agentleFS
LeadMagicLeadMagic/leadmagic-skills/skills/job-search/SKILL.md

job-search

Skill0 starsChanged 4 months agoMITView on GitHub

LeadMagic V3 jobs search via POST /v3/jobs/search — 46M+ open job postings with vector, facets, and deep modes. Use when searching job postings, mining hiring signals, building lists from who's hiring, handling jobs cursor pagination, or bulk-exporting postings.

  • Reads credentials
  • Sends data out

32 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use application-tracker, interview-prep and 3 more.

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.
  • xiding-codeSkill

    application-tracker

    Automatically log and track all job applications submitted. Use this skill after every application submission to record the details in a tracking spreadsheet and save relevant documents. Also trigger when the user asks "application status", "what have I applied to", "tracking", or wants to review their application history. Maintains a single source of truth for all job search activity.

    Also in 4 projects that use this

  • AnthropicSkill

    interview-prep

    Create structured interview plans with competency-based questions and scorecards. Trigger with "interview plan for", "interview questions for", "how should we interview", "scorecard for", or when the user is preparing to interview candidates.

    Also in 9 projects that use this

  • pepebot-spaceSkill

    job-application

    Write tailored cover letters and job applications using your CV and preferred style

    Also in 3 projects that use this

  • claude-office-skillsSkill

    company-research

    Conduct comprehensive company research and due diligence. Analyze business model, competitive landscape, management, and market position.

    Also in 3 projects that use this

  • claude-office-skillsSkill

    resume-tailor

    >

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 28 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never ration or narrow a query to save credits on an entitled plan — go broad.

    line 28
  2. Very specific:

    Never combine cursor with a nonzero offset — the API rejects it.

    line 73
  3. Very specific:

    Stop when next_cursor is null / has_more is false.

    line 74

“Common” is measured: kept by at least 6 in 10 of the 28 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

LeadMagic — Job search (V3)

Canonical endpoint: POST /v3/jobs/search — 46M+ open postings across corporate job boards. Aliases (same handler): /v3/jobs-search, /v3/job-search, /v2/jobs/search, /v1/jobs/search.

Docs: Job Search

Credit-free browse search on qualifying plans

On Professional and Ultimate, browse search on this endpoint costs no credits, at 5 req/s (Professional) or 10 req/s (Ultimate), within a fair-use cap (10M records/month, 13,333 searches/day) shared across People, Company and Jobs search — see leadmagic.io/unlimited. Other plans pay ~1 credit per returned job. Never ration or narrow a query to save credits on an entitled plan — go broad. Export is credit-metered on every plan.

Three modes, one endpoint

The body picks the mode; all three ride the unmetered plan entitlement:

ModeTriggerUse for
vector (default fast)nothing, or titles.vector: trueRanked browsing; semantic title match ("Head of Growth" also finds "VP Growth Marketing")
facetsincludeFacets: trueResults + aggregation counts (by country, seniority, industry) — filter UIs, market breakdowns
deepmode: "deep" or includeDescription: trueFull posting text — tool-mention mining, AI screening

preview / teaser / dryRun are reserved for the LeadMagic app UI — external keys are rejected.

curl -sS -X POST "https://api.leadmagic.io/v3/jobs/search" \
  -H "X-API-Key: $LEADMAGIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "titles": { "include": ["Sales Development Representative"], "vector": true },
    "location": { "countries": ["US"] },
    "postedWithin": 30,
    "limit": 25,
    "totalMode": "capped"
  }'

Filters (at least one required)

titles.include/exclude (10 each, vector flag) · companies.include/ids · location.countries/regions/states/cities/text · tags.include · occupationTaxonomy.level1/2/3 (names or IDs) · seniority · languages · jobTypeIds · industryIds · companyTypeIds · companySizeCodes · workModes (1–3) · salary.min_usd/max_usd · hasRemote · postedAfter/postedBefore (YYYY-MM-DD) or postedWithin (days, ≤365).

autoResolve: true (default) fuzzy-resolves friendly values — no exact IDs needed. totalMode: none | capped (default) | exact.

Cursor pagination

  • First page: send filters + limit (1–50, default 25). No cursor.
  • Response carries next_cursor (opaque string) and has_more.
  • Next page: same filters + "cursor": "<next_cursor>". Changing filters mid-cursor invalidates it.
  • Never combine cursor with a nonzero offset — the API rejects it.
  • Stop when next_cursor is null / has_more is false.
  • On Professional or Ultimate, paging is credit-free within the fair-use cap — respect the RPS.

Free helpers (0 credits, shape filters first)

HelperEndpoint
Resolve friendly values → IDsPOST /v3/jobs/search/resolve
AutocompleteGET /v3/jobs/search/{companies,titles,roles,tags,locations,occupation-taxonomy}
Filter catalogsGET /v3/jobs/search/catalogs
Dataset stats / freshnessGET /v3/jobs/search/stats

Bulk export (metered on all plans)

POST /v3/jobs/search/export — same filters, limit 1–5000 (default 100), descriptions on by default, no cursor (narrow filters instead), 1 credit per returned job.

Workflow

  1. Shape filters free: resolve or the GET catalogs.
  2. Scan broad in vector mode; add includeFacets to see the distribution.
  3. Drop to mode: "deep" only on the slice needing descriptions.
  4. Page with cursor until has_more is false.
  5. Need >50/page in one pull? Use export (metered) — tell the user the credit cost first.

When not to use this skill

  • People/contacts at a company → people-search
  • Company firmographics → company-search
  • Legacy V1 listing API (/v1/jobs/jobs-finder) → docs only; prefer V3

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.