agentleFS
suraj-davariyasuraj-davariya/ai-job-search/.agents/skills/example-portal/SKILL.md

example-portal

Skill22 starsChanged 5 months agoMITView on GitHub

TEMPLATE — a CareerForge example job-portal adapter (ADR-0004). Copy this directory to add structured search for a real job board. Not auto-loaded by Claude Code.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Add the portal to your search-queries.md so job-scraper knows to use it.

    line 59
  2. Very specific:

    Keep dependencies minimal.

    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

Example Portal Adapter — TEMPLATE (copy me)

⚠️ This is a template, not a working portal. Its cli/ returns clearly-labelled example data so you can run it end-to-end and see the contract. To add a real portal, copy this whole directory to .agents/skills/<portal-name>/ and implement real fetching in cli/index.ts.

Why .agents/skills/ and not .claude/skills/?

Per ADR-0004, structured portal adapters are a Plane-2 extension: each portal is a self-contained CLI tool that the country-agnostic job-scraper skill calls out to, with web search (site:<portal>) as the universal fallback. They live under .agents/skills/ deliberately — that path is not the Claude Code skill auto-load directory (.claude/skills/), so an adapter is invoked as a CLI (via bun run), never silently activated as a chat skill. This keeps the core framework clean and lets any market contribute an adapter without changing core code.

Directory contract (ADR-0004)

.agents/skills/<portal-name>/
├── SKILL.md           # this file — trigger keywords + contract
├── cli/
│   ├── package.json   # dependencies + start script (Bun/TypeScript)
│   └── index.ts       # CLI entry point implementing the contract below
└── url-reference.md   # optional — the portal's search-URL patterns

CLI contract

RuntimeBun (TypeScript). node/npx tsx also work for this template.
InputCLI flags: --keywords "<terms>", --location "<place>", --date-range <days>
OutputA JSON array on stdout, one object per posting: { title, company, location, url, date, snippet }
Exit code0 on success (even with zero results — emit []), 1 on error (message on stderr)

The job-scraper skill runs the adapter like:

bun run .agents/skills/<portal-name>/cli/index.ts \
  --keywords "data engineer" --location "Remote" --date-range 14

…then parses the JSON array, dedupes against seen_jobs.json, quick-rates fit, and presents results exactly as it does for web-search hits.

How to add a real portal

  1. Copy this directory to .agents/skills/<portal-name>/.
  2. In cli/index.ts, replace the example data with a real fetch (the portal's public search/API, or HTML parsing) that honours the input/output/exit-code contract.
  3. Record the portal's search-URL patterns in url-reference.md.
  4. Add the portal to your search-queries.md so job-scraper knows to use it.
  5. No core change is required — that is the whole point of ADR-0004.

Constraints

  • No fabrication (ARCH-0007): a real adapter must return only postings it actually found, with real URLs. This template clearly labels its output as example data.
  • Keep dependencies minimal; each adapter installs independently (bun install).

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.