jd-intel 0.1.0 → 0.2.0

package/README.md

@@ -3,6 +3,8 @@
 [![MIT License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
 [![Node.js 18+](https://img.shields.io/badge/node-18%2B-green.svg)](https://nodejs.org)
 [![npm](https://img.shields.io/npm/v/jd-intel.svg)](https://www.npmjs.com/package/jd-intel)
+[![npm downloads](https://img.shields.io/npm/dw/jd-intel-mcp.svg)](https://www.npmjs.com/package/jd-intel-mcp)
+[![GitHub stars](https://img.shields.io/github/stars/prPMDev/jd-intel.svg?style=flat)](https://github.com/prPMDev/jd-intel/stargazers)
 
 > **Stop pasting job descriptions into AI assistants. Let your AI fetch them directly.**
 
@@ -16,13 +18,17 @@ Your AI assistant already knows a lot about you. Your resume is in its memory. Y
 
 So you copy-paste.
 
-A JD from Stripe. Another from Mercury. Six more from your target list. Half have broken HTML. Salary info dies in translation. Links get stripped. And for every role, the dance starts over.
+A JD from one company. Another from the next. A half-dozen more from your target list. Half have broken HTML. Salary info dies in translation. Links get stripped. And for every role, the dance starts over.
 
 You could wait for the job boards to ship their own MCPs. They'll get there eventually. On their timeline. Filtered through their priorities, not yours. Tied to their query abstractions.
 
 jd-intel skips that wait. Raw JDs, fetched directly by your AI, on your terms. One level below the curated layer.
 
-> "Claude, pull the senior PM role at Stripe and draft a cover letter based on my resume."
+Try asking your AI:
+
+> "Find AI/ML engineering jobs posted this week."
+> "What product designer roles are open at fintechs right now?"
+> "Pull the staff PM roles posted in the last 7 days."
 
 Done.
 
@@ -30,10 +36,10 @@ Done.
 
 ## What you can do with it
 
-- Draft cover letters without pasting anything
+- Look up open roles at any company directly from your AI, no copy-paste
 - Tailor your resume across ten roles in one conversation
 - Rank openings by fit with your background
-- Scan a whole sector: "Pull PM roles at fintech companies posted this week"
+- Scan a whole sector: "Pull open roles at fintech companies posted this week"
 - Research teams by reading their JDs in bulk
 
 The toolkit fetches. Your AI thinks.
@@ -42,12 +48,63 @@ The toolkit fetches. Your AI thinks.
 
 ## Install
 
-### For Claude Desktop, Cursor, Windsurf users
+Works with MCP-aware AI clients: Claude Desktop, Claude Code, Cursor, Windsurf. ChatGPT, Gemini, and other non-MCP clients don't support this yet. They use different tool-calling systems. (We wish they did. The protocol works the same way regardless of which AI you talk to.)
+
+You'll need [Node.js 18 or newer](https://nodejs.org/). To check: open a terminal and run `node --version`. If it's missing or older, install from nodejs.org first.
+
+### For Claude Desktop (one command)
+
+1. **Open a terminal.** It's just a text window. Nothing destructive happens here.
+   - **macOS:** Spotlight (`⌘ Space`), type "Terminal", hit Enter.
+   - **Windows:** Start menu, type "PowerShell", hit Enter.
+
+2. **Paste this and hit Enter:**
+   ```bash
+   npx jd-intel-mcp install
+   ```
+
+3. **Quit and reopen Claude Desktop.** The tools appear automatically.
+
+Try: *"Find product roles at devtools companies."*
+
+If something goes wrong or you'd rather edit the config file directly, see [Manual install](#manual-install-fallback) below.
+
+### For Cursor and Windsurf
+
+These clients have their own MCP setup flows. Follow their docs:
+- Cursor: [docs.cursor.com](https://docs.cursor.com)
+- Windsurf: [docs.windsurf.com](https://docs.windsurf.com)
+
+Use this server config: `command: "npx"`, `args: ["-y", "jd-intel-mcp"]`.
 
-Add to your MCP config file:
+### For developers
 
-**macOS:** `~/Library/Application Support/Claude/claude_desktop_config.json`
-**Windows:** `%APPDATA%\Claude\claude_desktop_config.json`
+```bash
+npm install jd-intel
+```
+
+```js
+import { fetchJobs } from 'jd-intel';
+
+const jobs = await fetchJobs({
+  company: '<your-target-company>',
+  titleFilter: 'designer',
+  postedWithinDays: 14,
+  limit: 50,
+});
+```
+
+CLI usage: `npx jd-intel fetch <company-slug> --title-filter "engineer" --posted-within-days 14`. Full filter reference [below](#filters-quick-reference).
+
+Node.js 18+. No API keys. No configuration.
+
+### Manual install (fallback)
+
+If `npx jd-intel-mcp install` fails, edit the config directly.
+
+**Config file location:**
+- **macOS:** `~/Library/Application Support/Claude/claude_desktop_config.json`
+- **Windows:** `%APPDATA%\Claude\claude_desktop_config.json`
 
 ```json
 {
@@ -60,40 +117,26 @@ Add to your MCP config file:
 }
 ```
 
-Restart your AI client. The tools appear automatically. Ask your AI to fetch any role.
+Restart Claude Desktop.
 
-**One-command install (avoids hand-editing the config):**
-```bash
-npx jd-intel-mcp install
-```
+### Updating
 
-### For developers (CLI and library)
+`npx -y jd-intel-mcp` auto-updates within ~24 hours via npm's cache. To force an update immediately:
 
 ```bash
-npm install jd-intel
+npx clear-npx-cache
 ```
 
-Or run without installing:
+Then quit and reopen Claude Desktop.
 
-```bash
-npx jd-intel fetch stripe --title-filter "product manager"
-```
+If you installed the library or CLI directly:
 
-Or import as a library:
-
-```js
-import { fetchJobs, registry } from 'jd-intel';
-
-const jobs = await fetchJobs({
-  company: 'ramp',
-  titleFilter: 'engineer',
-  postedWithinDays: 14,
-  limit: 50,
-});
+```bash
+npm install jd-intel@latest       # force latest
+# or
+npm update jd-intel               # respect semver
 ```
 
-Node.js 18+. No API keys. No configuration.
-
 ---
 
 ## MCP tools
@@ -115,14 +158,14 @@ Every job normalizes to one schema, across every platform:
 ```json
 {
   "id": "a1b2c3d4e5f6",
-  "company": "Stripe",
-  "title": "Senior Product Manager, Integrations",
-  "department": "Product",
-  "location": "San Francisco, CA",
-  "locationType": "hybrid",
-  "salary": { "min": 180000, "max": 260000, "currency": "USD" },
-  "description": "Lead strategy for Stripe's integration ecosystem...",
-  "url": "https://boards.greenhouse.io/stripe/jobs/12345",
+  "company": "Example Co",
+  "title": "Senior Software Engineer, Platform",
+  "department": "Engineering",
+  "location": "Remote - US",
+  "locationType": "remote",
+  "salary": { "min": 180000, "max": 240000, "currency": "USD" },
+  "description": "Design and build the API surface our customers integrate against...",
+  "url": "https://boards.example.com/jobs/12345",
   "postedAt": "2026-04-10T14:30:00Z"
 }
 ```
@@ -152,6 +195,7 @@ No custom parsing per company.
 | Greenhouse | Shipped | Most widely used ATS in tech |
 | Ashby | Shipped | Growing fast with startups |
 | Lever | Shipped | Common at mid-stage companies |
+| SmartRecruiters | Shipped | Enterprise and mid-market |
 | BambooHR | Planned | Mid-market companies |
 | Workday | Planned | Large enterprises |
 
@@ -178,18 +222,18 @@ All filters AND together. Deep dive on patterns and gotchas: [docs/filters.md](d
 
 **Shipped**
 - Library, CLI, and MCP server (three surfaces of one toolkit)
-- Greenhouse, Ashby, Lever adapters
+- Greenhouse, Ashby, Lever, SmartRecruiters adapters
 - Title, topic, location, and date filters
 - Salary extraction from JD text
-- Verified company registry (66 companies)
+- Verified company registry (100+ companies)
 
 **Next**
+- TeamTailor adapter (European startup coverage)
 - Anthropic MCP marketplace submission
-- Setup guide with screenshots (non-technical walkthrough)
-- Remote MCP transport (for Claude.ai Custom Connectors)
 
 **Planned**
-- BambooHR and Workday adapters
+- BambooHR and Workable adapters
+- Workday support (scoped scraper — large enterprise universe)
 - Temporal tracking (when roles open, close, reopen)
 - Change detection
 - Resume-aware fit scoring
@@ -208,7 +252,7 @@ All filters AND together. Deep dive on patterns and gotchas: [docs/filters.md](d
 
 ## Built by
 
-**[Prashant R](https://prashantrana.xyz)**. PM who builds. I write about what actually happens at the layer below the AI hype.
+**[Prashant R](https://prashantrana.xyz)**. PM who builds. I try out and build what really matters below the AI hype.
 
 - Portfolio and writing: [prashantrana.xyz](https://prashantrana.xyz)
 - [LinkedIn](https://www.linkedin.com/in/prashant-rana)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "jd-intel",
-  "version": "0.1.0",
+  "version": "0.2.0",
   "description": "Fetch and normalize job descriptions across every major ATS (Greenhouse, Lever, Ashby) — for your AI assistant, no copy-paste.",
   "type": "module",
   "main": "src/index.js",
@@ -28,7 +28,17 @@
     "ai",
     "claude",
     "hiring",
-    "careers"
+    "careers",
+    "model-context-protocol",
+    "anthropic",
+    "cursor",
+    "windsurf",
+    "ai-tools",
+    "ai-assistant",
+    "job-search",
+    "applicant-tracking-system",
+    "developer-tools",
+    "nodejs"
   ],
   "author": "Prashant R",
   "license": "MIT",

package/registry/ashby.json

@@ -12,5 +12,18 @@
   {"slug": "shiftkey",  "name": "ShiftKey",  "sector": "healthcare staffing"},
   {"slug": "gorgias",   "name": "Gorgias",   "sector": "customer support"},
   {"slug": "zapier",    "name": "Zapier",    "sector": "integration platform"},
-  {"slug": "clickup",   "name": "ClickUp",   "sector": "productivity"}
+  {"slug": "clickup",   "name": "ClickUp",   "sector": "productivity"},
+  {"slug": "higharc",        "name": "Higharc",        "sector": "architecture tech"},
+  {"slug": "mural",          "name": "Mural",          "sector": "collaboration"},
+  {"slug": "ironcladhq",     "name": "Ironclad",       "sector": "legal tech"},
+  {"slug": "wrapbook",       "name": "Wrapbook",       "sector": "entertainment payroll"},
+  {"slug": "Tabs",           "name": "Tabs",           "sector": "fintech"},
+  {"slug": "vibe",           "name": "Vibe",           "sector": "saas"},
+  {"slug": "unicourt",       "name": "UniCourt",       "sector": "legal tech"},
+  {"slug": "meridianlink",   "name": "MeridianLink",   "sector": "fintech"},
+  {"slug": "Hippocratic AI", "name": "Hippocratic AI", "sector": "healthcare ai"},
+  {"slug": "scan-com",       "name": "Scan.com",       "sector": "healthcare imaging"},
+  {"slug": "hiive",          "name": "Hiive",          "sector": "marketplaces"},
+  {"slug": "virtuous",       "name": "Virtuous",       "sector": "nonprofit crm"},
+  {"slug": "jasper ai",      "name": "Jasper",         "sector": "ai writing"}
 ]

package/registry/greenhouse.json

@@ -43,5 +43,37 @@
   {"slug": "braze",             "name": "Braze",             "sector": "marketing tech"},
   {"slug": "appsflyer",         "name": "AppsFlyer",         "sector": "marketing tech"},
   {"slug": "attentive",         "name": "Attentive",         "sector": "marketing tech"},
-  {"slug": "iterable",          "name": "Iterable",          "sector": "marketing tech"}
+  {"slug": "iterable",          "name": "Iterable",          "sector": "marketing tech"},
+  {"slug": "nextroll",              "name": "NextRoll",                  "sector": "adtech"},
+  {"slug": "cloudbeds",             "name": "Cloudbeds",                 "sector": "hospitality tech"},
+  {"slug": "headspacesourcing",     "name": "Headspace (Sourcing)",      "sector": "mental health"},
+  {"slug": "fleetio",               "name": "Fleetio",                   "sector": "fleet management"},
+  {"slug": "engine",                "name": "Engine",                    "sector": "travel tech"},
+  {"slug": "axon",                  "name": "Axon",                      "sector": "public safety"},
+  {"slug": "sparrow",               "name": "Sparrow",                   "sector": "hr tech"},
+  {"slug": "remotecom",             "name": "Remote",                    "sector": "hr tech"},
+  {"slug": "weedmaps77",            "name": "Weedmaps",                  "sector": "cannabis"},
+  {"slug": "patterndata",           "name": "Pattern",                   "sector": "ecommerce data"},
+  {"slug": "tubitv",                "name": "Tubi",                      "sector": "streaming"},
+  {"slug": "future",                "name": "Future",                    "sector": "fitness"},
+  {"slug": "eltropyinc",            "name": "Eltropy",                   "sector": "fintech"},
+  {"slug": "ziprecruiter",          "name": "ZipRecruiter",              "sector": "recruiting tech"},
+  {"slug": "cognitiv",              "name": "Cognitiv",                  "sector": "adtech"},
+  {"slug": "maintainx",             "name": "MaintainX",                 "sector": "industrial saas"},
+  {"slug": "betterhelpcom",         "name": "BetterHelp",                "sector": "mental health"},
+  {"slug": "shopmonkey",            "name": "Shopmonkey",                "sector": "automotive saas"},
+  {"slug": "ezcaterinc",            "name": "ezCater",                   "sector": "food tech"},
+  {"slug": "trivelta",              "name": "TriVelta",                  "sector": "saas"},
+  {"slug": "firstconnectinsurance", "name": "First Connect Insurance",   "sector": "insurtech"},
+  {"slug": "justworks",             "name": "Justworks",                 "sector": "hr tech"},
+  {"slug": "starrez",               "name": "StarRez",                   "sector": "property management"},
+  {"slug": "upstart",               "name": "Upstart",                   "sector": "fintech"},
+  {"slug": "affirm",                "name": "Affirm",                    "sector": "fintech"},
+  {"slug": "houseaccount",          "name": "House Account",             "sector": "saas"},
+  {"slug": "appdirect",             "name": "AppDirect",                 "sector": "cloud commerce"},
+  {"slug": "rubrik",                "name": "Rubrik",                    "sector": "security"},
+  {"slug": "asana",                 "name": "Asana",                     "sector": "productivity"},
+  {"slug": "instacart",             "name": "Instacart",                 "sector": "grocery delivery"},
+  {"slug": "discord",               "name": "Discord",                   "sector": "social"},
+  {"slug": "hs",                    "name": "Headspace",                 "sector": "mental health"}
 ]

package/registry/lever.json

@@ -6,5 +6,12 @@
   {"slug": "clari",     "name": "Clari",    "sector": "sales tech"},
   {"slug": "netflix",   "name": "Netflix",  "sector": "media"},
   {"slug": "lever",     "name": "Lever",    "sector": "recruiting tech"},
-  {"slug": "postman",   "name": "Postman",  "sector": "developer tools"}
+  {"slug": "postman",      "name": "Postman",       "sector": "developer tools"},
+  {"slug": "agiloft",      "name": "Agiloft",       "sector": "contract management"},
+  {"slug": "gohighlevel",  "name": "HighLevel",     "sector": "marketing saas"},
+  {"slug": "veeva",        "name": "Veeva Systems", "sector": "life sciences"},
+  {"slug": "caremessage",  "name": "CareMessage",   "sector": "healthcare communications"},
+  {"slug": "rover",        "name": "Rover",         "sector": "pet care"},
+  {"slug": "LuminDigital", "name": "Lumin Digital", "sector": "fintech (banking)"},
+  {"slug": "redoxengine",  "name": "Redox",         "sector": "healthcare interop"}
 ]

package/registry/smartrecruiters.json

@@ -0,0 +1,13 @@
+[
+  {"slug": "Visa",           "name": "Visa",            "sector": "payments"},
+  {"slug": "Wise",           "name": "Wise",            "sector": "fintech"},
+  {"slug": "Wabtec",         "name": "Wabtec",          "sector": "rail / industrial"},
+  {"slug": "Sutherland",     "name": "Sutherland",      "sector": "bpo / cx"},
+  {"slug": "AveryDennison",  "name": "Avery Dennison",  "sector": "materials"},
+  {"slug": "PublicStorage",  "name": "Public Storage",  "sector": "real estate"},
+  {"slug": "Sportradar",     "name": "Sportradar",      "sector": "sports data"},
+  {"slug": "Entain",         "name": "Entain",          "sector": "gaming"},
+  {"slug": "Picnic",         "name": "Picnic",          "sector": "grocery delivery"},
+  {"slug": "Hootsuite",      "name": "Hootsuite",       "sector": "social media management"},
+  {"slug": "BusinessWire",   "name": "Business Wire",   "sector": "pr / newswire"}
+]

package/src/adapters/index.js

@@ -1,11 +1,13 @@
 export { fetchGreenhouse, hasGreenhouse } from './greenhouse.js';
 export { fetchLever, hasLever } from './lever.js';
 export { fetchAshby, hasAshby } from './ashby.js';
+export { fetchSmartrecruiters, hasSmartrecruiters } from './smartrecruiters.js';
 
 export const ADAPTERS = {
   greenhouse: { fetch: (...args) => import('./greenhouse.js').then(m => m.fetchGreenhouse(...args)), has: (...args) => import('./greenhouse.js').then(m => m.hasGreenhouse(...args)) },
   lever: { fetch: (...args) => import('./lever.js').then(m => m.fetchLever(...args)), has: (...args) => import('./lever.js').then(m => m.hasLever(...args)) },
   ashby: { fetch: (...args) => import('./ashby.js').then(m => m.fetchAshby(...args)), has: (...args) => import('./ashby.js').then(m => m.hasAshby(...args)) },
+  smartrecruiters: { fetch: (...args) => import('./smartrecruiters.js').then(m => m.fetchSmartrecruiters(...args)), has: (...args) => import('./smartrecruiters.js').then(m => m.hasSmartrecruiters(...args)) },
 };
 
 export const ATS_NAMES = Object.keys(ADAPTERS);

package/src/adapters/smartrecruiters.js

@@ -0,0 +1,108 @@
+import { normalize, stripHtml } from '../normalizer.js';
+
+const BASE_URL = 'https://api.smartrecruiters.com/v1/companies';
+const PAGE_SIZE = 100;
+
+/**
+ * Fetch all postings from a SmartRecruiters company.
+ * Public API, no auth required.
+ * Docs: https://developers.smartrecruiters.com/reference/postingsget-1
+ *
+ * Two-step flow (unavoidable N+1):
+ *   - The postings LIST endpoint omits the job description entirely.
+ *   - jd-intel's contract is "full JD text", so we must fetch each
+ *     posting's DETAIL endpoint to get jobAd.sections.
+ * Large enterprise tenants with hundreds of openings will therefore be
+ * slow against SmartRecruiters specifically. This is the API's shape,
+ * not a bug here.
+ *
+ * @param {string} slug - SmartRecruiters company identifier (e.g., 'Visa')
+ * @returns {Promise<Array>} Normalized job objects
+ */
+export async function fetchSmartrecruiters(slug) {
+  // 1. Page through the postings list.
+  const postings = [];
+  let offset = 0;
+
+  while (true) {
+    const listUrl = `${BASE_URL}/${slug}/postings?limit=${PAGE_SIZE}&offset=${offset}`;
+    const resp = await fetch(listUrl);
+
+    if (!resp.ok) {
+      if (resp.status === 404) return []; // Company not found
+      throw new Error(`SmartRecruiters API error for ${slug}: ${resp.status}`);
+    }
+
+    const data = await resp.json();
+    const content = data.content || [];
+    postings.push(...content);
+
+    offset += PAGE_SIZE;
+    if (content.length === 0 || offset >= (data.totalFound || 0)) break;
+  }
+
+  // 2. Fetch detail per posting for the description.
+  const jobs = await Promise.all(postings.map(async (p) => {
+    let sections = {};
+    let postingUrl = '';
+
+    try {
+      const detailResp = await fetch(`${BASE_URL}/${slug}/postings/${p.id}`);
+      if (detailResp.ok) {
+        const detail = await detailResp.json();
+        sections = detail.jobAd?.sections || {};
+        postingUrl = detail.postingUrl || detail.applyUrl || '';
+      }
+    } catch {
+      // Detail fetch failed: fall back to list-only fields (no description).
+    }
+
+    const description = [
+      sections.jobDescription?.text,
+      sections.qualifications?.text,
+      sections.additionalInformation?.text,
+    ].filter(Boolean).join('\n\n');
+
+    const loc = p.location || {};
+    const place = loc.fullLocation
+      || [loc.city, loc.region, loc.country].filter(Boolean).join(', ');
+    let location = place;
+    if (loc.remote) location = `Remote - ${place}`.replace(/ - $/, ' ');
+    else if (loc.hybrid) location = `Hybrid - ${place}`.replace(/ - $/, ' ');
+
+    return normalize({
+      companySlug: slug,
+      company: p.company?.name || slug,
+      title: p.name || '',
+      department: p.department?.label || p.function?.label || '',
+      location,
+      description: stripHtml(description),
+      url: postingUrl,
+      postedAt: p.releasedDate || null,
+      salary: null, // SmartRecruiters has no structured salary; normalizer parses text
+      metadata: {
+        smartRecruitersId: p.id,
+        refNumber: p.refNumber || '',
+        function: p.function?.label || '',
+        experienceLevel: p.experienceLevel?.label || '',
+        typeOfEmployment: p.typeOfEmployment?.label || '',
+      },
+    }, 'smartrecruiters');
+  }));
+
+  return jobs;
+}
+
+/**
+ * Check if a company exists on SmartRecruiters.
+ * (HEAD isn't reliably supported on the postings endpoint, so use a
+ * minimal GET.)
+ */
+export async function hasSmartrecruiters(slug) {
+  try {
+    const resp = await fetch(`${BASE_URL}/${slug}/postings?limit=1`);
+    return resp.ok;
+  } catch {
+    return false;
+  }
+}