Skip to content

peteedoo/project-template / .agents/skills/ai-job-search/jobbank-search

jobbank-search

Verified

Make sure to use this skill whenever the user mentions anything related to job searching on Akademikernes Jobbank, jobbank.dk, or looking for academic or highly educated positions in Denmark — even if they don't mention jobbank.dk explicitly. Also invoke this skill for questions about Danish job listings, graduate trainee positions, Ph.d. jobs, or finding work in specific industries or regions in Denmark. Trigger phrases include: jobbank, akademikernes jobbank, jobs denmark, academic jobs denmark, find job denmark, highly educated jobs, graduate job denmark, trainee position denmark, ph.d. position denmark, postdoc denmark, studiejob, fuldtidsjob, deltidsjob, vikariat, freelance job, praktikplads, job søgning, jobsøgning, søg job, ledige stillinger, nye jobs, it jobs denmark, engineering jobs denmark, marketing jobs denmark, finance jobs denmark, healthcare jobs denmark, remote job denmark, fjernarbejde, job københavn, job aarhus, job odense, nyuddannede job, job til nyuddannede, international job denmark, jobbank søgning, find stilling, data scientist job, software developer job, projektleder stilling, konsulent job, data analyse job.

FileKindSize
SKILL.mdskill md6.3 KB
cli/README.mdmarkdown12.8 KB
cli/package.jsonmanifest597 B
cli/src/cli.tsscript374 B
cli/src/commands/detail.tsscript5.6 KB
cli/src/commands/search.tsscript7.2 KB
cli/src/helpers.tsscript5.1 KB
cli/tests/helpers.tsscript959 B
cli/tsconfig.jsonconfig489 B
url-reference.mdmarkdown10.0 KB

cli/src/helpers.ts

View on GitHub
export const BASE_URL = "https://jobbank.dk"

export const USER_AGENT =
  "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"

export function writeError(error: string, code: string): void {
  process.stderr.write(JSON.stringify({ error, code }) + "\n")
}

export async function fetchWithUA(url: string): Promise<Response> {
  const maxRetries = 6
  let delay = 500
  for (let attempt = 0; attempt <= maxRetries; attempt++) {
    const response = await fetch(url, {
      headers: { "User-Agent": USER_AGENT },
    })
    if (response.status === 429 || response.status >= 500) {
      if (attempt === maxRetries) {
        throw new Error(`Request failed: ${response.status} ${response.statusText}`)
      }
      const jitter = Math.floor(Math.random() * 500)
      await new Promise((resolve) => setTimeout(resolve, delay + jitter))
      delay = Math.min(delay * 2, 5000)
      continue
    }
    return response
  }
  throw new Error("Request failed after max retries")
}

export interface RssItem {
  title: string
  description: string
  link: string
  pubDate: string
}

function extractCdata(xml: string, tag: string): string {
  // Try CDATA first
  const cdataRe = new RegExp(`<${tag}><\\!\\[CDATA\\[(.*?)\\]\\]><\\/${tag}>`, "s")
  const cdataMatch = xml.match(cdataRe)
  if (cdataMatch) return cdataMatch[1].trim()
  // Plain content
  const plainRe = new RegExp(`<${tag}>(.*?)<\\/${tag}>`, "s")
  const plainMatch = xml.match(plainRe)
  return plainMatch ? plainMatch[1].trim() : ""
}

function extractLink(xml: string): string {
  // <link> in RSS can conflict with atom namespace — extract text node after <link>
  // Try CDATA variant first
  const cdataMatch = xml.match(/<link><!\[CDATA\[(.*?)\]\]><\/link>/s)
  if (cdataMatch) return cdataMatch[1].trim()
  // Plain link
  const plainMatch = xml.match(/<link>(.*?)<\/link>/s)
  if (plainMatch) return plainMatch[1].trim()
  // Some RSS feeds put the URL as text after <link> without a closing tag (self-closing style)
  // Try matching href in atom:link
  return ""
}

function parseRssItems(xml: string): RssItem[] {
  const items: RssItem[] = []
  // Split on <item> boundaries
  const itemMatches = xml.matchAll(/<item>([\s\S]*?)<\/item>/g)
  for (const match of itemMatches) {
    const itemXml = match[1]
    const title = extractCdata(itemXml, "title")
    const description = extractCdata(itemXml, "description")
    const link = extractLink(itemXml)
    const pubDate = extractCdata(itemXml, "pubDate") || itemXml.match(/<pubDate>(.*?)<\/pubDate>/)?.[1]?.trim() || ""
    items.push({ title, description, link, pubDate })
  }
  return items
}

export async function rssFetch(params: Record<string, string | string[]>): Promise<RssItem[]> {
  const searchParams = new URLSearchParams()
  for (const [key, value] of Object.entries(params)) {
    if (Array.isArray(value)) {
      for (const v of value) {
        searchParams.append(key, v)
      }
    } else {
      searchParams.append(key, value)
    }
  }
  const url = `${BASE_URL}/job/rss?${searchParams.toString()}`
  const response = await fetchWithUA(url)
  if (!response.ok) {
    throw new Error(`Failed to fetch RSS feed: ${response.status} ${response.statusText}`)
  }
  const xml = await response.text()
  return parseRssItems(xml)
}

export interface ParsedDescription {
  jobType: string
  company: string
  location: string
  deadline: string | null
}

export function parseRssDescription(desc: string): ParsedDescription {
  // Format: "JobType hos Company, Location (Ansøgningsfrist: DD.MM.YYYY)"
  // or: "JobType hos Company, Location (Ansøgningsfrist: løbende)"
  // or multiple types: "Fuldtidsjob, Graduate/trainee hos Company, Location (Ansøgningsfrist: ...)"

  let jobType = ""
  let company = ""
  let location = ""
  let deadline: string | null = null

  const hosIdx = desc.indexOf(" hos ")
  if (hosIdx === -1) {
    // Can't parse — return desc as company
    return { jobType: "", company: desc, location: "", deadline: null }
  }

  jobType = desc.substring(0, hosIdx).trim()
  let rest = desc.substring(hosIdx + 5) // skip " hos "

  // Extract deadline from parenthetical at the end
  const deadlineMatch = rest.match(/\(Ans[øo]gningsfrist:\s*(.*?)\)\s*$/)
  if (deadlineMatch) {
    const deadlineStr = deadlineMatch[1].trim()
    if (deadlineStr.toLowerCase() === "løbende" || deadlineStr.toLowerCase() === "lobende") {
      deadline = null
    } else {
      deadline = deadlineStr
    }
    // Remove the deadline portion from rest
    rest = rest.substring(0, deadlineMatch.index).trim()
  }

  // rest is now "Company, Location"
  // Split on first ", " to get company and location
  const firstComma = rest.indexOf(", ")
  if (firstComma !== -1) {
    company = rest.substring(0, firstComma).trim()
    location = rest.substring(firstComma + 2).trim()
  } else {
    company = rest.trim()
    location = ""
  }

  return { jobType, company, location, deadline }
}

export function extractJobIdFromUrl(url: string): string {
  // URL format: https://jobbank.dk/job/{id}/{company-slug}/{title-slug}
  const match = url.match(/\/job\/(\d+)\//)
  return match ? match[1] : ""
}
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall