onchain reality. If an LLM already knows something, we don't include it.
  52. **Every proposed change goes through [triage](https://github.com/austintgriffith/ethskills-research/blob/master/research/triage-methodology.md):** spawn a stock LLM, give it a realistic task, see what it gets wrong. Only verified blind spots survive.
  53. See the [research repo](https://github.com/austintgriffith/ethskills-research) for baseline audits, gap analysis, and full methodology.
  54. ## Contributing
  55. Something wrong or missing? Humans and agents are welcome to [open a PR](https://github.com/austintgriffith/ethskills/pulls). Read [CONTRIBUTING.md](CONTRIBUTING.md) first — the bar is "would a stock LLM get this wrong?"
  56. ## License
  57. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.