feat: add skills

.agents/skills/jobindex-search/cli/README.md

@@ -0,0 +1,247 @@
+# jobindex-cli
+
+CLI for searching jobs on [Jobindex.dk](https://www.jobindex.dk).
+
+**Base URL**: `https://www.jobindex.dk/`
+**Authentication**: None required.
+**Format**: The API returns JSON with embedded HTML blobs. The CLI parses the HTML internally and emits clean JSON.
+
+---
+
+## Installation
+
+```bash
+cd skills/jobindex-search/cli
+bun install
+```
+
+---
+
+## Commands
+
+| Command | Description |
+|---------|-------------|
+| `search` | Search for job listings |
+| `detail` | Fetch full detail for a single job listing |
+
+All commands accept `--format json|table|plain` (default: `json`).
+All errors are written to **stderr** as `{ "error": "...", "code": "..." }` and the process exits with code `1`.
+
+---
+
+## `search` — Search for job listings
+
+**Endpoint**: `GET https://www.jobindex.dk/jobsoegning.json`
+
+```bash
+bun run src/cli.ts search [flags]
+```
+
+The API always returns 20 results per page (fixed — no `--per-page` flag). The CLI parses the `result_list_box_html` HTML blob from the response to extract structured job records.
+
+### Flags
+
+| Flag | Type | Default | Description |
+|------|------|---------|-------------|
+| `--query` / `-q` | string | — | Keyword search query (e.g. `python`, `grafisk designer`) |
+| `--page` | number | `1` | Page number (1-indexed) |
+| `--jobage` | number | `9999` | Max age of posting in days: `1`, `7`, `14`, `30`, or `9999` (all) |
+| `--sort` | string | `score` | Sort order: `score` (relevance) or `date` (newest first) |
+| `--limit` | number | — | Cap total results returned by the CLI (client-side) |
+| `--format` | string | `json` | Output format: `json`, `table`, `plain` |
+
+### Sort options
+
+| Value | Description |
+|-------|-------------|
+| `score` | Relevance / best match (default) |
+| `date` | Newest postings first |
+
+### jobage options
+
+| Value | Description |
+|-------|-------------|
+| `1` | Posted today |
+| `7` | Last 7 days |
+| `14` | Last 14 days |
+| `30` | Last 30 days |
+| `9999` | All time (default) |
+
+### Example
+
+```bash
+# Search for Python jobs posted in the last 7 days, sorted by date
+bun run src/cli.ts search --query python --jobage 7 --sort date
+
+# Search for "grafisk designer" jobs — show first 5 results
+bun run src/cli.ts search --query "grafisk designer" --limit 5
+
+# Page 2 of results for data engineer
+bun run src/cli.ts search --query "data engineer" --page 2 --format table
+```
+
+### Response shape
+
+```json
+{
+  "meta": {
+    "total": 237,
+    "page": 1,
+    "perPage": 20
+  },
+  "results": [
+    {
+      "id": "h1647303",
+      "title": "Data Engineer til opbygning af Gavefabrikkens dataplatform",
+      "company": "Gavefabrikken",
+      "companyUrl": "https://www.gavefabrikken.dk/",
+      "location": "Valby",
+      "date": "2026-03-12",
+      "url": "https://www.jobindex.dk/jobannonce/h1647303/data-engineer-til-opbygning-af-gavefabrikkens-dataplatform",
+      "description": "Vi søger en dygtig Data Engineer til at opbygge og vedligeholde vores dataplatform..."
+    }
+  ]
+}
+```
+
+**Field notes:**
+- `id` — string ID prefixed with `h` (e.g. `h1647303`). Use this with the `detail` command.
+- `company` — company name; may be `null` for some aggregated listings.
+- `companyUrl` — company homepage URL; may be `null` if not present.
+- `location` — city or area; may be `null` if not listed.
+- `date` — ISO date string (`YYYY-MM-DD`) from the `datetime` attribute on the `<time>` element; may be `null`.
+- `description` — short excerpt from the listing; may be `null` or empty.
+- `url` — full Jobindex.dk URL for the listing.
+- `total` in `meta` — parsed from `hitcount_html` (Danish thousands separator `.` is stripped before parsing, e.g. `18.903` → `18903`).
+
+> **Note on area filtering**: The Jobindex API does not reliably support area/region filtering via query parameters. `area` and `geoareaid` params are silently ignored. To filter by location, use `--query` with a city name (e.g. `--query "python aarhus"`) or apply `--limit` and filter the JSON output externally.
+
+---
+
+## `detail` — Fetch full job listing detail
+
+**URL**: `https://www.jobindex.dk/jobannonce/{id}/{slug}`
+
+```bash
+bun run src/cli.ts detail <id> [--format json|plain]
+```
+
+The `id` is the job ID from `search` results (e.g. `h1647303`). The slug is optional — the CLI fetches the canonical URL by first constructing `https://www.jobindex.dk/jobannonce/{id}` and following any redirect, or by using the full URL from the `url` field in `search` results.
+
+You may also pass the full URL directly as the `id` argument.
+
+### Flags
+
+| Flag | Type | Default | Description |
+|------|------|---------|-------------|
+| `--format` | string | `json` | Output format: `json`, `plain` |
+
+### Example
+
+```bash
+# Using ID from search results
+bun run src/cli.ts detail h1647303
+
+# Using full URL
+bun run src/cli.ts detail "https://www.jobindex.dk/jobannonce/h1647303/data-engineer-til-opbygning-af-gavefabrikkens-dataplatform"
+
+# Plain text output
+bun run src/cli.ts detail h1647303 --format plain
+```
+
+### Response shape
+
+```json
+{
+  "id": "h1647303",
+  "title": "Data Engineer til opbygning af Gavefabrikkens dataplatform",
+  "company": "Gavefabrikken",
+  "companyUrl": "https://www.gavefabrikken.dk/",
+  "location": "Valby, København",
+  "date": "2026-03-12",
+  "deadline": "2026-04-01",
+  "employmentType": "Fastansættelse",
+  "hours": "Fuldtid",
+  "applyUrl": "https://www.gavefabrikken.dk/jobs/apply/123",
+  "url": "https://www.jobindex.dk/jobannonce/h1647303/data-engineer-til-opbygning-af-gavefabrikkens-dataplatform",
+  "description": "Full job description text here..."
+}
+```
+
+**Field notes:**
+
+Jobindex serves detail pages in two shapes, and field availability differs:
+a **jobindex-native** page (recognisable by its `jd-*` facts blocks) carries
+company, location, an ISO deadline, employment type and hours; an **external
+ATS passthrough** (the employer's hosted ad, e.g. hr-manager/Talentech, served
+through jobindex) has no reliable company anchor, so `company` is `null` there
+rather than the ATS brand, and location/deadline come from the ad's own
+widgets when present.
+
+- `id` / `url` — always the jobindex id and its `jobannonce` URL, never the
+  page's `og:url`/canonical (on passthrough pages those point at the external
+  ATS, not the posting).
+- `deadline` — `YYYY-MM-DD` or `null`; Danish long dates ("13. september
+  2026") and `DD-MM-YYYY` widget dates are converted.
+- `employmentType` / `hours` — from the native facts blocks; `null` on
+  passthrough pages.
+- `companyUrl` — currently always `null`; no page shape carries a usable
+  company link.
+- `applyUrl` — the Jobindex redirect link (`/c?t=...`) when present; `null`
+  otherwise.
+- `description` — plain text of the ad body (HTML stripped), falling back to
+  the page's meta description when the body is empty.
+- All fields except `id`, `title`, and `url` may be `null`.
+
+---
+
+## Error handling
+
+All errors are written to **stderr** in JSON format and exit with code `1`:
+
+```json
+{ "error": "Job not found", "code": "NOT_FOUND" }
+{ "error": "API request failed: 500 Internal Server Error", "code": "API_ERROR" }
+{ "error": "Failed to parse job listing HTML", "code": "PARSE_ERROR" }
+{ "error": "--query is required", "code": "MISSING_REQUIRED" }
+```
+
+---
+
+## URL construction
+
+Job detail pages on jobindex.dk:
+- `https://www.jobindex.dk/jobannonce/{id}/{slug}`
+
+The slug is part of the `url` returned by `search`. When calling `detail` with just an ID, the CLI fetches `https://www.jobindex.dk/jobannonce/{id}` which redirects to the full URL.
+
+---
+
+## Parsing notes
+
+### Total count from `hitcount_html`
+
+The API returns pagination info as an HTML string like:
+
+```html
+<div class="jix_pagination_total"><strong>1</strong> til <strong>20</strong> af <strong>18.903</strong> resultater.</div>
+```
+
+Parse total with: `/af <strong>([\d.]+)<\/strong>/` and strip `.` before converting to integer.
+
+### Job card selectors
+
+Each job card is wrapped in `[data-beacon-tid]`. Inside, select:
+
+| Field | Selector |
+|-------|----------|
+| `id` | `[data-beacon-tid]` attribute value |
+| `title` | `h4 > a` text content |
+| `url` | `h4 > a[href]` |
+| `company` | `.jix-toolbar-top__company a` text |
+| `companyUrl` | `.jix-toolbar-top__company a[href]` |
+| `location` | `span.jix_robotjob--area` text |
+| `date` | `time[datetime]` attribute value |
+| `description` | `p` text content (first `<p>` in card) |
+
+Two card types exist: `div.PaidJob` (sponsored) and `div.jix_robotjob` (aggregated). Both use the same selector pattern.

.agents/skills/jobindex-search/cli/package.json

@@ -0,0 +1,25 @@
+{
+  "name": "jobindex-cli",
+  "version": "1.0.0",
+  "description": "CLI for searching jobs on Jobindex.dk",
+  "type": "module",
+  "main": "src/cli.ts",
+  "bin": {
+    "jobindex": "src/cli.ts"
+  },
+  "scripts": {
+    "start": "bun run src/cli.ts",
+    "test": "bun test --timeout 30000",
+    "typecheck": "tsc --noEmit"
+  },
+  "dependencies": {
+    "@bunli/core": "0.9.1",
+    "@bunli/utils": "0.6.0",
+    "node-html-parser": "^6.1.13",
+    "zod": "^3.23.0"
+  },
+  "devDependencies": {
+    "typescript": "^5.4.0",
+    "@types/bun": "1.3.14"
+  }
+}

.agents/skills/jobindex-search/cli/src/cli.ts

@@ -0,0 +1,45 @@
+import { createCLI } from "@bunli/core"
+import { writeError } from "./helpers.js"
+import { search } from "./commands/search.js"
+import { detail } from "./commands/detail.js"
+
+const cli = await createCLI({
+  name: "jobindex-cli",
+  version: "0.1.0",
+  description: "CLI for searching jobs on Jobindex.dk",
+})
+
+const commands = [search, detail]
+for (const command of commands) {
+  cli.command(command)
+}
+
+// Reject unknown --flags before dispatch. bunli silently discards them, and a
+// silently discarded filter changes what the search returns without any error
+// (a wrong flag name once returned an entire portal's database as if it
+// matched the query). add-portal.md's contract requires a bogus flag to exit 1
+// with a JSON error on stderr; this enforces it for the reference CLIs too.
+const argv = process.argv.slice(2)
+const invoked = commands.find((c) => (c as { name?: string }).name === argv[0])
+if (invoked) {
+  const known = new Set([
+    ...Object.keys((invoked as { options?: Record<string, unknown> }).options ?? {}),
+    "help",
+    "version",
+  ])
+  for (const token of argv.slice(1)) {
+    if (token === "--") break
+    if (token.startsWith("--")) {
+      const flag = token.slice(2).split("=")[0]
+      if (!known.has(flag)) {
+        writeError(
+          `unknown flag --${flag} for '${argv[0]}' - flags are never silently ignored, because a discarded filter changes what the search returns; see --help for the supported flags`,
+          "UNKNOWN_FLAG",
+        )
+        process.exit(1)
+      }
+    }
+  }
+}
+
+await cli.run()

.agents/skills/jobindex-search/cli/src/commands/detail.ts

@@ -0,0 +1,321 @@
+import { defineCommand, option } from "@bunli/core"
+import { z } from "zod"
+import { htmlFetch, writeError } from "../helpers.js"
+
+const BASE_URL = "https://www.jobindex.dk"
+
+interface DetailResult {
+  id: string
+  title: string
+  company: string | null
+  companyUrl: string | null
+  location: string | null
+  date: string | null
+  deadline: string | null
+  employmentType: string | null
+  hours: string | null
+  applyUrl: string | null
+  url: string
+  description: string | null
+}
+
+/**
+ * Convert a Unicode code point to a string. Uses `fromCodePoint` (not
+ * `fromCharCode`) so supplementary-plane code points (e.g. emoji, U+1F600)
+ * decode correctly, and drops out-of-range values instead of throwing.
+ */
+function numericEntity(cp: number): string {
+  return cp >= 0 && cp <= 0x10ffff ? String.fromCodePoint(cp) : ""
+}
+
+/**
+ * Decode HTML entities in text
+ */
+function decodeHtmlEntities(text: string): string {
+  return text
+    .replace(/&amp;/g, "&")
+    .replace(/&lt;/g, "<")
+    .replace(/&gt;/g, ">")
+    .replace(/&quot;/g, '"')
+    .replace(/&#39;/g, "'")
+    .replace(/&apos;/g, "'")
+    // Danish letters appear as named entities in employer-hosted ad markup.
+    .replace(/&oslash;/g, "ø")
+    .replace(/&Oslash;/g, "Ø")
+    .replace(/&aelig;/g, "æ")
+    .replace(/&AElig;/g, "Æ")
+    .replace(/&aring;/g, "å")
+    .replace(/&Aring;/g, "Å")
+    // Numeric character references: decimal (&#233;) and hexadecimal (&#xE9;).
+    .replace(/&#(\d+);/g, (_, dec) => numericEntity(parseInt(dec, 10)))
+    .replace(/&#[xX]([0-9a-fA-F]+);/g, (_, hex) => numericEntity(parseInt(hex, 16)))
+    .replace(/&nbsp;/g, " ")
+}
+
+/**
+ * Strip HTML tags from text
+ */
+function stripTags(html: string): string {
+  return html.replace(/<[^>]+>/g, "").trim()
+}
+
+/**
+ * Extract job ID from URL or return as-is if already an ID
+ */
+function extractIdFromUrl(url: string): string {
+  // Match IDs like h1647303, r13677312, etc.
+  const match = url.match(/\/jobannonce\/([a-zA-Z]\d+)/)
+  if (match) return match[1]
+  return url
+}
+
+function buildUrl(idOrUrl: string): { url: string; id: string } {
+  if (idOrUrl.startsWith("http")) {
+    const id = extractIdFromUrl(idOrUrl)
+    return { url: idOrUrl, id }
+  }
+  // It's a bare ID
+  const url = `${BASE_URL}/jobannonce/${idOrUrl}`
+  return { url, id: idOrUrl }
+}
+
+const DANISH_MONTHS: Record<string, string> = {
+  januar: "01", februar: "02", marts: "03", april: "04", maj: "05", juni: "06",
+  juli: "07", august: "08", september: "09", oktober: "10", november: "11", december: "12",
+}
+
+/**
+ * Normalize a date found on a detail page to YYYY-MM-DD, or null.
+ * Live pages carry three shapes: ISO, DD-MM-YYYY (the hr-manager widget),
+ * and Danish long form ("13. september 2026", the jobindex-native facts box).
+ */
+export function toIsoDate(value: string | null | undefined): string | null {
+  if (!value) return null
+  const text = value.trim()
+  let m = text.match(/^(\d{4})-(\d{2})-(\d{2})/)
+  if (m) return `${m[1]}-${m[2]}-${m[3]}`
+  m = text.match(/^(\d{2})-(\d{2})-(\d{4})/)
+  if (m) return `${m[3]}-${m[2]}-${m[1]}`
+  m = text.match(/^(\d{1,2})\.?\s+([a-zæøå]+)\s+(\d{4})/i)
+  if (m) {
+    const month = DANISH_MONTHS[m[2].toLowerCase()]
+    if (month) return `${m[3]}-${month}-${m[1].padStart(2, "0")}`
+  }
+  return null
+}
+
+function metaContent(html: string, matcher: string): string | null {
+  const re = new RegExp(
+    `<meta[^>]+(?:property|name|itemprop)="${matcher}"[^>]+content="([^"]*)"|<meta[^>]+content="([^"]*)"[^>]+(?:property|name|itemprop)="${matcher}"`,
+    "i",
+  )
+  const m = html.match(re)
+  const value = m ? (m[1] ?? m[2]) : null
+  return value ? decodeHtmlEntities(value).trim() || null : null
+}
+
+/** The text of the <p> inside a jobindex-native jd-* facts block. */
+function jdBlockValue(html: string, cls: string): string | null {
+  const m = html.match(new RegExp(`class="${cls}"[^>]*>[\\s\\S]*?<p[^>]*>([\\s\\S]*?)</p>`, "i"))
+  return m ? decodeHtmlEntities(stripTags(m[1])).replace(/\s+/g, " ").trim() || null : null
+}
+
+/** Drop head/script/style content so text scans never read CSS or JS. */
+function visibleHtml(html: string): string {
+  return html
+    .replace(/<head[\s\S]*?<\/head>/gi, "")
+    .replace(/<script[\s\S]*?<\/script>/gi, "")
+    .replace(/<style[\s\S]*?<\/style>/gi, "")
+    .replace(/<!--[\s\S]*?-->/g, "")
+}
+
+function bodyText(html: string): string | null {
+  const text = decodeHtmlEntities(stripTags(visibleHtml(html).replace(/<(br|\/p|\/div|\/li|\/h[1-6])[^>]*>/gi, "\n")))
+    .split("\n")
+    .map((line) => line.replace(/\s+/g, " ").trim())
+    .filter(Boolean)
+    .join("\n")
+  return text || null
+}
+
+/**
+ * Parse a live detail page. Jobindex serves two shapes (verified live
+ * 2026-08-19; the selectors the previous parser used exist in neither):
+ *
+ * - the jobindex-native shape, recognisable by its `jd-*` facts blocks
+ *   (jd-deadline, jd-location, ...), with the company as the `<title>`
+ *   prefix ("COMPANY - Job title");
+ * - an external ATS passthrough (hr-manager/Talentech and similar), where
+ *   the page IS the employer's hosted ad: `og:url` points at the ATS,
+ *   `og:site_name` is the ATS brand, and there is no reliable company
+ *   anchor at all - so `company` is honestly null there, never the ATS.
+ *
+ * `id` and `url` are always the caller's jobindex id and its jobannonce
+ * URL: the canonical/og:url on these pages is the external ATS, and
+ * storing that broke /scrape's "store a URL that resolves to the posting".
+ */
+export function parseDetailPage(html: string, url: string, id: string): DetailResult {
+  const isNative = html.includes('class="jd-')
+
+  const ogTitle = metaContent(html, "og:title")
+  const itempropName = metaContent(html, "name")
+  const h1 = html.match(/<h1[^>]*>([\s\S]*?)<\/h1>/i)
+  const h1Title = h1 ? decodeHtmlEntities(stripTags(h1[1])).replace(/\s+/g, " ").trim() : null
+  const title = ogTitle ?? itempropName ?? h1Title ?? ""
+  if (!title) {
+    throw new Error("Failed to parse job listing HTML")
+  }
+
+  // Company: only the native shape carries one - as the <title> prefix,
+  // "VELLIV - Udvikler til Camunda/AWS". Require the suffix to be the job
+  // title so an unrelated <title> never becomes a company name.
+  let company: string | null = null
+  if (isNative) {
+    const titleTag = html.match(/<title>([\s\S]*?)<\/title>/i)
+    const pageTitle = titleTag ? decodeHtmlEntities(titleTag[1]).replace(/\s+/g, " ").trim() : ""
+    if (pageTitle.endsWith(` - ${title}`)) {
+      company = pageTitle.slice(0, -(title.length + 3)).trim() || null
+    }
+  }
+
+  let location: string | null = null
+  let deadline: string | null = null
+  let employmentType: string | null = null
+  let hours: string | null = null
+  let description: string | null = null
+
+  if (isNative) {
+    location = jdBlockValue(html, "jd-location")
+    deadline = toIsoDate(jdBlockValue(html, "jd-deadline"))
+    employmentType = jdBlockValue(html, "jd-type")
+    hours = jdBlockValue(html, "jd-workhours")
+    const desc = html.match(/class="jd-description"[^>]*>([\s\S]*?)<\/div>/i)
+    description = desc
+      ? decodeHtmlEntities(stripTags(desc[1])).replace(/\s+/g, " ").trim() || null
+      : null
+  } else {
+    // hr-manager-style widget: a rowheader label followed by the value span.
+    const workplace = visibleHtml(html).match(
+      /class="workplace[^"]*"[\s\S]*?<span class="empty">([\s\S]*?)<\/span>/i,
+    )
+    location = workplace
+      ? decodeHtmlEntities(stripTags(workplace[1])).replace(/\s+/g, " ").trim() || null
+      : null
+
+    // Deadline: label + a real date within range, scanned only over visible
+    // markup - the label also appears inside a CSS comment on these pages,
+    // which the previous parser captured verbatim as the deadline.
+    const due = visibleHtml(html).match(
+      /(?:Ansøgningsfrist|Application\s*due|Frist)[\s\S]{0,300}?(\d{2}-\d{2}-\d{4}|\d{4}-\d{2}-\d{2}|\d{1,2}\.?\s+[a-zæøå]+\s+\d{4})/i,
+    )
+    deadline = due ? toIsoDate(due[1]) : null
+
+    description = bodyText(html)
+    if (!description || description.length < 100) {
+      description = metaContent(html, "og:description") ?? metaContent(html, "description") ?? description
+    }
+  }
+
+  if (!description) {
+    description = metaContent(html, "og:description")
+  }
+
+  // Apply URL: jobindex's own /c?t= redirect when present.
+  let applyUrl: string | null = null
+  const ctMatch = html.match(/href="(\/c\?t=[^"]+)"/)
+  if (ctMatch) {
+    applyUrl = `${BASE_URL}${decodeHtmlEntities(ctMatch[1])}`
+  }
+
+  const timeMatch = html.match(/<time[^>]+datetime="([^"]+)"/)
+
+  return {
+    id,
+    title,
+    company,
+    companyUrl: null,
+    location,
+    date: timeMatch ? toIsoDate(timeMatch[1]) : null,
+    deadline,
+    employmentType,
+    hours,
+    applyUrl,
+    url,
+    description,
+  }
+}
+
+export const detail = defineCommand({
+  name: "detail",
+  description: "Fetch full job listing detail by ID or URL",
+  options: {
+    format: option(z.enum(["json", "plain"]).default("json"), {
+      description: "Output format: json, plain",
+    }),
+  },
+  handler: async ({ positional, flags, signal }) => {
+    if (signal.aborted) return
+
+    const idArg = positional[0]
+    if (!idArg) {
+      writeError("Job ID or URL is required", "MISSING_REQUIRED")
+      process.exit(1)
+    }
+
+    const { url, id } = buildUrl(idArg)
+
+    try {
+      const html = await htmlFetch(url)
+
+      if (signal.aborted) return
+
+      let data: DetailResult
+      try {
+        data = parseDetailPage(html, url, id)
+      } catch (parseErr) {
+        const msg = parseErr instanceof Error ? parseErr.message : String(parseErr)
+        writeError(msg, "PARSE_ERROR")
+        process.exit(1)
+      }
+
+      // Verify it's a valid job page (has a title)
+      if (!data.title) {
+        writeError("Failed to parse job listing HTML", "PARSE_ERROR")
+        process.exit(1)
+      }
+
+      if (flags.format === "json") {
+        console.log(JSON.stringify(data, null, 2))
+      } else {
+        outputPlain(data)
+      }
+    } catch (err) {
+      const message = err instanceof Error ? err.message : String(err)
+      if (message.includes("Job not found") || message.includes("404") || message.includes("NOT_FOUND")) {
+        writeError("Job not found", "NOT_FOUND")
+      } else if (message.includes("Failed to parse") || message.includes("PARSE_ERROR")) {
+        writeError(message, "PARSE_ERROR")
+      } else {
+        writeError(message, "API_ERROR")
+      }
+      process.exit(1)
+    }
+  },
+})
+
+function outputPlain(data: DetailResult): void {
+  console.log(`id: ${data.id}`)
+  console.log(`title: ${data.title}`)
+  console.log(`company: ${data.company ?? "-"}`)
+  console.log(`location: ${data.location ?? "-"}`)
+  console.log(`date: ${data.date ?? "-"}`)
+  console.log(`deadline: ${data.deadline ?? "-"}`)
+  console.log(`employmentType: ${data.employmentType ?? "-"}`)
+  console.log(`hours: ${data.hours ?? "-"}`)
+  console.log(`applyUrl: ${data.applyUrl ?? "-"}`)
+  console.log(`url: ${data.url}`)
+  console.log("")
+  if (data.description) {
+    console.log(data.description)
+  }
+}

.agents/skills/jobindex-search/cli/src/commands/search.ts

@@ -0,0 +1,103 @@
+import { defineCommand, option } from "@bunli/core"
+import { z } from "zod"
+import { BASE_URL, htmlFetch, parseSearchPage, writeError, type JobCard } from "../helpers.js"
+
+export const search = defineCommand({
+  name: "search",
+  description: "Search for job listings on Jobindex.dk",
+  options: {
+    query: option(z.string().optional(), {
+      short: "q",
+      description: "Keyword search query (e.g. python, grafisk designer)",
+    }),
+    page: option(z.coerce.number().int().min(1).default(1), {
+      description: "Page number (1-indexed)",
+    }),
+    jobage: option(z.coerce.number().int().min(1).default(9999), {
+      description: "Max age of posting in days: 1, 7, 14, 30, or 9999 (all)",
+    }),
+    sort: option(z.string().default("score"), {
+      description: "Sort order: score (relevance) or date (newest first)",
+    }),
+    limit: option(z.coerce.number().int().min(1).optional(), {
+      description: "Cap total results returned by the CLI (client-side)",
+    }),
+    format: option(z.enum(["json", "table", "plain"]).default("json"), {
+      description: "Output format: json, table, plain",
+    }),
+  },
+  handler: async ({ flags, signal }) => {
+    if (!flags.query) {
+      writeError("--query is required", "MISSING_REQUIRED")
+      process.exit(1)
+    }
+
+    if (signal.aborted) return
+
+    const params = new URLSearchParams({
+      q: flags.query,
+      page: String(flags.page),
+      jobage: String(flags.jobage),
+      sort: flags.sort,
+    })
+
+    try {
+      const html = await htmlFetch(`${BASE_URL}/jobsoegning?${params.toString()}`)
+
+      if (signal.aborted) return
+
+      const parsed = parseSearchPage(html)
+      const total = parsed.total
+      let results = parsed.results
+
+      if (flags.limit !== undefined) {
+        results = results.slice(0, flags.limit)
+      }
+
+      const output = {
+        meta: {
+          total,
+          page: flags.page,
+          perPage: 20,
+        },
+        results,
+      }
+
+      if (flags.format === "json") {
+        console.log(JSON.stringify(output, null, 2))
+      } else if (flags.format === "table") {
+        outputTable(results)
+      } else {
+        outputPlain(results)
+      }
+    } catch (err) {
+      writeError(err instanceof Error ? err.message : String(err), "API_ERROR")
+      process.exit(1)
+    }
+  },
+})
+
+function outputTable(results: JobCard[]): void {
+  console.log("id          title                                    company              location")
+  for (const r of results) {
+    const id = r.id.padEnd(11)
+    const title = r.title.substring(0, 40).padEnd(40)
+    const company = (r.company ?? "-").substring(0, 20).padEnd(20)
+    const location = r.location ?? "-"
+    console.log(`${id} ${title} ${company} ${location}`)
+  }
+}
+
+function outputPlain(results: JobCard[]): void {
+  for (const r of results) {
+    console.log(`id: ${r.id}`)
+    console.log(`title: ${r.title}`)
+    console.log(`company: ${r.company ?? "-"}`)
+    console.log(`location: ${r.location ?? "-"}`)
+    console.log(`date: ${r.date ?? "-"}`)
+    console.log(`deadline: ${r.deadline ?? "-"}`)
+    console.log(`url: ${r.url}`)
+    if (r.description) console.log(`description: ${r.description}`)
+    console.log("")
+  }
+}

.agents/skills/jobindex-search/cli/src/helpers.ts

@@ -0,0 +1,346 @@
+export const BASE_URL = "https://www.jobindex.dk"
+
+export function writeError(error: string, code: string): void {
+  process.stderr.write(JSON.stringify({ error, code }) + "\n")
+}
+
+export async function apiFetch<T>(path: string, params?: Record<string, string>): Promise<T> {
+  let url = `${BASE_URL}${path}`
+  if (params && Object.keys(params).length > 0) {
+    const qs = new URLSearchParams(params)
+    url += `?${qs.toString()}`
+  }
+
+  const maxRetries = 6
+  let delay = 500
+  for (let attempt = 0; attempt <= maxRetries; attempt++) {
+    const response = await fetch(url, { signal: AbortSignal.timeout(15000) })
+    if (response.status === 429 || response.status >= 500) {
+      if (attempt === maxRetries) {
+        throw new Error(`API 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
+    }
+    if (!response.ok) {
+      throw new Error(`API request failed: ${response.status} ${response.statusText}`)
+    }
+    return response.json() as Promise<T>
+  }
+  throw new Error("API request failed after max retries")
+}
+
+export async function htmlFetch(url: string): Promise<string> {
+  const maxRetries = 6
+  let delay = 500
+  for (let attempt = 0; attempt <= maxRetries; attempt++) {
+    const response = await fetch(url, {
+      headers: {
+        "User-Agent": "Mozilla/5.0 (compatible; jobindex-cli/1.0)",
+        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
+        "Accept-Language": "da,en;q=0.9",
+      },
+      redirect: "follow",
+      signal: AbortSignal.timeout(15000),
+    })
+    if (response.status === 429 || response.status >= 500) {
+      if (attempt === maxRetries) {
+        throw new Error(`API 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
+    }
+    if (response.status === 404) {
+      throw new Error(`Job not found`)
+    }
+    if (!response.ok) {
+      throw new Error(`API request failed: ${response.status} ${response.statusText}`)
+    }
+    return response.text()
+  }
+  throw new Error("Request failed after max retries")
+}
+
+export interface JobCard {
+  id: string
+  title: string
+  company: string | null
+  companyUrl: string | null
+  location: string | null
+  date: string | null
+  deadline: string | null
+  url: string
+  description: string | null
+}
+
+/**
+ * Jobindex moved its search results client-side. The /jobsoegning.json endpoint
+ * now returns 204 No Content. The HTML page (/jobsoegning) embeds the full result
+ * payload in a `var Stash = {...}` script blob, under
+ * jobsearch/result_app -> storeData -> searchResponse -> { hitcount, results[] }.
+ * This extracts and parses that blob.
+ */
+export function extractStash(html: string): any {
+  const marker = "var Stash = "
+  const start = html.indexOf(marker)
+  if (start === -1) throw new Error("Could not locate Stash blob in jobindex HTML")
+  const open = start + marker.length
+  let depth = 0
+  let inStr = false
+  let esc = false
+  let end = -1
+  for (let j = open; j < html.length; j++) {
+    const c = html[j]
+    if (inStr) {
+      if (esc) esc = false
+      else if (c === "\\") esc = true
+      else if (c === '"') inStr = false
+    } else {
+      if (c === '"') inStr = true
+      else if (c === "{") depth++
+      else if (c === "}") {
+        depth--
+        if (depth === 0) {
+          end = j + 1
+          break
+        }
+      }
+    }
+  }
+  if (end === -1) throw new Error("Unterminated Stash blob in jobindex HTML")
+  return JSON.parse(html.slice(open, end))
+}
+
+function findSearchResponse(node: any): any {
+  if (node && typeof node === "object") {
+    if (!Array.isArray(node)) {
+      if (
+        node.searchResponse &&
+        typeof node.searchResponse === "object" &&
+        Array.isArray(node.searchResponse.results)
+      ) {
+        return node.searchResponse
+      }
+      for (const key of Object.keys(node)) {
+        const found = findSearchResponse(node[key])
+        if (found) return found
+      }
+    } else {
+      for (const item of node) {
+        const found = findSearchResponse(item)
+        if (found) return found
+      }
+    }
+  }
+  return null
+}
+
+export interface SearchPageResult {
+  total: number
+  results: JobCard[]
+}
+
+export function parseSearchPage(html: string): SearchPageResult {
+  const stash = extractStash(html)
+  const sr = findSearchResponse(stash)
+  if (!sr) throw new Error("Could not locate searchResponse in jobindex Stash")
+
+  const results: JobCard[] = (sr.results ?? []).map((r: any): JobCard => {
+    const tid: string = r.tid ?? ""
+    let location: string | null = r.area ?? null
+    if (!location) {
+      try {
+        location = r.geojson?.features?.[0]?.properties?.title ?? null
+      } catch {
+        location = null
+      }
+    }
+    let deadline: string | null = null
+    // apply_deadline_asap means the posting states no fixed deadline ("apply
+    // now"). The /scrape contract represents that as null, and consumers do
+    // date arithmetic on this field - so the flag maps to null, and wins over
+    // any date field that happens to be present.
+    if (r.apply_deadline_asap) deadline = null
+    else if (typeof r.apply_deadline === "string") deadline = r.apply_deadline.slice(0, 10)
+    else if (typeof r.lastdate === "string") deadline = r.lastdate
+
+    return {
+      id: tid,
+      title: r.headline ?? "",
+      company: r.company?.name ?? r.companytext ?? null,
+      companyUrl: r.company?.homeurl ?? null,
+      location,
+      date: r.firstdate ?? null,
+      deadline,
+      url: tid ? `${BASE_URL}/jobannonce/${tid}` : (r.share_url ?? r.url ?? ""),
+      description: null,
+    }
+  })
+
+  const total = typeof sr.hitcount === "number" ? sr.hitcount : results.length
+  return { total, results }
+}
+
+/**
+ * Convert a Unicode code point to a string. Uses `fromCodePoint` (not
+ * `fromCharCode`) so supplementary-plane code points (e.g. emoji, U+1F600)
+ * decode correctly, and drops out-of-range values instead of throwing.
+ */
+function numericEntity(cp: number): string {
+  return cp >= 0 && cp <= 0x10ffff ? String.fromCodePoint(cp) : ""
+}
+
+/**
+ * Decode HTML entities in text
+ */
+function decodeHtmlEntities(text: string): string {
+  return text
+    .replace(/&amp;/g, "&")
+    .replace(/&lt;/g, "<")
+    .replace(/&gt;/g, ">")
+    .replace(/&quot;/g, '"')
+    .replace(/&#39;/g, "'")
+    .replace(/&apos;/g, "'")
+    // Numeric character references: decimal (&#233;) and hexadecimal (&#xE9;).
+    .replace(/&#(\d+);/g, (_, dec) => numericEntity(parseInt(dec, 10)))
+    .replace(/&#[xX]([0-9a-fA-F]+);/g, (_, hex) => numericEntity(parseInt(hex, 16)))
+    .replace(/&nbsp;/g, " ")
+}
+
+/**
+ * Strip HTML tags from text
+ */
+function stripTags(html: string): string {
+  return html.replace(/<[^>]+>/g, "").trim()
+}
+
+/**
+ * Parse job cards from result_list_box_html using regex.
+ * node-html-parser has nesting bugs with this specific HTML structure
+ * (unclosed tags inside buttons cause incorrect DOM tree).
+ * Regex parsing is more reliable for this specific HTML format.
+ */
+export function parseJobCards(html: string): JobCard[] {
+  const results: JobCard[] = []
+
+  // Split HTML by jobad-wrapper to get individual card HTML chunks
+  const wrapperPattern = /<div[^>]+id="jobad-wrapper-(h\d+|r\d+)"[^>]*>([\s\S]*?)(?=<div[^>]+id="jobad-wrapper-|$)/g
+
+  let match: RegExpExecArray | null
+  while ((match = wrapperPattern.exec(html)) !== null) {
+    const id = match[1]
+    const cardHtml = match[2]
+
+    // Extract title: look for <h4>...<a|A href="...">Title</a>...</h4>
+    const titleMatch = cardHtml.match(/<h4[^>]*>[\s\S]*?<[Aa][^>]+href="([^"]+)"[^>]*>([\s\S]*?)<\/[Aa]>/i)
+    if (!titleMatch) continue
+    const rawTitle = stripTags(titleMatch[2])
+    const title = decodeHtmlEntities(rawTitle)
+    if (!title) continue
+
+    // Determine URL: prefer jobindex.dk /jobannonce/ URL, fallback to constructed URL
+    let url: string
+    const jobannonce = cardHtml.match(/href="(https:\/\/www\.jobindex\.dk\/jobannonce\/[^"]+)"/)
+    if (jobannonce) {
+      url = jobannonce[1]
+    } else {
+      // Construct canonical URL from ID
+      url = `${BASE_URL}/jobannonce/${id}`
+    }
+
+    // Extract company: <a ...> inside jix-toolbar-top__company
+    let company: string | null = null
+    let companyUrl: string | null = null
+    const companySection = cardHtml.match(/class="jix-toolbar-top__company"[^>]*>([\s\S]*?)<\/div>/i)
+    if (companySection) {
+      const companyLinkMatch = companySection[1].match(/<[Aa][^>]+href="([^"]+)"[^>]*>([\s\S]*?)<\/[Aa]>/i)
+      if (companyLinkMatch) {
+        company = decodeHtmlEntities(stripTags(companyLinkMatch[2])) || null
+        companyUrl = companyLinkMatch[1] || null
+      }
+    }
+
+    // Extract location: <span class="jix_robotjob--area">Location</span>
+    const locMatch = cardHtml.match(/<span[^>]+class="jix_robotjob--area"[^>]*>([\s\S]*?)<\/span>/i)
+    const location = locMatch ? decodeHtmlEntities(stripTags(locMatch[1])) || null : null
+
+    // Extract date: <time datetime="YYYY-MM-DD">
+    const dateMatch = cardHtml.match(/<time[^>]+datetime="([^"]+)"/)
+    const date = dateMatch ? dateMatch[1] : null
+
+    // Extract description: first <p class="..."> or first standalone <p> (not in toolbar)
+    // Skip the toolbar/menu section and look for the description paragraph
+    let description: string | null = null
+    const innerSection = cardHtml.match(/class="PaidJob-inner"[^>]*>([\s\S]*?)(?:<\/div>\s*<\/div>|$)/i) ||
+                         cardHtml.match(/class="jix_robotjob-inner"[^>]*>([\s\S]*?)(?:<\/div>\s*<\/div>|$)/i)
+    if (innerSection) {
+      const pMatch = innerSection[1].match(/<p[^>]*>([\s\S]*?)<\/p>/i)
+      if (pMatch) {
+        const text = decodeHtmlEntities(stripTags(pMatch[1]))
+        description = text.length > 0 ? text.substring(0, 300) : null
+      }
+    } else {
+      // Fallback: look for p after the jobannonce link
+      const pMatches = [...cardHtml.matchAll(/<p[^>]*>([\s\S]*?)<\/p>/gi)]
+      for (const pm of pMatches) {
+        const text = decodeHtmlEntities(stripTags(pm[1]))
+        if (text.length > 20) {
+          description = text.substring(0, 300)
+          break
+        }
+      }
+    }
+
+    results.push({
+      id,
+      title,
+      company: company || null,
+      companyUrl: companyUrl || null,
+      location: location || null,
+      date: date || null,
+      deadline: null,
+      url,
+      description: description || null,
+    })
+  }
+
+  return results
+}
+
+export function extractDivContent(html: string, className: string): string | null {
+  const escaped = className.replace(/[.*+?^${}()|[\]\\]/g, '\\$&')
+  const openRe = new RegExp(`<div[^>]*class="[^"]*${escaped}[^"]*"[^>]*>`, 'i')
+  const open = openRe.exec(html)
+  if (!open) return null
+
+  let i = open.index + open[0].length
+  let depth = 1
+
+  while (depth > 0 && i < html.length) {
+    const nextOpen = html.indexOf('<div', i)
+    const nextClose = html.indexOf('</div>', i)
+
+    if (nextClose === -1) return null
+
+    if (nextOpen !== -1 && nextOpen < nextClose) {
+      depth++
+      i = nextOpen + 4
+    } else {
+      depth--
+      i = nextClose + 6
+    }
+  }
+
+  return html.slice(open.index + open[0].length, i - 6)
+}
+
+export function parseHitCount(html: string): number {
+  const match = html.match(/af <strong>([\d.]+)<\/strong>/)
+  if (!match) return 0
+  const numStr = match[1].replace(/\./g, "")
+  return parseInt(numStr, 10) || 0
+}

.agents/skills/jobindex-search/cli/tests/cli-contract.test.ts

@@ -0,0 +1,38 @@
+import { describe, expect, test } from "bun:test";
+import { runCLI } from "./helpers";
+
+describe("Jobindex CLI error contract", () => {
+  test("search without a query fails with JSON on stderr", async () => {
+    const result = await runCLI(["search"]);
+
+    expect(result.exitCode).toBe(1);
+    expect(result.stdout).toBe("");
+    expect(JSON.parse(result.stderr)).toEqual({
+      error: "--query is required",
+      code: "MISSING_REQUIRED",
+    });
+  });
+
+  test("detail without an ID fails before making a request", async () => {
+    const result = await runCLI(["detail"]);
+
+    expect(result.exitCode).toBe(1);
+    expect(result.stdout).toBe("");
+    expect(JSON.parse(result.stderr)).toEqual({
+      error: "Job ID or URL is required",
+      code: "MISSING_REQUIRED",
+    });
+  });
+
+  test("an invalid numeric option fails before making a request", async () => {
+    const result = await runCLI(["search", "--query", "test", "--page", "not-a-number"]);
+    const error = JSON.parse(result.stderr);
+
+    expect(result.exitCode).toBe(1);
+    expect(result.stdout).toBe("");
+    expect(error.ok).toBe(false);
+    expect(error.error.kind).toBe("validation");
+    expect(error.error.option).toBe("page");
+    expect(error.error.message).toContain("Expected number");
+  });
+});

.agents/skills/jobindex-search/cli/tests/cli-flag-validation.test.ts

@@ -0,0 +1,80 @@
+import { describe, expect, test } from "bun:test";
+import { runCLI } from "./helpers";
+
+// All cases fail schema validation (or the required-flag guard) before any
+// network request, so the suite is network-free. Regression context: a bare
+// z.coerce.number() accepted --limit=-1, and slice(0, -1) then silently
+// dropped the last result instead of erroring. Filter flags (--jobage) also
+// accepted negative and fractional values that were sent raw to the portal.
+
+function expectValidationError(result: { exitCode: number; stdout: string; stderr: string }, option: string) {
+  expect(result.exitCode).toBe(1);
+  expect(result.stdout).toBe("");
+  const error = JSON.parse(result.stderr);
+  expect(error.ok).toBe(false);
+  expect(error.error.kind).toBe("validation");
+  expect(error.error.option).toBe(option);
+}
+
+describe("Jobindex CLI flag validation", () => {
+  test("--limit=-1 is rejected instead of silently dropping the last result", async () => {
+    const result = await runCLI(["search", "--query", "test", "--limit=-1"]);
+    expectValidationError(result, "limit");
+    expect(JSON.parse(result.stderr).error.message).toContain("greater than or equal to 1");
+  });
+
+  test("--limit=0 is rejected", async () => {
+    const result = await runCLI(["search", "--query", "test", "--limit=0"]);
+    expectValidationError(result, "limit");
+  });
+
+  test("--limit=1.5 is rejected as non-integer", async () => {
+    const result = await runCLI(["search", "--query", "test", "--limit=1.5"]);
+    expectValidationError(result, "limit");
+    expect(JSON.parse(result.stderr).error.message).toContain("Expected integer");
+  });
+
+  test("--page=0 is rejected on the 1-indexed portal", async () => {
+    const result = await runCLI(["search", "--query", "test", "--page=0"]);
+    expectValidationError(result, "page");
+  });
+
+  test("--jobage=-5 is rejected", async () => {
+    const result = await runCLI(["search", "--query", "test", "--jobage=-5"]);
+    expectValidationError(result, "jobage");
+    expect(JSON.parse(result.stderr).error.message).toContain("greater than or equal to 1");
+  });
+
+  test("--jobage=1.5 is rejected as non-integer", async () => {
+    const result = await runCLI(["search", "--query", "test", "--jobage=1.5"]);
+    expectValidationError(result, "jobage");
+    expect(JSON.parse(result.stderr).error.message).toContain("Expected integer");
+  });
+
+  test("valid numeric flags pass schema validation (proven offline via the required-flag guard)", async () => {
+    const result = await runCLI(["search", "--page=2", "--limit=5"]);
+
+    expect(result.exitCode).toBe(1);
+    expect(JSON.parse(result.stderr)).toEqual({
+      error: "--query is required",
+      code: "MISSING_REQUIRED",
+    });
+  });
+});
+
+
+describe("unknown flag rejection", () => {
+  // add-portal.md's contract: "a bogus flag or missing required arg exits 1
+  // with a JSON error on stderr". A silently discarded flag is worse than an
+  // error: on jobdanmark a wrong flag name returned the entire database
+  // (13,862 results) as if it matched the query (review finding F13,
+  // 2026-08-19). Rejection happens before dispatch, so these are network-free.
+  test("a bogus --flag exits 1 with a JSON error instead of being silently discarded", async () => {
+    const result = await runCLI(["search", "--query", "test", "--bogus-flag", "xyz"]);
+    expect(result.exitCode).toBe(1);
+    expect(result.stdout).toBe("");
+    const error = JSON.parse(result.stderr);
+    expect(error.code).toBe("UNKNOWN_FLAG");
+    expect(error.error).toContain("--bogus-flag");
+  });
+});

.agents/skills/jobindex-search/cli/tests/detail-parsing.test.ts

@@ -0,0 +1,152 @@
+import { describe, expect, test } from "bun:test";
+import { parseDetailPage } from "../src/commands/detail";
+
+// Jobindex redesigned its detail pages; every selector the old parser used
+// (job-text, jix-info, jix_robotjob--area, jix-toolbar-top__company) is gone
+// from live pages, so detail returned null company/location/date, CSS-comment
+// text as the deadline, and an external ATS URL as its own id/url - exit 0,
+// nothing signalling breakage (review finding F14, 2026-08-19, measured on
+// 5/5 live postings). These fixtures are trimmed from live pages captured
+// 2026-08-19: the jobindex-native "jd-*" shape and the external-ATS
+// (hr-manager/Talentech) passthrough shape.
+
+const NATIVE_PAGE = `<!DOCTYPE html>
+<html lang="da">
+<head>
+  <title>VELLIV - Udvikler til Camunda/AWS</title>
+  <meta property="og:title" content="Udvikler til Camunda/AWS" />
+  <meta property="og:url" content="https://www.jobindex.dk/jobannonce/h1690934" />
+  <meta property="og:description" content="VELLIV" />
+</head>
+<body>
+  <div class="jd-appetizer">
+    <h1>Udvikler til Camunda/AWS</h1>
+  </div>
+  <div id="container" class="container">
+    <div class="row">
+      <div class="twelve columns jd-details">
+        <div class="jd-description">
+          <p class="appetizer">En virksomhed med mere end 100 &aring;rs historie, der samtidig er cloud-only, er ikke hverdagskost.</p>
+          <p>Hos Velliv f&aring;r du mulighed for at arbejde med Camunda, AWS og automatisering af processer.</p>
+        </div>
+      </div>
+      <div class="four columns jd-facts">
+        <div class="jd-type">
+          <h3>Jobtype:</h3>
+          <p>Fast</p>
+        </div>
+        <div class="jd-workhours">
+          <h3>Arbejdstid:</h3>
+          <p>Fuldtid</p>
+        </div>
+        <div class="jd-worktime">
+          <h3>Arbejdsdage:</h3>
+          <p>Dag</p>
+        </div>
+        <div class="jd-deadline">
+          <h3>Ans&oslash;gningsfrist:</h3>
+          <p>13. september 2026</p>
+        </div>
+        <div class="jd-location">
+          <h3>Arbejdssted:</h3>
+          <p>Ballerup</p>
+        </div>
+      </div>
+    </div>
+  </div>
+</body>
+</html>`;
+
+// The external shape: an employer's ATS-hosted ad served through jobindex.
+// og:url points at the ATS (NOT the posting), og:site_name is the ATS brand,
+// and the only occurrence of the deadline label outside the widget is inside
+// a CSS comment - the exact text the old regex captured as the deadline.
+const EXTERNAL_PAGE = `<!DOCTYPE html>
+<html>
+<head>
+  <title>
+	Talentech - C#-udvikler til kritiske analysel&oslash;sninger i elnettet
+</title>
+  <meta name="description" content="Vi s&oslash;ger en udvikler til elnettet" />
+  <meta itemprop="name" content="C#-udvikler til kritiske analysel&oslash;sninger i elnettet" />
+  <meta property="og:title" content="C#-udvikler til kritiske analysel&oslash;sninger i elnettet" />
+  <meta property="og:site_name" content="Talentech" />
+  <meta property="og:url" content="https://candidate.hr-manager.net/ApplicationInit.aspx?cid=316&amp;ProjectId=188792" />
+  <style>
+    /* Defines the style of the Application Due text */
+    /* DK: Ansøgningsfrist                           */
+    /* BOKSTAV: K                                    */
+    .frist { padding-bottom: 15px; }
+  </style>
+</head>
+<body>
+  <h1>C#-udvikler til kritiske analysel&oslash;sninger i elnettet</h1>
+  <p>Vil du v&aelig;re med til at udvikle og drifte de systemer, der underst&oslash;tter udbygningen af Danmarks kommende elnet? Vi arbejder i krydsfeltet mellem IT og energi.</p>
+  <div class="workplacelist emptyparent"><div id="workplacelist_lang" class="rowheader">Workplace</div><div class="widget-line"></div><span class="empty">Fredericia</span><br></div>
+  <div class="frist emptyparent"><div id="frist_lang" class="rowheader">Application due</div><div class="widget-line"></div><span class="empty">21-09-2026</span><br></div>
+</body>
+</html>`;
+
+const JOBANNONCE_URL = "https://www.jobindex.dk/jobannonce/";
+
+describe("parseDetailPage - jobindex-native (jd-*) shape", () => {
+  const job = parseDetailPage(NATIVE_PAGE, `${JOBANNONCE_URL}h1690934`, "h1690934");
+
+  test("extracts the contract fields", () => {
+    expect(job).toMatchObject({
+      id: "h1690934",
+      title: "Udvikler til Camunda/AWS",
+      company: "VELLIV",
+      location: "Ballerup",
+      deadline: "2026-09-13",
+      url: `${JOBANNONCE_URL}h1690934`,
+    });
+  });
+
+  test("converts the Danish long date to ISO", () => {
+    expect(job.deadline).toBe("2026-09-13");
+  });
+
+  test("extracts employment metadata and the description body", () => {
+    expect(job.employmentType).toBe("Fast");
+    expect(job.hours).toBe("Fuldtid");
+    expect(job.description).toContain("Camunda, AWS og automatisering");
+  });
+});
+
+describe("parseDetailPage - external ATS passthrough shape", () => {
+  const job = parseDetailPage(EXTERNAL_PAGE, `${JOBANNONCE_URL}h1690445`, "h1690445");
+
+  test("keeps the jobindex id and jobannonce URL, never the ATS og:url", () => {
+    expect(job.id).toBe("h1690445");
+    expect(job.url).toBe(`${JOBANNONCE_URL}h1690445`);
+    expect(job.url).not.toContain("hr-manager.net");
+  });
+
+  test("extracts the title and never reports the ATS brand as the company", () => {
+    expect(job.title).toBe("C#-udvikler til kritiske analyseløsninger i elnettet");
+    expect(job.company).toBeNull();
+  });
+
+  test("extracts the workplace widget location", () => {
+    expect(job.location).toBe("Fredericia");
+  });
+
+  test("finds the real deadline, not the CSS comment", () => {
+    expect(job.deadline).toBe("2026-09-21");
+  });
+
+  test("description is readable body text, not a stylesheet", () => {
+    expect(job.description).toContain("udbygningen af Danmarks kommende elnet");
+    expect(job.description).not.toContain("padding-bottom");
+  });
+
+  test("deadline is null when only the CSS comment mentions the label", () => {
+    const noDueWidget = EXTERNAL_PAGE.replace(
+      /<div class="frist emptyparent">[\s\S]*?<br><\/div>/,
+      "",
+    );
+    const parsed = parseDetailPage(noDueWidget, `${JOBANNONCE_URL}h9`, "h9");
+    expect(parsed.deadline).toBeNull();
+  });
+});

.agents/skills/jobindex-search/cli/tests/helpers.ts

@@ -0,0 +1,39 @@
+import { join } from "path";
+
+const CLI_PATH = join(import.meta.dir, "../src/cli.ts");
+
+export interface CLIResult {
+  stdout: string;
+  stderr: string;
+  exitCode: number;
+}
+
+export async function runCLI(args: string[]): Promise<CLIResult> {
+  const proc = Bun.spawn(["bun", "run", CLI_PATH, ...args], {
+    stdout: "pipe",
+    stderr: "pipe",
+  });
+
+  const [stdout, stderr, exitCode] = await Promise.all([
+    new Response(proc.stdout).text(),
+    new Response(proc.stderr).text(),
+    proc.exited,
+  ]);
+
+  return { stdout: stdout.trim(), stderr: stderr.trim(), exitCode };
+}
+
+export function parseJSON<T = unknown>(result: CLIResult): T {
+  if (result.exitCode !== 0) {
+    throw new Error(
+      `CLI exited with code ${result.exitCode}. stderr: ${result.stderr}`
+    );
+  }
+  try {
+    return JSON.parse(result.stdout) as T;
+  } catch {
+    throw new Error(
+      `Failed to parse JSON. stdout: ${result.stdout}\nstderr: ${result.stderr}`
+    );
+  }
+}

.agents/skills/jobindex-search/cli/tests/parsing.test.ts

@@ -0,0 +1,98 @@
+import { describe, test, expect } from "bun:test";
+import { parseJobCards, extractDivContent } from "../src/helpers";
+
+// Minimal jobad-wrapper markup: parseJobCards splits on `jobad-wrapper-<id>`
+// and reads the title from the <h4><a href>…</a></h4> and the company from the
+// jix-toolbar-top__company link. We inject HTML entities to exercise decoding.
+function card(id: string, title: string, company = "Acme A/S"): string {
+  return `<div id="jobad-wrapper-${id}" class="PaidJob">
+    <h4><a href="https://www.jobindex.dk/jobannonce/${id}">${title}</a></h4>
+    <div class="jix-toolbar-top__company">
+      <a href="https://www.jobindex.dk/virksomhed/acme">${company}</a>
+    </div>
+  </div>`;
+}
+
+describe("decodeHtmlEntities (via parseJobCards)", () => {
+  test("decodes hexadecimal numeric entities (&#xF8; -> ø)", () => {
+    const [c] = parseJobCards(card("h1", "Sm&#xF8;rrebro Chef"));
+    expect(c.title).toBe("Smørrebro Chef");
+  });
+
+  test("decodes uppercase-X hexadecimal entities (&#XE6; -> æ)", () => {
+    const [c] = parseJobCards(card("h2", "K&#XE6;re Kollega"));
+    expect(c.title).toBe("Kære Kollega");
+  });
+
+  test("still decodes decimal numeric entities (&#229; -> å) — regression", () => {
+    const [c] = parseJobCards(card("h3", "&#229;rhus Lead"));
+    expect(c.title).toBe("århus Lead");
+  });
+
+  test("decodes supplementary-plane code points with fromCodePoint (&#128512;)", () => {
+    const [c] = parseJobCards(card("h4", "Growth &#128512;"));
+    expect(c.title).toBe("Growth 😀");
+  });
+
+  test("decodes hex supplementary-plane code points (&#x1F600;)", () => {
+    const [c] = parseJobCards(card("h5", "Growth &#x1F600;"));
+    expect(c.title).toBe("Growth 😀");
+  });
+
+  test("decodes hex entities in the company name too", () => {
+    const [c] = parseJobCards(card("h6", "Engineer", "N&#xF8;rrebro ApS"));
+    expect(c.company).toBe("Nørrebro ApS");
+  });
+});
+
+describe("extractDivContent", () => {
+  test("extracts content from simple div", () => {
+    const html = '<div class="job-text">Simple text</div>';
+    expect(extractDivContent(html, "job-text")).toBe("Simple text");
+  });
+
+  test("extracts content with nested divs — the regression case", () => {
+    const html = `<div class="job-text">
+      <div class="highlight">First section</div>
+      <div class="details">Second section with important info</div>
+    </div>`;
+    expect(extractDivContent(html, "job-text")).toBe(
+      '\n      <div class="highlight">First section</div>\n      <div class="details">Second section with important info</div>\n    ',
+    );
+  });
+
+  test("returns null when class not found", () => {
+    expect(extractDivContent("<div>no class</div>", "nonexistent")).toBeNull();
+  });
+
+  test("works with extra attributes on the div", () => {
+    const html = '<div id="desc" class="job-text" data-x="1">Content</div>';
+    expect(extractDivContent(html, "job-text")).toBe("Content");
+  });
+
+  test("handles deeply nested divs (3 levels)", () => {
+    const html = `<div class="job-text">
+      <div>
+        <div>Deep content</div>
+      </div>
+    </div>`;
+    expect(extractDivContent(html, "job-text")).toBe(
+      '\n      <div>\n        <div>Deep content</div>\n      </div>\n    ',
+    );
+  });
+
+  test("handles empty content", () => {
+    const html = '<div class="job-text"></div>';
+    expect(extractDivContent(html, "job-text")).toBe("");
+  });
+
+  test("handles br and other non-div tags", () => {
+    const html = '<div class="job-text">Line1<br>Line2<br>Line3</div>';
+    expect(extractDivContent(html, "job-text")).toBe("Line1<br>Line2<br>Line3");
+  });
+
+  test("escapes special regex characters in class name", () => {
+    const html = '<div class="job-text (special)">Content</div>';
+    expect(extractDivContent(html, "job-text (special)")).toBe("Content");
+  });
+});

.agents/skills/jobindex-search/cli/tests/request-timeout.test.ts

@@ -0,0 +1,34 @@
+import { afterEach, describe, expect, test } from "bun:test";
+import { apiFetch, htmlFetch } from "../src/helpers";
+
+// A stalled upstream connection (accepted socket, no response) would otherwise
+// hang the CLI forever - fetch has no default timeout. Assert both request
+// wrappers carry an AbortSignal timeout. Fails on the pre-fix code (no signal).
+const originalFetch = globalThis.fetch;
+afterEach(() => {
+  globalThis.fetch = originalFetch;
+});
+
+describe("request timeout", () => {
+  test("apiFetch passes an AbortSignal timeout to fetch", async () => {
+    let init: RequestInit | undefined;
+    globalThis.fetch = (async (_url: string | URL | Request, i?: RequestInit) => {
+      init = i;
+      return new Response("{}", { status: 200 });
+    }) as unknown as typeof fetch;
+
+    await apiFetch("/search");
+    expect(init?.signal).toBeInstanceOf(AbortSignal);
+  });
+
+  test("htmlFetch passes an AbortSignal timeout to fetch", async () => {
+    let init: RequestInit | undefined;
+    globalThis.fetch = (async (_url: string | URL | Request, i?: RequestInit) => {
+      init = i;
+      return new Response("<html></html>", { status: 200 });
+    }) as unknown as typeof fetch;
+
+    await htmlFetch("https://www.jobindex.dk/x");
+    expect(init?.signal).toBeInstanceOf(AbortSignal);
+  });
+});

.agents/skills/jobindex-search/cli/tests/retry-backoff.test.ts

@@ -0,0 +1,89 @@
+import { afterEach, describe, expect, test } from "bun:test";
+import { apiFetch, htmlFetch } from "../src/helpers";
+
+// The portal contract requires backoff on 429/5xx. These tests pin the retry
+// loop offline: a stubbed fetch counts attempts, and a stubbed setTimeout
+// fires immediately so the exhaustion case does not sleep through the real
+// 500ms -> 5s backoff schedule. apiFetch and htmlFetch carry separate copies
+// of the loop, so both are exercised to keep them from drifting apart.
+
+const originalFetch = globalThis.fetch;
+const originalSetTimeout = globalThis.setTimeout;
+
+afterEach(() => {
+  globalThis.fetch = originalFetch;
+  globalThis.setTimeout = originalSetTimeout;
+});
+
+function instantTimers() {
+  globalThis.setTimeout = ((fn: () => void) =>
+    originalSetTimeout(fn, 0)) as unknown as typeof setTimeout;
+}
+
+function stubFetch(responses: Array<() => Response>): { calls: number } {
+  const state = { calls: 0 };
+  globalThis.fetch = (async () => {
+    const i = Math.min(state.calls, responses.length - 1);
+    state.calls++;
+    return responses[i]();
+  }) as unknown as typeof fetch;
+  return state;
+}
+
+describe("htmlFetch retry/backoff", () => {
+  test("retries a 429 and succeeds on the next attempt", async () => {
+    instantTimers();
+    const state = stubFetch([
+      () => new Response("", { status: 429 }),
+      () => new Response("<html>ok</html>", { status: 200 }),
+    ]);
+
+    const html = await htmlFetch("https://www.jobindex.dk/x");
+    expect(html).toContain("ok");
+    expect(state.calls).toBe(2);
+  });
+
+  test("does not retry a plain 4xx", async () => {
+    const state = stubFetch([() => new Response("", { status: 400 })]);
+
+    await expect(htmlFetch("https://www.jobindex.dk/x")).rejects.toThrow(/400/);
+    expect(state.calls).toBe(1);
+  });
+
+  test("gives up after the initial attempt plus six retries on persistent 5xx", async () => {
+    instantTimers();
+    const state = stubFetch([() => new Response("", { status: 500 })]);
+
+    await expect(htmlFetch("https://www.jobindex.dk/x")).rejects.toThrow(/500/);
+    expect(state.calls).toBe(7);
+  });
+});
+
+describe("apiFetch retry/backoff", () => {
+  test("retries a 429 and succeeds on the next attempt", async () => {
+    instantTimers();
+    const state = stubFetch([
+      () => new Response("", { status: 429 }),
+      () => new Response('{"ok":true}', { status: 200 }),
+    ]);
+
+    const data = await apiFetch<{ ok: boolean }>("/x");
+    expect(data.ok).toBe(true);
+    expect(state.calls).toBe(2);
+  });
+
+  test("does not retry a plain 4xx", async () => {
+    const state = stubFetch([() => new Response("", { status: 400 })]);
+
+    await expect(apiFetch("/x")).rejects.toThrow(/400/);
+    expect(state.calls).toBe(1);
+  });
+
+  test("gives up after the initial attempt plus six retries on persistent 5xx", async () => {
+    instantTimers();
+    const state = stubFetch([() => new Response("", { status: 500 })]);
+
+    await expect(apiFetch("/x")).rejects.toThrow(/500/);
+    expect(state.calls).toBe(7);
+  });
+});

.agents/skills/jobindex-search/cli/tests/search-page.test.ts

@@ -0,0 +1,69 @@
+import { describe, expect, test } from "bun:test";
+import { parseSearchPage } from "../src/helpers";
+
+// parseSearchPage had no tests at all: mutating total to stop using
+// sr.hitcount survived the whole suite (review finding F35, 2026-08-19).
+// The fixture mirrors the real Stash nesting documented in helpers.ts:
+// jobsearch/result_app -> storeData -> searchResponse -> { hitcount, results[] }.
+function stashPage(searchResponse: object): string {
+  const stash = { jobsearch: { result_app: { storeData: { searchResponse } } } };
+  return `<html><head><script>var Stash = ${JSON.stringify(stash)};</script></head></html>`;
+}
+
+const RESULT = {
+  tid: "h1689961",
+  headline: "Softwareudvikler",
+  company: { name: "Acme A/S", homeurl: "https://acme.example" },
+  area: "Aarhus",
+  firstdate: "2026-08-10",
+  apply_deadline: "2026-09-11T00:00:00",
+};
+
+describe("parseSearchPage", () => {
+  test("total comes from hitcount, not the page's result count", () => {
+    const page = stashPage({ hitcount: 435, results: [RESULT] });
+    const parsed = parseSearchPage(page);
+    expect(parsed.total).toBe(435);
+    expect(parsed.results).toHaveLength(1);
+  });
+
+  test("total falls back to the result count when hitcount is absent", () => {
+    const page = stashPage({ results: [RESULT, { ...RESULT, tid: "h2" }] });
+    expect(parseSearchPage(page).total).toBe(2);
+  });
+
+  test("maps the contract fields from a Stash result", () => {
+    const [job] = parseSearchPage(stashPage({ hitcount: 1, results: [RESULT] })).results;
+    expect(job).toMatchObject({
+      id: "h1689961",
+      title: "Softwareudvikler",
+      company: "Acme A/S",
+      location: "Aarhus",
+      date: "2026-08-10",
+      deadline: "2026-09-11",
+      url: "https://www.jobindex.dk/jobannonce/h1689961",
+    });
+  });
+
+  test("maps an ASAP posting's deadline to null (no stated deadline)", () => {
+    // apply_deadline_asap means "no fixed deadline, apply now". The /scrape
+    // schema defines null as exactly that, and every consumer (rank's expiry
+    // sweep, notion-sync's typed date column) does date arithmetic on this
+    // field - a bare "ASAP" string broke all of them on half of live results
+    // (review finding F12, 2026-08-19). lastdate present too: the flag wins.
+    const [job] = parseSearchPage(
+      stashPage({
+        hitcount: 1,
+        results: [{ ...RESULT, apply_deadline: undefined, apply_deadline_asap: true, lastdate: "2026-09-30" }],
+      }),
+    ).results;
+    expect(job.deadline).toBeNull();
+  });
+
+  test("falls back to lastdate when apply_deadline is absent", () => {
+    const [job] = parseSearchPage(
+      stashPage({ hitcount: 1, results: [{ ...RESULT, apply_deadline: undefined, lastdate: "2026-09-30" }] }),
+    ).results;
+    expect(job.deadline).toBe("2026-09-30");
+  });
+});

.agents/skills/jobindex-search/cli/tsconfig.json

@@ -0,0 +1,20 @@
+{
+  "compilerOptions": {
+    "target": "ESNext",
+    "module": "ESNext",
+    "moduleResolution": "bundler",
+    "lib": ["ESNext"],
+    "types": ["bun-types"],
+    "strict": true,
+    "noImplicitAny": true,
+    "strictNullChecks": true,
+    "noUnusedLocals": true,
+    "noUnusedParameters": true,
+    "noFallthroughCasesInSwitch": true,
+    "skipLibCheck": true,
+    "outDir": "dist",
+    "rootDir": "."
+  },
+  "include": ["src/**/*", "tests/**/*"],
+  "exclude": ["node_modules", "dist"]
+}