agentleFS
Mateus-Nogueira-GTMateus-Nogueira-GT/ai-job-search-brasil/.agents/skills/vagas-search/SKILL.md

vagas-search

Skill2 starsChanged 27 days agoMITView on GitHub

Use this skill to search Brazilian job listings on VAGAS.com.br, one of the oldest general job boards in Brazil, strong in administrative, finance, commercial, healthcare, industry and operations roles (and the source of many postings that show a salary range). Invoke when the user wants jobs in Brazil by keyword or city, or to read a specific VAGAS.com.br posting. Trigger phrases: vagas.com, vagas.com.br, vagas de emprego, emprego em <cidade>, procurar emprego, vagas administrativas, vagas financeiro, vagas com salário, faixa salarial, jobs in Brazil.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    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
  1. Very specific:

    Search output fields: id, title, company (often Confidencial), level (Júnior/Pleno/Sênior/...), location ("Cidade / UF"), remote, date, …

    line 66

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “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

VAGAS.com.br Search Skill

Busca vagas ao vivo no VAGAS.com.br. Sem autenticação, zero dependências de runtime.

Commands

Search

bun run .agents/skills/vagas-search/cli/src/cli.ts search --query "<texto>" [flags]
  • --query <text> / -q — required. Turned into the site's URL slug (analista financeiro → /vagas-de-analista-financeiro).
  • --city <cidade> / -c — e.g. "São Paulo", "Belo Horizonte" (→ -em-belo-horizonte).
  • --jobage <days> — posted within N days (client-side filter on the card date).
  • --remote — only cards whose location reads "100% Home Office".
  • --limit <n> / -n, --format json|table|plain.

Matching is literal and stem-sensitive: contabil finds 224 postings where contador finds 1. Prefer the root/area term (contabil, administrativo, logistica) and check meta.total — when it is much larger than meta.count, narrow with --city or a more specific term rather than assuming you saw everything.

No pagination. One query returns at most ~40 cards (the site does not paginate for anonymous clients). Use specific terms and --city rather than broad ones. There is no --page flag; passing one is rejected.

Detail

bun run .agents/skills/vagas-search/cli/src/cli.ts detail <id|url> [--format json|plain]

id is the numeric id from search (2840369, v2840369) or a vagas.com.br/vagas/v<id>/... URL. Returns contractType (e.g. CLT, PJ), salary (the posted range, e.g. R$ 6.000 a R$ 7.000, or null), benefits[], level, date, validThrough, full description, and isActive (false once validThrough has passed).

Examples

bun run .agents/skills/vagas-search/cli/src/cli.ts search -q "analista financeiro" -c "São Paulo" --jobage 14 --format table
bun run .agents/skills/vagas-search/cli/src/cli.ts search -q "engenheiro de produção" -c "Curitiba" --format table
bun run .agents/skills/vagas-search/cli/src/cli.ts detail v2840369 --format plain

Notes

  • Search output fields: id, title, company (often Confidencial), level (Júnior/Pleno/Sênior/...), location ("Cidade / UF"), remote, date, snippet, url.
  • robots.txt allows /vagas-de-* and /vagas/v*; it disallows /vagas/pesquisas, /api/, /v1/, which this CLI never calls.
  • Tech roles are thinner here than on Gupy/LinkedIn; VAGAS is most useful for non-tech and for salary signals.
  • Errors go to stderr as { "error": "...", "code": "..." }, exit code 1.

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.