跳到正文
cccskills
免费在 GitHub 公开

radar

Registers the user on job platforms, configures alerts with profile keywords, sets up career site alerts (big tech + target companies), creates a Gmail filter to route alerts to a Job Alerts folder.

中文简介正在准备中。当前显示原文说明。

galiprandi/job-seeker星标 58(GitHub 58 + cccskills 0)

实测评分 未实测

查看安装方法

包含的文件(1)

  • SKILL.md9.8 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Radar

Trigger

Keyword: radar

The user says radar (or variants: "set up alerts", "register on platforms", "new platforms") and the registration + alert configuration + career site alerts + Gmail filter flow is triggered.

Purpose

Passive sourcing: platforms and career sites bring opportunities to the user without having to search manually. Alerts arrive in a Job Alerts folder in Gmail, and the news skill consumes them when the user says news.

Three alert sources:

  1. Job boards (Otta, Torre, Built In, etc.) — broad reach
  2. Big tech career sites (Google, Meta, Amazon, etc.) — high-value companies not in the 40 targets
  3. Target company ATS alerts (configured during targets flow registration) — deep monitoring of the 40 target companies

Flow

0. Pre-flight

  • Verify active Gmail session. If session closed → open browser with wrapper (see AGENTS.md "Browser session"): node .agents/skills/browser-automation/scripts/browser.js open <url> --headed (Gold Rule 5)
  • Browser: always use node .agents/skills/browser-automation/scripts/browser.js for open/close/goto. See AGENTS.md "Browser session" for details. Never call agent-browser open directly, never open Chrome directly
  • Read PLATFORMS.md "Alert Tracking" section to see which platforms need configuration
  • Read PROFILE.md to get keywords, seniority, location, preferences
  • Load active preferences (see memory skill):
    node scripts/db.js "SELECT category, key, value, confidence, source FROM preferences WHERE user_id = <user_id> AND status = 'active' ORDER BY category, key"
    
  • Load target companies (companies loaded from users.data.target_companies in DB, each {name, url, sector}). These are priority targets for alert configuration and platform prioritization:
    node scripts/db.js "SELECT data->'target_companies' AS target_companies FROM users WHERE id = <user_id>"
    

1. Register on platforms

For each unconfigured platform (column "Profile" = "—"):

  • Navigate to the platform
  • Login with Google when possible (preferred). If no Google login → open browser with wrapper (node .agents/skills/browser-automation/scripts/browser.js open <url> --headed) and ask user to login manually (Gold Rule 5)
  • Complete minimum profile:
    • First name, last name
    • Title / headline (from PROFILE.md)
    • Location (from PROFILE.md)
    • Seniority (from PROFILE.md)
    • Upload CV (CV path in DB or .env)
    • Preferences: remote, full-time, USD salary range
  • Mark "Profile" = "✅" in PLATFORMS.md

2. Configure alerts

For each platform with complete profile but no alerts:

  • Create alert with profile keywords (derived from profile.title, profile.skills, and job_preferences):
    • Use the user's primary role title, key skills, and seniority level
    • Examples (if profile is AI-focused): AI Architect, AI Strategy, LLM, Agent-First, AI Workflow
    • Examples (if profile is engineering leadership): Engineering Manager, Staff Engineer, Platform Engineer, Technical Lead
  • If the platform supports company-specific alerts or saved searches, configure alerts for target companies from the DB (40 companies: Nubank, dLocal, Mercado Libre, Globant, Ualá, BBVA, Santander Tecnología, Auth0, etc.). Group by sector if the platform allows it (Fintech, Banking, SaaS, IT Services)
  • Filters: remote only, full-time, senior/lead
  • Frequency: daily or weekly (depending on platform option)
  • Mark "Alerts" = "✅" in PLATFORMS.md with keywords used

3. Configure career site alerts (big tech + target companies)

Beyond job board alerts, configure alerts directly on career sites of high-value companies. These are companies not in the 40 target companies (those are handled by targets flow) but worth monitoring for roles matching the user's profile.

Big tech career sites with native alert features:

CompanyURLAlert featureNotes
Googlecareers.google.com"Save search" + email alertsSearch user's role + skills + location "Remote" or user's country
Metametacareers.com"Job alerts" signupSearch user's role + skills
Amazonamazon.jobs"Save search" + email alertsSearch user's role + equivalent Amazon title (e.g: SDM for eng manager)
Microsoftcareers.microsoft.com"Job alerts" signupSearch user's role + skills
Applejobs.apple.com"Save search" + alertsSearch user's role + skills
Netflixjobs.netflix.comNo native alerts. Monitor via Google AlertsSearch user's role + skills
Stripestripe.com/jobs"Job alerts" signupSearch user's role + skills
OpenAIopenai.com/careersNo native alerts. Monitor via Google AlertsSearch all roles
Anthropicanthropic.com/careersNo native alerts. Monitor via Google AlertsSearch all roles
Vercelvercel.com/careers"Job alerts" via AshbySearch user's role + skills
Cloudflarecloudflare.com/careers"Job alerts" signupSearch user's role + skills
Datadogcareers.datadog.com"Job alerts" via GreenhouseSearch user's role + skills
Snowflakecareers.snowflake.com"Job alerts" via WorkdaySearch user's role + skills

For each company with native alerts:

  • Navigate to the career site using node .agents/skills/browser-automation/scripts/browser.js goto <url>
  • Search with keywords derived from profile.title and profile.skills (the user's primary role + key skills)
  • Filter: Remote, and locations from job_preferences.location / job_preferences.timezones
  • Look for "Save search", "Create alert", "Job alerts", "Notify me" button
  • Subscribe with user's Gmail (so alerts route through the Gmail filter)
  • Set frequency: daily if available, weekly otherwise
  • Record in DB:
    node scripts/db.js "INSERT INTO company_registrations (user_id, company, region, sector, careers_url, ats_platform, registration_status, notes) VALUES (<user_id>, '<company>', 'big_tech', '<sector>', '<url>', '<ats>', 'alert_only', 'Alerts configured via radar') ON CONFLICT (user_id, company) DO UPDATE SET notes = EXCLUDED.notes, updated_at = NOW()" --write
    

For companies without native alerts (Netflix, OpenAI, Anthropic):

  • Create Google Alerts as backup:
    • Navigate to google.com/alerts
    • Create alert: site:<company-domain>/careers (AI OR "Engineering Manager" OR "AI Architect" OR LLM OR Agent)
    • Set frequency: daily
    • Set delivery: email to user's Gmail

4. Create Gmail filter

Once, when configuring the first platform:

  • Create label Job Alerts in Gmail
  • Create filter with domains of all configured platforms AND ATS alert senders:
    from:(otta.com OR torre.co OR weworkremotely.com OR builtin.com OR workatastartup.com
      OR greenhouse.io OR lever.co OR ashbyhq.com OR workable.com OR smartrecruiters.com
      OR teamtailor.com OR successfactors.com OR notifications@ashbyhq.com
      OR google.com OR amazon.jobs OR metacareers.com OR careers.microsoft.com
      OR jobs.apple.com OR stripe.com)
    → skip inbox → apply label: Job Alerts
    
  • If new platforms or career sites are added later, update the filter by adding the new domain
  • Mark "Gmail Filter" = "✅" in PLATFORMS.md

5. Persist

  • Update PLATFORMS.md "Alert Tracking" section with each platform's status
  • Update PROFILE.md "Configured alerts" section with keywords and platforms
  • Register in DB via db CLI (if exists): save alert status to users.data.platforms JSONB:
    node scripts/db.js "UPDATE users SET data = jsonb_set(data, '{platforms}', '<json>'::jsonb) WHERE id = <user_id>" --write
    

6. Report

  • Summary to user: "Registered on X platforms, Y alerts configured, Z career site alerts, Gmail filter created"
  • List next actions: "Run news to check alerts when they arrive"

Initial platforms (ADR-003)

PlatformURLGoogle loginNotes
Ottaotta.comYesCurated tech startups. Excellent remote + AI filtering
Torretorre.coYesLATAM-focused with AI matching. Remote-first
We Work Remotelyweworkremotely.comNoLargest remote job board. Email + password
Built Inbuiltin.comYesTech-focused with cities + remote. Serious companies
Y Combinatorworkatastartup.comYesYC startups exclusively. Many AI startups

Rules

  • Google login first. If not available → wrapper with --headed + manual login (Gold Rule 5)
  • Minimum profile: name, title, location, seniority, CV, remote/full-time preferences
  • Alert keywords come from PROFILE.md Search keywords
  • Gmail filter is created once and updated when adding platforms OR career site alert sources
  • Career site alerts are for big tech companies NOT in the 40 target companies. The 40 targets get their alerts configured during the targets flow registration
  • Google Alerts as backup for companies without native alert features (Netflix, OpenAI, Anthropic)
  • Persist status in PLATFORMS.md after each action
  • Don't apply — this skill is registration + alerts only. Applications go through apply or targets
  • Don't reply to messages — that goes through news
  • Single user (repo owner)

Learnings

  • 2026-07-31: An agent running radar couldn't identify target companies because the pre-flight didn't load users.data.target_companies. Fixed: added target_companies loading to pre-flight and company-specific alert configuration to step 2. The DB has target companies (loaded from users.data.target_companies in DB) with {name, url, sector} structure. See DATA.md for the canonical schema.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

apply

免费

Searches for jobs on LinkedIn, filters by profile Must-haves, applies via Easy Apply, registers each application in DB.

中文简介正在准备中。当前显示原文说明。

galiprandi/job-seeker582026年10月26日 更新

Control a dedicated browser via agent-browser (Vercel). Use when automating web apps, scraping authenticated sites, filling forms, or navigating SPAs. Do NOT use for desktop apps or API-only integrations.

中文简介正在准备中。当前显示原文说明。

galiprandi/job-seeker582026年10月26日 更新

daily

免费

Periodic routine that runs news, cleans up inbox and applies if there's no recent activity. Designed to run 1-2 times per day.

中文简介正在准备中。当前显示原文说明。

galiprandi/job-seeker582026年10月26日 更新

dashboard

免费

Opens a local web dashboard that visualizes the job application pipeline, funnel stats, recent messages, and target company status. The agent opens it at the end of a round so the user can visually review the pipeline.

中文简介正在准备中。当前显示原文说明。

galiprandi/job-seeker582026年10月26日 更新

db

免费

Safe Postgres CLI. Reads DATABASE_URL from .env, runs SQL, prints JSON. Read-only by default.

中文简介正在准备中。当前显示原文说明。

galiprandi/job-seeker582026年10月26日 更新

memory

免费

Autonomous user preference detection, storage and injection. The agent detects preferences from conversation, saves them to Postgres, and loads active ones at the start of every flow.

中文简介正在准备中。当前显示原文说明。

galiprandi/job-seeker582026年10月26日 更新

查看 galiprandi 的全部技能

报告此技能的问题