bot-hub/scripts/catalog.mjs

#!/usr/bin/env node
// Write the catalogue migration: every skill Hanzo Bot ships, as Base records.
//
//   git -C ../bot archive <ref> skills | tar -x -C /tmp/bot
//   node scripts/catalog.mjs /tmp/bot/skills <commit>
//
// Each directory holding a SKILL.md is one skill: its slug is the directory
// name, its display name and summary come from the SKILL.md front matter, and
// every file in the directory is carried inline, so the hub serves the skill
// with no object storage behind it. The output replaces
// base/hz_migrations/1709000001_catalog.js; rerun it against a newer commit to
// move the catalogue.

import { createHash } from 'node:crypto'
import { readdirSync, readFileSync, statSync, writeFileSync } from 'node:fs'
import { join, relative } from 'node:path'

const [root, commit] = process.argv.slice(2)
if (!root || !/^[0-9a-f]{40}$/.test(commit ?? '')) {
  console.error('usage: node scripts/catalog.mjs <bot skills dir> <40-hex commit>')
  process.exit(2)
}

const RESERVED = new Set([
  'auth', 'changelog-preview', 'download', 'integrations', 'personas', 'resolve',
  'search', 'stars', 'telemetry', 'tokens', 'upload', 'users', 'whoami',
])

function frontmatter(text) {
  const m = text.match(/^---\n([\s\S]*?)\n---\n/)
  if (!m) return {}
  const field = (key) => {
    const line = m[1].match(new RegExp(`^${key}:\\s*(.+)$`, 'm'))?.[1]?.trim()
    if (!line) return undefined
    return line.startsWith('"') ? JSON.parse(line) : line.replace(/^'(.*)'$/, '$1')
  }
  return { name: field('name'), description: field('description'), version: field('version') }
}

function files(dir) {
  return readdirSync(dir, { recursive: true })
    .map((entry) => join(dir, entry))
    .filter((path) => statSync(path).isFile())
    .sort()
}

const skills = []
for (const slug of readdirSync(root).sort()) {
  const dir = join(root, slug)
  if (!statSync(dir).isDirectory()) continue
  const skillMd = join(dir, 'SKILL.md')
  try { statSync(skillMd) } catch { continue }
  if (!/^[a-z0-9][a-z0-9-]*$/.test(slug)) throw new Error(`${slug}: not a url-safe slug`)
  if (RESERVED.has(slug)) throw new Error(`${slug}: names a route under /v1/skills`)

  const meta = frontmatter(readFileSync(skillMd, 'utf8'))
  const entries = files(dir).map((path) => {
    const bytes = readFileSync(path)
    const content = bytes.toString('utf8')
    if (Buffer.from(content, 'utf8').compare(bytes) !== 0) throw new Error(`${path}: not UTF-8 text`)
    return {
      path: relative(dir, path),
      size: bytes.length,
      sha256: createHash('sha256').update(bytes).digest('hex'),
      contentType: path.endsWith('.md') ? 'text/markdown' : 'text/plain',
      content,
    }
  })
  const digest = createHash('sha256')
  for (const f of entries) digest.update(`${f.path}\0${f.sha256}\n`)

  skills.push({
    slug,
    displayName: meta.name ?? slug,
    summary: meta.description ?? '',
    version: meta.version ?? '1.0.0',
    sha256hash: digest.digest('hex'),
    files: entries,
  })
}

const out = `/// <reference path="../base_/data/types.d.ts" />

// GENERATED by scripts/catalog.mjs from github.com/hanzoai/bot@${commit}/skills.
// Do not edit; rerun the script.
//
// The catalogue: ${skills.length} skills Hanzo Bot ships, published by the hanzo account.

migrate((app) => {
  const catalog = ${JSON.stringify(skills).replace(/\u2028/g, '\\u2028').replace(/\u2029/g, '\\u2029')}

  const users = app.findCollectionByNameOrId("users")
  const hanzo = new Record(users, {
    handle: "hanzo",
    displayName: "Hanzo",
    name: "Hanzo AI",
    role: "admin",
    trustedPublisher: true,
    image: "https://hanzo.ai/favicon.svg",
  })
  hanzo.setEmail("[email protected]")
  hanzo.setVerified(true)
  hanzo.set("password", $security.randomString(48))
  app.save(hanzo)

  const skills = app.findCollectionByNameOrId("skills")
  const versions = app.findCollectionByNameOrId("skill_versions")
  for (const s of catalog) {
    const skill = new Record(skills, {
      slug: s.slug,
      displayName: s.displayName,
      summary: s.summary,
      ownerUserId: hanzo.id,
      tags: {},
      badges: { official: { byUserId: hanzo.id, at: Date.now() } },
      moderationStatus: "active",
      statsDownloads: 0,
      statsStars: 0,
      statsVersions: 1,
      statsComments: 0,
    })
    app.save(skill)

    const version = new Record(versions, {
      skillId: skill.id,
      version: s.version,
      changelog: "Published from github.com/hanzoai/bot@${commit.slice(0, 12)}.",
      changelogSource: "auto",
      files: s.files,
      parsed: { frontmatter: { name: s.displayName, description: s.summary } },
      createdBy: hanzo.id,
      sha256hash: s.sha256hash,
    })
    app.save(version)

    skill.set("latestVersionId", version.id)
    app.save(skill)
  }
}, (app) => {
  const hanzo = app.findFirstRecordByData("users", "handle", "hanzo")
  for (const skill of app.findRecordsByFilter("skills", "ownerUserId = {:id}", "", 0, 0, { id: hanzo.id })) {
    app.delete(skill)
  }
  app.delete(hanzo)
})
`

const target = new URL('../base/hz_migrations/1709000001_catalog.js', import.meta.url)
writeFileSync(target, out)
console.log(`${skills.length} skills, ${skills.reduce((n, s) => n + s.files.length, 0)} files -> ${target.pathname}`)