defi-native v1.10.0
  Staying current

Keeping defi-native up to date.

New content, sources, and data are continually added to defi-native as onchain finance evolves. Here's how to keep it up to date.

Ask your agent to do it

The same trick as installing. Paste this and it handles the rest.

paste into your agent

>Update the defi-native skill by running: npx skills update defi-native

Or run one command

In a terminal. Add -y to skip the prompts.

terminal

$npx skills update defi-native

 bare npx skills update refreshes every skill you have

Or run npx skills update defi-native in a terminal.

The skill will not update itself, on purpose. Installing is your call, and a skill that silently rewrites its own files cannot be reviewed. What it will do is tell you, once per session, when the repo has moved ahead of your copy.

your agent, at the start of a session

 defi-native 1.9.0 installed, 1.10.0 available.

Live at the start of every session

Install the manual way, so the skill folder is a symlink to your clone. Now git pull is the update. Add a session hook that pulls before every run and the last thing you pushed is what your agent loads.

~/.claude/settings.json Claude Code
{
  "hooks": {
    "SessionStart": [
      {
        "matcher": "startup",
        "hooks": [
          {
            "type": "command",
            "command": "git -C \"$HOME/code/defi-native-skill\" pull --ff-only -q || true"
          }
        ]
      }
    ]
  }
}

--ff-only refuses to merge, so it can never touch a local edit. The || true means a session on a plane still starts. Skills load at session start, so a mid-session push lands in the next one.

No session hooks in your agent?

Pull on a timer instead. Same symlinked clone, and it works for Cursor, Codex, Grok and anything else reading that folder.

crontab -e any host, mac or linux
# pull every 30 minutes, quietly, never merging
*/30 * * * * /usr/bin/git -C "$HOME/code/defi-native-skill" pull --ff-only -q

Make sure what you pushed is worth pulling

On every push the verifier re-checks the manifest schema, enforces the writing conventions, and fails if a reference file went missing from the README. A second check compares every number printed on this page against the skill itself, so the page cannot quietly outlive what it describes. Source liveness runs on a monthly schedule instead, so a vendor's docs going down never blocks a deploy.

.github/workflows/pages.yml github actions
name: Publish site

on:
  push:
    branches: [main]

permissions:
  contents: read
  pages: write
  id-token: write

jobs:
  build:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-python@v5
        with:
          python-version: "3.12"

      # the same gate the pull request check runs
      - run: python3 scripts/verify_manifest.py --skip-network

      # refuse to publish a page whose numbers drifted
      - run: python3 scripts/build_site.py

      - uses: actions/upload-pages-artifact@v3
        with:
          path: site

  deploy:
    needs: build
    runs-on: ubuntu-latest
    environment: github-pages
    steps:
      - uses: actions/deploy-pages@v4

Switch it on once under Settings, Pages, Source, GitHub Actions. A monthly job already runs the same verifier and opens a pull request with proposed updates. Automation checks facts. People change judgment.