Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free
6,000+ web scrapers for your AI agent, start free logo6,000+ web scrapers for your AI agent, start free

Apify gives your agent live web data: 6,000+ prebuilt scrapers and actors, MCP-ready. Sign up free with $5 in usage credits.

Try Apify free
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free
Reach 48,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here

Summary

Kleros ecosystem skills — IPFS uploads via x402 gateway, Curate token-curated registries (Light Curate, Stake Curate, Scout).

Install to Claude Code

/plugin install kleros-skills@kleros-skills

Run in Claude Code. Add the marketplace first with /plugin marketplace add kleros/kleros-skills if you haven't already.

README.md

Kleros Skills

Knowledge base for AI agents working with Kleros — the decentralized justice protocol.

Adapted from ethskills, credits to @austintgriffith

Install

Claude Code:

/plugin marketplace add kleros/kleros-skills
/plugin install kleros-ipfs-upload@kleros-skills

OpenClaw:

clawhub install kleros-skills

Codex: Create AGENTS.md in your repo root with:

Read https://skills.kleros.io/SKILL.md and follow it before interacting with Kleros protocol.

Any agent: Paste the prompt Read https://skills.kleros.io/SKILL.md or curl -s https://skills.kleros.io/SKILL.md.

Skills included

  • kleros-ipfs-upload — Upload one Kleros file per paid request to IPFS via the x402 gateway on Base mainnet. Reuse a CID for identical bytes; upload different contents separately.
  • kleros-curate — Operate Kleros Curate token-curated registries: Light Curate, Stake Curate (PGTCR), and Scout on Ethereum, Gnosis, and Sepolia. Submit items, challenge requests, fund appeals, deploy and verify lists.

Feedback

Something broken or confusing in a skill? Fetch feedback/SKILL.md — it teaches an agent (or its human operator) how to file a structured report via the Kleros MCP, gh CLI, or a prefilled GitHub issue URL.

Project structure

SKILL.md                    # Top-level entry point / router (also served as /llms.txt)
index.html                  # Landing page (deployed on Netlify)
kleros-ipfs-upload/         # Published skill — IPFS uploads via x402
kleros-curate/              # Published skill — Curate token-curated registries (Light Curate, Stake Curate, Scout)
openclaw-skill/             # OpenClaw-compatible skill package
feedback/                   # Agent-to-maintainer feedback channel (kleros-feedback skill)
.claude-plugin/             # Claude Code plugin manifest
  plugin.json               # Plugin definition (version source of truth)
  marketplace.json           # Catalog index

Development

npm install
npm test

Landing page: npx serve . then open http://localhost:3000.

Branch model

This repo uses a two-branch model to keep end-user plugin installs lean.

Why: claude plugin marketplace add and clawhub install clone the entire git repository to user machines (twice — once for the marketplace mirror, once for the version-pinned cache). Everything committed ships to every user. Without this split, dozens of planning files, tests, and dev-only scripts would land in ~/.claude/plugins/... on every install. There is no native .claudeignore / files field in the plugin spec at the time of writing, so the split is the cleanest way to scope what reaches consumers.

How:

| Branch | Role | What's on it | |--------|------|--------------| | dev | Source of truth — all human work, PRs, planning artefacts, tests, build tooling | Full repo | | master (default) | Consumer-facing — what plugin installs and Netlify serve | dev minus the strip-list |

Strip-list (removed from master): .planning/, test/, scripts/, package.json, yarn.lock, .yarnrc.yml, root FEEDBACK.md, root HANDOVER*.md.

Keep-list (present on both branches): .claude-plugin/, skill dirs, feedback/, root SKILL.md, index.html, netlify/, .well-known/, sitemap.xml, robots.txt, favicons, LICENSE, README.md, CHANGELOG.md, .github/workflows/.

master is regenerated automatically by .github/workflows/sync-master.yml on release-tag pushes. Direct human pushes to master are discouraged — the workflow will overwrite them on the next sync. Tag protection rules restrict who can create release tags; the sync workflow itself runs under a dedicated kleros-skills-sync GitHub App identity scoped to this repo.

For the full design rationale, security model, and rejected alternatives, see SEED-002 on the dev branch.

Contributing

1. Branch from dev (or fork and branch from your fork's dev) 2. Make your changes 3. Run npm test locally 4. Open a PR targeting dev — never master

Releases (maintainers)

1. Merge release-ready commits into dev 2. Bump the relevant version per the release procedures — skill content change → skillname@vX.Y.Z; plugin manifest or distribution change → .claude-plugin/plugin.json bump + vX.Y.Z 3. Tag (GPG-signed) and push:

   # Skill release
   git tag -s "kleros-curate@v1.0.1" -m "release notes here"
   git push origin "kleros-curate@v1.0.1"

   # Plugin-level release (digit-anchored)
   git tag -s "v2.1.0" -m "release notes here"
   git push origin "v2.1.0"

4. The sync Action runs:

  • npm test (must pass)
  • npm run update-digests freshness check (must pass)
  • Strips dev-only files
  • Sanity-checks the stripped tree (asserts strip-list absent and keep-list present)
  • Force-pushes the result to master under the kleros-skills-sync[bot] identity

5. master redeploys to Netlify; the new release is live for plugin installs within minutes

If any gate fails, master stays at the previous good state — the tag exists but the release does not reach users until the issue is fixed and a new tag is pushed.

Links

Related plugins

Browse all →