job-market-intel

What this skill does

# Job Market Intel — Live Salary & Demand Data Before You Negotiate

You have access to the TinyFish CLI (`tinyfish`), a tool that runs browser automations from the terminal using natural language goals. This skill deploys agents across LinkedIn, Indeed, and Glassdoor in parallel, navigates login walls and search forms, and synthesizes live job listings into a single market snapshot.

---

## Pre-flight Check (REQUIRED)

Before making any TinyFish call, always run BOTH checks:

**1. CLI installed?**

PowerShell:
```powershell
Get-Command tinyfish; tinyfish --version
```
bash/zsh:
```bash
which tinyfish && tinyfish --version || echo "TINYFISH_CLI_NOT_INSTALLED"
```

If not installed, stop and tell the user:
> Install the TinyFish CLI: `npm install -g @tiny-fish/cli`

**2. Authenticated?**

```bash
tinyfish auth status
```

If not authenticated, stop and tell the user:

> You need a TinyFish API key. Get one at: https://agent.tinyfish.ai/api-keys
>
> Then authenticate:
>
> **Option 1 — CLI login (interactive):**
> ```
> tinyfish auth login
> ```
>
> **Option 2 — PowerShell (current session only):**
> ```powershell
> $env:TINYFISH_API_KEY="your-api-key-here"
> ```
>
> **Option 3 — PowerShell (persist across sessions):**
> ```powershell
> [System.Environment]::SetEnvironmentVariable("TINYFISH_API_KEY", "your-api-key-here", "User")
> ```
> Then close and reopen PowerShell for it to take effect.
>
> **Option 4 — bash/zsh (Mac/Linux):**
> ```bash
> export TINYFISH_API_KEY="your-api-key-here"
> ```
>
> **Option 5 — Claude Code settings:** Add to `~/.claude/settings.local.json`:
> ```json
> {
>   "env": {
>     "TINYFISH_API_KEY": "your-api-key-here"
>   }
> }
> ```

Do NOT proceed until both checks pass.

---

## What This Skill Does

Given a job title and tech stack (e.g. *"Senior Backend Engineer, Go + Kubernetes"*), this skill:

1. Searches **LinkedIn Jobs** for matching postings, extracting salary ranges, seniority levels, and company names
2. Searches **Indeed** for the same role, pulling compensation data and required skills from job descriptions
3. Searches **Glassdoor** for salary data, company ratings, and remote/hybrid/onsite ratios

It then synthesizes all three sources into a structured market snapshot: what the role actually pays, which skills show up most, who is hiring, and whether remote is realistic.

---

## Core Command

```bash
tinyfish agent run --url <url> "<goal>"
```

### Flags

| Flag | Purpose |
|------|---------|
| `--url <url>` | Target website URL |
| `--sync` | Wait for full result before returning |
| `--async` | Submit and return immediately |
| `--pretty` | Human-readable formatted output |

---

## Step-by-Step Workflow

### Inputs Required

Before running, collect from the user:
- **Job title** — e.g. `Senior Backend Engineer`, `ML Engineer`, `Staff iOS Developer`
- **Tech stack** — e.g. `Go Kubernetes`, `Python PyTorch`, `Swift SwiftUI`
- **Location** (optional) — e.g. `San Francisco`, `Remote`, `London`

Derive URL-encoded search strings from these inputs for each platform.

---

### Step 1 — Search LinkedIn Jobs

```bash
tinyfish agent run --sync \
  --url "https://www.linkedin.com/jobs/search/?keywords=<title+stack>&location=<location>&f_TPR=r604800" \
  "Extract the top 10 job listings as JSON: [{\"title\": str, \"company\": str, \"location\": str, \"salary_range\": str, \"posted_date\": str, \"remote_type\": str, \"url\": str}]. If salary is not shown, set salary_range to null. The f_TPR=r604800 filter means postings from the last 7 days — note the recency in each result."
```

**Example for Senior Backend Engineer, Go + Kubernetes:**
```bash
tinyfish agent run --sync \
  --url "https://www.linkedin.com/jobs/search/?keywords=Senior+Backend+Engineer+Go+Kubernetes&location=Remote&f_TPR=r604800" \
  "Extract the top 10 job listings as JSON: [{\"title\": str, \"company\": str, \"location\": str, \"salary_range\": str, \"posted_date\": str, \"remote_type\": str, \"url\": str}]. Set salary_range to null if not listed."
```

---

### Step 2 — Search Indeed

```bash
tinyfish agent run --sync \
  --url "https://www.indeed.com/jobs?q=<title+stack>&l=<location>&fromage=7&sort=date" \
  "Extract the top 10 job listings as JSON: [{\"title\": str, \"company\": str, \"location\": str, \"salary_range\": str, \"required_skills\": [str], \"posted_date\": str, \"remote_type\": str, \"url\": str}]. Pull required_skills from the snippet or description preview shown in results. Set salary_range to null if not listed."
```

**Example:**
```bash
tinyfish agent run --sync \
  --url "https://www.indeed.com/jobs?q=Senior+Backend+Engineer+Go+Kubernetes&l=Remote&fromage=7&sort=date" \
  "Extract the top 10 job listings as JSON: [{\"title\": str, \"company\": str, \"location\": str, \"salary_range\": str, \"required_skills\": [str], \"posted_date\": str, \"remote_type\": str, \"url\": str}]. Pull required_skills from visible description snippets."
```

---

### Step 3 — Search Glassdoor

```bash
tinyfish agent run --sync \
  --url "https://www.glassdoor.com/Job/jobs.htm?sc.keyword=<title+stack>&locT=N&locId=1&jobType=all&fromAge=7" \
  "Extract the top 10 job listings as JSON: [{\"title\": str, \"company\": str, \"company_rating\": str, \"salary_range\": str, \"location\": str, \"remote_type\": str, \"posted_date\": str, \"url\": str}]. Include company_rating (out of 5) if shown. Set salary_range to null if not listed."
```

**Example:**
```bash
tinyfish agent run --sync \
  --url "https://www.glassdoor.com/Job/jobs.htm?sc.keyword=Senior+Backend+Engineer+Go+Kubernetes&locT=N&locId=1&jobType=all&fromAge=7" \
  "Extract the top 10 job listings as JSON: [{\"title\": str, \"company\": str, \"company_rating\": str, \"salary_range\": str, \"location\": str, \"remote_type\": str, \"posted_date\": str, \"url\": str}]."
```

---

## Parallel Execution

All three steps are independent — run them simultaneously. Do NOT wait for LinkedIn before starting Indeed or Glassdoor.

**bash/zsh — Parallel calls (Mac/Linux):**
```bash
tinyfish agent run --sync \
  --url "https://www.linkedin.com/jobs/search/?keywords=<title+stack>&location=<location>&f_TPR=r604800" \
  "Extract top 10 listings as JSON: [{\"title\": str, \"company\": str, \"location\": str, \"salary_range\": str, \"posted_date\": str, \"remote_type\": str, \"url\": str}]" \
  > /tmp/linkedin_results.json &

tinyfish agent run --sync \
  --url "https://www.indeed.com/jobs?q=<title+stack>&l=<location>&fromage=7&sort=date" \
  "Extract top 10 listings as JSON: [{\"title\": str, \"company\": str, \"location\": str, \"salary_range\": str, \"required_skills\": [str], \"posted_date\": str, \"remote_type\": str, \"url\": str}]" \
  > /tmp/indeed_results.json &

tinyfish agent run --sync \
  --url "https://www.glassdoor.com/Job/jobs.htm?sc.keyword=<title+stack>&locT=N&locId=1&jobType=all&fromAge=7" \
  "Extract top 10 listings as JSON: [{\"title\": str, \"company\": str, \"company_rating\": str, \"salary_range\": str, \"location\": str, \"remote_type\": str, \"posted_date\": str, \"url\": str}]" \
  > /tmp/glassdoor_results.json &

wait
```

**PowerShell — Parallel calls using Start-Job / Wait-Job:**
```powershell
$linkedinJob = Start-Job {
    tinyfish agent run --sync `
      --url "https://www.linkedin.com/jobs/search/?keywords=<title+stack>&location=<location>&f_TPR=r604800" `
      "Extract top 10 listings as JSON: [{`"title`": str, `"company`": str, `"location`": str, `"salary_range`": str, `"posted_date`": str, `"remote_type`": str, `"url`": str}]"
}

$indeedJob = Start-Job {
    tinyfish agent run --sync `
      --url "https://www.indeed.com/jobs?q=<title+stack>&l=<location>&fromage=7&sort=date" `
      "Extract top 10 listings as JSON: [{`"title`": str, `"company`": str, `"location`": str, `"salary_range`": str, `"required_skills`": [str], `"posted_date`": str, `"remote_type`": str, `"url`": str}]"
}

$glassdoorJob = Start-Job {
    tinyfish agent run --sync `
      --url "https://www.glassdoor.com/J