py/ai-job-search
1
0
Fork 0
mirror of https://github.com/MadsLorentzen/ai-job-search.git synced 2026-09-17 08:36:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

Use CLI detail in scraper Step 2; broaden skill description (#102)

Browse Source 
Follow-up to #65 feedback after #52 merged CLI-first search. Step 2 now
uses each portal's detail command for CLI-sourced jobs (WebFetch only for
WebSearch fallbacks). Skill description reflects market-agnostic portal
CLIs instead of Danish-only wording.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Yash Rajeshbhai Darji
2026-07-09 21:12:15 +02:00
committed by GitHub
co-authored by Cursor
parent 6e92a4358a
commit 3bb4688e5d
1 changed files with 22 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.claude/skills/job-scraper/SKILL.md
+22 -9
View File
@@ -1,8 +1,10 @@
---
name: scrape
description: >
Scrapes Danish job sites for new positions matching your profile. Deduplicates across runs.
Triggers on: job scrape, find jobs, search jobs, new jobs, job search, scrape jobs, /scrape
Finds new job postings matching your profile via installed portal-search CLIs
(LinkedIn, local job boards, and any skills added with /add-portal). Deduplicates
across runs. Triggers on: job scrape, find jobs, search jobs, new jobs, job search,
scrape jobs, /scrape
allowed-tools: Read, Write, Edit, Glob, Grep, Bash(bun --version), Bash(bun run .agents/skills/*/cli/src/cli.ts *), WebFetch, WebSearch, Agent, AskUserQuestion
---
@@ -12,7 +14,10 @@ allowed-tools: Read, Write, Edit, Glob, Grep, Bash(bun --version), Bash(bun run
## How It Works
This skill searches multiple Danish job sites using targeted queries based on your profile, deduplicates against previously seen jobs and the application tracker, and presents new matches with a quick fit assessment.
This skill searches job portals using the **installed portal-search CLIs** in
`.agents/skills/` (plus WebSearch as a fallback), using queries from your profile.
It deduplicates against previously seen jobs and the application tracker, and
presents new matches with a quick fit assessment.
## Invocation
@@ -62,7 +67,7 @@ For each installed portal skill:
4. Cap results to ~20 per call using the portal's limit flag.
5. Use `--format json` for machine-readable output.
Run all portal CLI calls in parallel where possible using the Agent tool. Collect all `results` arrays into a single pool for Step 2.
Run all portal CLI calls in parallel where possible using the Agent tool. Collect all `results` arrays into a single pool for Step 2, keeping each result tagged with its source portal skill (for Step 2 `detail` lookups).
If a CLI tool exits with a non-zero code, log the error message and continue — do not abort the whole search.
@@ -78,8 +83,16 @@ Use the site-specific query strings from `search-queries.md` directly as WebSear
### Step 2: Fetch & Parse
For each promising result from Step 1:
- Use `WebFetch` to retrieve the job posting page
- Extract: **job title**, **company**, **location**, **posting date** (or "recent"), **URL**, **key requirements** (brief), **application deadline** (if listed)
**From CLI results:** Search output already includes title, company, location, date,
and URL. For jobs worth a deeper look, fetch full detail with that portal's `detail`
command (see its SKILL.md — do not guess flags) to extract **key requirements**,
**application deadline**, and a brief description snippet.
**From WebSearch results:** Use `WebFetch` on the posting URL and extract the same
fields manually.
For every candidate:
- Skip if the URL or company+title combo already exists in `seen_jobs.json`
- Skip if the company+role already appears in `job_search_tracker.csv`
@@ -145,9 +158,9 @@ If the user decides to apply to any job, add a row to `job_search_tracker.csv`.
## Important Rules
1. **Never fabricate job postings.** Only present jobs found via actual WebSearch/WebFetch results.
1. **Never fabricate job postings.** Only present jobs from actual CLI search/detail output or WebSearch/WebFetch results.
2. **Respect deduplication.** Always check seen_jobs.json AND job_search_tracker.csv before presenting.
3. **Focus on configured geographic area.** Skip jobs that require relocation or are clearly outside commute range.
4. **Only open positions.** Skip postings with expired deadlines or those marked as closed.
5. **Be efficient with WebFetch.** Don't fetch every search result - use titles and snippets to pre-filter before fetching.
6. **Parallel searches.** Use the Agent tool or parallel WebSearch calls to speed up the search phase.
5. **Be efficient with detail fetches.** Don't run `detail` or WebFetch on every search hit — pre-filter by title/snippet, then fetch only promising matches.
6. **Parallel searches.** Run portal CLI searches in parallel; use WebSearch only for gaps the CLIs don't cover.