radar
Skill136 starsChanged 3 days agoMITView on GitHub
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.
- Reads credentials
12 other projects use a version of this.
Adopted by
Most recently taken up by
- fullstackhouse/skillstheir own version, first seen Nov 15, 2026
- norrietaylor/distillerytheir own version, first seen Nov 1, 2026
- bekhruztbx/ai-creative-teamtheir own version, first seen Oct 25, 2026
- simota/agent-skillstheir own version, first seen Oct 23, 2026
- Samdev2420/radar-aitheir own version, first seen Oct 20, 2026
- coreyhaines31/makerskillstheir own version, first seen Oct 13, 2026
Used with
Projects with it also use decide.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
dirienSkilldecide
Three-agent adversarial debate protocol for strategic decisions. Two advocates steelman opposing positions while a moderator identifies risks and synthesizes a binding consensus. Use when choosing between alternatives, evaluating tradeoffs, or making high-stakes decisions.
Also in 3 projects that use this
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- coreyhaines31/makerskills★ 916same name
- simota/agent-skills★ 99same name
- norrietaylor/distillery★ 25same name
- bekhruztbx/ai-creative-team★ 18same name
- fullstackhouse/skills★ 1same name
- mralabs/radar★ 1same name
- Samdev2420/radar-ai★ 1same name
- ScienceLiveHub/forrt-replication-template★ 1same name
- brianshepardpss/plugin-studio★ 0same name
- lavine888/career-alpha★ 0same name
2 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- acp-connectorSkill
- applySkill
- browser-automationSkill
- dailySkill
- dashboardSkill
- dbSkill
- memorySkill
- newsSkill
- onboardingSkill
- polishSkill
- profileSkill
- referralsSkill
- strategySkill
- targetsSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 60
Use the user's primary role title, key skills, and seniority level
- Very specific: line 152
Google login first: If not available → wrapper with --headed + manual login (Gold Rule 5)
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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:
- Job boards (Otta, Torre, Built In, etc.) — broad reach
- Big tech career sites (Google, Meta, Amazon, etc.) — high-value companies not in the 40 targets
- Target company ATS alerts (configured during
targetsflow 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.jsfor open/close/goto. See AGENTS.md "Browser session" for details. Never callagent-browser opendirectly, never open Chrome directly - Read
PLATFORMS.md"Alert Tracking" section to see which platforms need configuration - Read
PROFILE.mdto get keywords, seniority, location, preferences - Load active preferences (see
memoryskill):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, andjob_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:
| Company | URL | Alert feature | Notes |
| careers.google.com | "Save search" + email alerts | Search user's role + skills + location "Remote" or user's country | |
| Meta | metacareers.com | "Job alerts" signup | Search user's role + skills |
| Amazon | amazon.jobs | "Save search" + email alerts | Search user's role + equivalent Amazon title (e.g: SDM for eng manager) |
| Microsoft | careers.microsoft.com | "Job alerts" signup | Search user's role + skills |
| Apple | jobs.apple.com | "Save search" + alerts | Search user's role + skills |
| Netflix | jobs.netflix.com | No native alerts. Monitor via Google Alerts | Search user's role + skills |
| Stripe | stripe.com/jobs | "Job alerts" signup | Search user's role + skills |
| OpenAI | openai.com/careers | No native alerts. Monitor via Google Alerts | Search all roles |
| Anthropic | anthropic.com/careers | No native alerts. Monitor via Google Alerts | Search all roles |
| Vercel | vercel.com/careers | "Job alerts" via Ashby | Search user's role + skills |
| Cloudflare | cloudflare.com/careers | "Job alerts" signup | Search user's role + skills |
| Datadog | careers.datadog.com | "Job alerts" via Greenhouse | Search user's role + skills |
| Snowflake | careers.snowflake.com | "Job alerts" via Workday | Search 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.titleandprofile.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 Alertsin 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.platformsJSONB: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
newsto check alerts when they arrive"
Initial platforms (ADR-003)
| Platform | URL | Google login | Notes |
| Otta | otta.com | Yes | Curated tech startups. Excellent remote + AI filtering |
| Torre | torre.co | Yes | LATAM-focused with AI matching. Remote-first |
| We Work Remotely | weworkremotely.com | No | Largest remote job board. Email + password |
| Built In | builtin.com | Yes | Tech-focused with cities + remote. Serious companies |
| Y Combinator | workatastartup.com | Yes | YC 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
targetsflow 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
applyortargets - 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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

