agentleFS
fn-jakubkarpfn-jakubkarp/crocthejob/.claude/skills/job-scraper/SKILL.md

scrape

Skill0 starsChanged 3 months agoMITView on GitHub

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

36 other projects use a version of this, 5 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use ios-sync, setup-gbrain and 8 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.
  • Saqlain-811Skill

    ios-sync

    Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)

    Also in 6 projects that use this

  • ShreyRaviSkill

    setup-gbrain

    Set up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy. One command from zero to "gbrain is running, and this agent can call it." Use when: "setup gbrain", "connect gbrain", "start gbrain", "install gbrain", "configure gbrain for this machine". (gstack)

    Also in 8 projects that use this

  • ShreyRaviSkill

    plan-tune

    Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). Review which AskUserQuestion prompts fire across gstack skills, set per-question preferences (never-ask / always-ask / ask-only-for-one-way), inspect the dual-track profile (what you declared vs what your behavior suggests), and enable/disable question tuning. Conversational interface — no CLI syntax required.

    Also in 10 projects that use this

  • Saqlain-811Skill

    ios-clean

    Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)

    Also in 5 projects that use this

  • timurgaleevSkill

    document-generate

    Generate missing docs for a feature, module or project as tutorials, how-tos, reference and explanation.

    Also in 7 projects that use this

  • bastosSkill

    ios-design-review

    Review iOS app UI/UX design quality using Apple's design principles and the Liquid Glass-era design language from WWDC25/26. Use when asked for a design review, UX critique, visual design assessment, or evaluation of an app's interface quality, design intent, alignment with the new Apple design system, or usability. Triggers: "design review", "UX review", "visual design critique", "review the UI", "does this design work", "evaluate this interface", "design feedback", "Liquid Glass review".

    Also in 5 projects that use this

  • +3 more from ShreyRavi
  • +1 more from Saqlain-811

The file

Show its rules and text

We split this skill into the rules it gives an agent

23 rules. 0 are common, 7 are distinctive, and 16 are very specific to this project.

  • 0

    Common

    Most of the 29 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 16

    Very specific

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

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

    Read data/jobs.json (create if missing - start with {"seen": {}})

    line 41
  2. Very specific:

    Read search-queries.md (this directory) for the search strategy

    line 43
  3. Very specific:

    Read search-queries.md (this directory) for the search strategy.

    line 47
  4. Distinctive:

    If this fails (bun not installed), skip to 1c (WebSearch fallback) for all portals and note the fallback in the Step 5 output.

    line 57
  5. Very specific:

    Read its SKILL.md to find the correct bun run … invocation and supported flags.

    line 67
  6. Very specific:

    Use --format json for machine-readable output.

    line 71
  7. Very specific:

    Run all portal CLI calls in parallel where possible using the Agent tool.

    line 73
  8. Distinctive:

    If a CLI tool exits with a non-zero code, log the error message and continue — do not abort the whole search.

    line 75
  9. Distinctive:

    When bun is unavailable (Step 1a failed)

    line 82
  10. Very specific:

    Use the site-specific query strings from search-queries.md directly as WebSearch queries for these portals.

    line 84
  11. Very specific:

    From CLI results: Search output already includes title, company, location, date, and URL.

    line 90
  12. Very specific:

    From WebSearch results: Use WebFetch on the posting URL and extract the same fields manually.

    line 95
  13. Very specific:

    Every posting a detail or WebFetch call returned in full gets written to documents/postings/<company-slug>-<role-slug>.md, and the entry …

    line 104
  14. Very specific:

    Write the text the fetch returned, never a summary and never a reconstruction.

    line 109
  15. Very specific:

    Add ALL fetched jobs (new and skipped) to data/jobs.json with structure:

    line 143
  16. Distinctive:

    Only present jobs NOT already in the seen list or tracker.

    line 183
  17. Very specific:

    Use a short keyword drawn from the posting's title for <role keyword> - e.g.

    line 204
  18. Distinctive:

    If the user picks a number, invoke the job-application-assistant skill workflow (fit evaluation first, then the tailored CV if approved).

    line 270
  19. Very specific:

    If the user decides to apply to any job, set that entry's status to applied and its applied_date in data/jobs.json.

    line 276
  20. Distinctive:

    Never fabricate job postings: Only present jobs from actual CLI search/detail output or WebSearch/WebFetch results.

    line 285
  21. Very specific:

    Respect deduplication: Always check data/jobs.json before presenting - it holds every posting ever seen and every application ever made.

    line 286
  22. Very specific:

    Be efficient with detail fetches: Don't run detail or WebFetch on every search hit — pre-filter by title/snippet, then fetch only promising …

    line 289
  23. Distinctive:

    Parallel searches: Run portal CLI searches in parallel.

    line 290

“Common” is measured: kept by at least 6 in 10 of the 29 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

Job Scraper


How It Works

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

The user triggers this skill by saying things like:

  • "Find new jobs"
  • "Scrape for jobs"
  • "Any new positions?"
  • "/scrape"

Optional arguments:

  • A focus area, e.g. "/scrape data science" or "/scrape geophysics"
  • "broad" to run all search categories, e.g. "/scrape broad"
  • "health" to run the portal health check only (Step 4.75), without searching, deduplicating, or presenting jobs - e.g. "/scrape health", or "/scrape health linkedin" to probe one portal even if disabled

Execution Steps

Step 0: Load State

  1. Read data/jobs.json (create if missing - start with {"seen": {}})
  2. From the same file, extract the already-applied companies+roles: every entry whose status is applied, screening, tech_interview, offer or rejected
  3. Read search-queries.md (this directory) for the search strategy

Step 1: Search

Read search-queries.md (this directory) for the search strategy. By default, run the top 3 priority query categories. If the user said "broad", run all categories. If the user specified a focus area (e.g. "data science"), prioritize queries from that category.

Use the installed CLI tools as the primary search mechanism. Fall back to WebSearch only for portals that do not have a CLI skill, or if bun is unavailable on the system.

1a. Check bun availability

bun --version

If this fails (bun not installed), skip to 1c (WebSearch fallback) for all portals and note the fallback in the Step 5 output.

1b. Run CLI tools (primary — run these in parallel where possible)

Discover all installed portal CLI skills by reading every SKILL.md found under .agents/skills/*/SKILL.md. Each file documents that portal's exact CLI flags and usage examples. Use each portal's own documented interface — do not guess flags. This approach automatically includes any new portals added via /add-portal without requiring changes to this file.

Honor the enabled toggle. A portal is enabled unless its SKILL.md frontmatter sets enabled: false (a missing key means enabled — the default). Skip each disabled portal and record it for the Step 5 summary. A fork can thus keep a portal installed but sit out a run without deleting its directory.

For each enabled portal skill:

  1. Read its SKILL.md to find the correct bun run … invocation and supported flags.
  2. Translate the query terms from search-queries.md into that portal's flag format (e.g. --key, --search-string, --query, filter codes — whatever the portal's SKILL.md specifies).
  3. Scope to the last 14 days using the portal's supported recency flag (--jobage, --since <YYYY-MM-DD>, --order PublicationDate, etc. — as documented per portal).
  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, 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.

1c. WebSearch fallback

Use WebSearch for:

  • Portals listed in search-queries.md that do not have a corresponding directory under .agents/skills/
  • Any portal whose CLI fails at runtime
  • When bun is unavailable (Step 1a failed)

Use the site-specific query strings from search-queries.md directly as WebSearch queries for these portals.

Step 2: Fetch & Parse

For each promising result from Step 1:

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 data/jobs.json
  • Skip if the company+role is already applied to (see Step 0.2)

Step 2.25: Keep the Posting Text

Every posting a detail or WebFetch call returned in full gets written to documents/postings/<company-slug>-<role-slug>.md, and the entry records that path in posting_file (Step 4). Listings expire; this is the copy that survives, and the board reads it there. If the filename is taken by a different posting, append -2, -3.

Write the text the fetch returned, never a summary and never a reconstruction. A posting that could not be fetched in full gets no file and no posting_file.

# <Title> - <Company>

<location> · <work mode> · <salary or "no salary stated">
Source: <url>
Saved: YYYY-MM-DD from <portal>

---

<the description, verbatim>

Save nothing for a posting fetched only as a search-result snippet: half a posting under a filename that promises the whole one is worse than the link alone.

Step 2.5: Mass-Posting Detection (within this run)

A distribution pattern worth flagging to the user as a caution signal, not as an accusation against the employer - it describes how a listing is being distributed, not a verdict on whether the company is legitimate. It alone proves nothing is wrong (companies do legitimately hire the same role across several cities); flag it so the user can factor it in when deciding whether to invest time, don't downgrade fit or silently exclude the result because of it.

If two or more results in this run's pool (from the same company, or sharing the same req/job ID visible in the URL or title) have substantially the same description and differ only in city/location/title, don't present them as separate rows. Consolidate into a single row and note the spread, e.g. "posted identically across 6 cities (BR, MX, GT)".

Step 3: Quick Fit Assessment

For each new job, do a rapid fit check (NOT the full evaluation from 04-job-evaluation.md - just a quick signal):

  • High match: Role directly involves your core skills
  • Medium match: Role is adjacent to your experience
  • Low match: Role requires significant skills you lack

Step 4: Deduplicate & Store

  1. Add ALL fetched jobs (new and skipped) to data/jobs.json with structure:
{
  "seen": {
    "<url_or_company_title_key>": {
      "title": "...",
      "company": "...",
      "url": "...",
      "first_seen": "YYYY-MM-DD",
      "fit": "high/medium/low",
      "status": "new/skipped/evaluated/ranked/expired",
      "portal": "<source portal skill, e.g. justjoinit-search>",
      "posting_file": "documents/postings/<company-slug>-<role-slug>.md"
    }
  }
}

posting_file is the Step 2.25 copy, repo-relative. Absent means nothing was saved - the board's only existence check, so never write the field without writing the file.

The portal field records which CLI skill produced the job (results are already tagged per portal in Step 1b - persist that tag here). Entries written before this field existed lack it; the health check (Step 4.75) attributes those by matching the URL's domain against each portal's base URL, so do not backfill.

/rank extends this schema additively: ranked entries also carry rank_score (0–100 overall score), rank_verdict (fit band, e.g. "strong fit"), and rank_date (ISO date of ranking). The status field is set to "ranked". Do not drop any of these fields when re-writing entries.

The kanban board (studio/apps/web/) writes two fields of its own on entries the user moves by hand: status, and notes for anything they typed about the posting. One status is the board's alone - dismissed, meaning the user read the posting and ruled it out themselves, with the reason in notes. Treat those entries as closed: they stay in the dedup set like any other seen entry, /rank never re-scores them, and nothing here overwrites their notes. status in the schema above is therefore one of new/skipped/evaluated/ranked/expired/dismissed, plus the application stages the board sets (applied/screening/tech_interview/offer/rejected).

ghosted and withdrawn are no longer statuses. Every way an application ends without an offer is now status: "rejected", and which way is in the outcome array. Writing either old value still works - the board translates it on read and on write - but write rejected plus the tag instead. There are only ten statuses now, not twelve.

Six more fields belong to the board alone. Carry them through untouched and never write them here:

FieldWhere it livesWhat it means
next_idfile root, not an entryThe next id to hand out. Leave it alone; if it goes missing the board recomputes it from the highest id present.
idinteger, first key of an entryThe role's stable number, the handle the user refers to a posting by (#153). Assigned once by the board, never reused, never renumbered. Do not invent one for a new entry - write the entry without an id and the board backfills it on next load.
status_dateISO dateThe day status last changed, which is how the board ages a live application.
applied_dateISO dateThe day the application actually went out, set by hand on the board. Separate from status_date, which is only ever the day of the change: an application logged after the fact needs to say when it happened.
duplicate_ofkey, or nullThe entry this one is a copy of, so the board can hide it. Explicit null means the user checked and ruled it standalone - absent and null are not the same, so never replace one with the other.
outcomearray of tags, next to statusWhy a rejected application ended, and combinable: ghosted, withdrawn, on_hold, failed_screening, failed_tech, failed_behavioural. ["ghosted", "failed_tech"] is a real entry - they went quiet after the technical. Absent or empty means they simply said no; there is deliberately no tag for that, so never add one.
  1. Only present jobs NOT already in the seen list or tracker.
  2. Compare URLs in their canonical form when deduplicating. Portals hand the same posting back under tracking parameters and locale prefixes, and treating those as distinct is what produced ~7 twin entries in this file: nofluffjobs.com/pl/job/qa-test-engineer-merit-remote and nofluffjobs.com/job/qa-test-engineer-merit-remote?utm_source=freehire.me are one Merit listing. Before comparing a fetched URL against data/jobs.json, lowercase the host, drop a leading www., drop a leading language segment (/pl, /en, …), strip a trailing slash, and remove utm_* and other referrer parameters (ref, source, src, fbclid, gclid, trk*). packages/jobs-data/dupes.ts holds the same rule in code if you need the exact list. A match means the posting is already seen - do not add a second entry.

Step 4.5: Generate Referral Contact Links (High & Medium Fit Only)

For every job from this run with fit of high or medium (skip low-fit jobs), build two LinkedIn people-search URLs so the user can find a recruiter or team member to reach out to for a referral or a warm intro. This is deliberately a link-generation step, not an automated lookup: no scraping, no third-party API, zero runtime dependencies or credentials required.

A. Recruiters / Talent Acquisition (the referral path)

https://www.linkedin.com/search/results/people/?keywords=<url-encoded "<Company Name> recruiter">&origin=GLOBAL_SEARCH_HEADER

B. Role/team peers (informational-outreach / warm-intro path)

https://www.linkedin.com/search/results/people/?keywords=<url-encoded "<Company Name> <role keyword>">&origin=GLOBAL_SEARCH_HEADER

Use a short keyword drawn from the posting's title for <role keyword> - e.g. a posting titled "AI Program Manager" becomes "<Company Name> AI Program Manager".

Both links are for the user to open and browse themselves - never fetch or scrape the LinkedIn people-search result pages programmatically. Never fabricate contacts or claim a specific person was found; these are search links, not results.

Step 4.75: Portal Health Check

Scraper-based portal CLIs rot silently: when a portal changes its markup, the parser usually exits 0 with zero results or with null/garbled fields, and the Step 1c fallback never fires because it only triggers on hard failure. This step catches that from evidence the run already holds.

Free pass (no extra requests). For each enabled portal that ran in Step 1b:

  • Degraded scan: inspect the results it returned this run. Flags: company null or empty on every result, empty titles, undecoded entities (&amp;) or HTML fragments in titles, URLs that do not point at the portal. Any of these means the parser is half-working and /scrape is silently collecting junk.
  • Yield history: if the portal returned zero results across all of this run's queries, check whether data/jobs.json holds prior entries from it (via the portal field, or by matching URL domains for entries predating the field). A portal that produced jobs on earlier runs and produces nothing now is suspect - the same queries worked before.

Escalation (bounded, on suspicion only). A suspect portal gets one sentinel probe: run its documented search with the example query from its own SKILL.md (that query provably worked when the skill was registered), the portal's limit flag capped at 3, --format json. If that returns nothing, retry once with a single common word. Only then is the verdict broken. A 429 or block page is never evidence of breakage - record the portal as inconclusive (rate-limited), back off, and do not retry.

Verdicts. Healthy portals get silence - no table, no line. Anything else surfaces in the Step 5 summary as a health line.

Probe-only mode (/scrape health). Skip Steps 1-4 and this step's free pass (there is no fresh run to scan); instead probe every installed portal directly - enabled ones by default, a disabled one only when named explicitly (e.g. /scrape health linkedin). Each portal gets the sentinel probe above, the degraded criteria applied to whatever it returns, and - since the user explicitly asked for diagnosis - one detail fetch on the first result of each healthy portal (description must be readable decoded text; a failure downgrades to degraded). Report all statuses in this mode, including healthy. Volume stays bounded: one search, at most one retry, at most one detail per portal.

Step 5: Present Results

Present new jobs in a table sorted by fit (high first). When Step 1b skipped portals (enabled: false), report them with the skipped (disabled): line below so opting one out stays visible rather than silent; omit the line when nothing was skipped. When Step 4.75 found a portal degraded, broken, or inconclusive, add one health: line per suspect portal (healthy portals get no line); after the report, offer to set that portal's enabled: false so /scrape stops running it (and covers it via the Step 1c fallback) until it is fixed - only edit the toggle with the user's confirmation, and never edit anything else in the skill.

## New Job Matches - YYYY-MM-DD

Found X new positions (Y high, Z medium, W low match).

skipped (disabled): <portal-name>, <portal-name>

health: <portal-name> - degraded (company null on all 12 results); parsing anchors in .agents/skills/<portal-name>/url-reference.md
health: <portal-name> - broken (0 results for the SKILL.md test query and a broader retry); parsing anchors in .agents/skills/<portal-name>/url-reference.md

| # | Fit | Title | Company | Location | Deadline | URL |
|---|-----|-------|---------|----------|----------|-----|
| 1 | High | ... | ... | ... | ... | [Link](...) |

If Step 2.5 flagged a mass-posting pattern, note it in the Title cell (e.g. "Frontend Developer (posted in 6 cities)") rather than burying it - it's a signal the user should see at a glance, not just in the detail highlights below.

### High-Match Highlights
For each high-match job, add 2-3 bullet points:
- Why it matches your profile
- Key requirements to check
- Any red flags (including mass-posting signals from Step 2.5)

### Contacts
For each high/medium-fit job from Step 4.5, add a short contacts block with the two
LinkedIn search links:
- Recruiters/TA search link, for the referral path
- Role/team-peer search link, for the warm-intro / informational-outreach path

After presenting, ask:

"Want me to evaluate any of these in detail? Just give me the number(s)."

If the user picks a number, invoke the job-application-assistant skill workflow (fit evaluation first, then the tailored CV if approved).

If the run found many new jobs (roughly 8+), also suggest /rank - it batch-scores all new postings against the full fit framework and returns a ranked shortlist, which beats eyeballing a long table. (/rank sets the ranked and expired status values in data/jobs.json; treat both as already-seen for dedup purposes.)

Step 6: Record an Application (Optional)

If the user decides to apply to any job, set that entry's status to applied and its applied_date in data/jobs.json. A posting they applied to that this run did not find gets a new entry keyed manual:<company-slug>:<role-slug> with portal: "manual (user)", the same shape the board's Add posting dialog writes.


Important Rules

  1. Never fabricate job postings. Only present jobs from actual CLI search/detail output or WebSearch/WebFetch results.
  2. Respect deduplication. Always check data/jobs.json before presenting - it holds every posting ever seen and every application ever made.
  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 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.
  7. No automated people lookups. Referral contacts (Step 4.5) are LinkedIn search links only - never fetch or scrape LinkedIn people-search result pages programmatically.
  8. Health checks are bounded and honest. Step 4.75 spends at most one probe, one retry, and (in health mode) one detail fetch per portal - a diagnosis, not a crawl. A rate-limit is never evidence of breakage. Health verdicts come only from observed CLI output; a portal that could not be tested is reported as inconclusive, never guessed. The enabled toggle is the only thing the health check may edit, and only with confirmation.
  9. Flag distribution patterns, never accuse. The mass-posting signal (Step 2.5) describes how a listing is being distributed, not a claim that the employer is a scam. Never name a company as fraudulent or untrustworthy - present the observation and let the user decide.

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.