メニュー
Ingest the user's resume, CV, and other career documents to build a structured profile that grounds all job matching and application tailoring. Use when the user wants to upload or update their resume/CV, or run "/jobfinder:profile <files>".
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Apply to a job the hybrid way — auto-draft an EMAIL application (into the user's Gmail drafts, resume attached) when the ad accepts email, or hand back a ready-to-submit pack (direct link + cover letter on the clipboard + prepared screening answers) for form-only jobs. Use for "/jobfinder:apply adzuna:12345" or "apply to this job for me".
Save recurring job searches and surface only newly-posted matches on demand. Use when the user wants a saved search / job alert, e.g. "/jobfinder:alerts save devops devops engineer Brisbane" or "/jobfinder:alerts run".
Search Australian job listings (Adzuna + Workforce Australia) and rank them against the user's profile. Use when the user wants to find jobs, e.g. "/jobfinder:search devops engineer Brisbane" or "find me remote data roles".
One-time setup for the jobfinder plugin — configure Adzuna API credentials and verify each Australian job source is reachable. Run this first.
Draft a tailored cover letter and resume-tweak suggestions for a specific job listing, grounded in the user's profile. Use when the user wants to apply to or tailor an application for a saved job, e.g. "/jobfinder:tailor adzuna:12345".
Track and view the job-application pipeline (saved, applied, interviewing, offer). Use when the user wants to save a job, update its status, add a note, or see their pipeline, e.g. "/jobfinder:track applied adzuna:12345" or "/jobfinder:track list".
| name | profile |
| description | Ingest the user's resume, CV, and other career documents to build a structured profile that grounds all job matching and application tailoring. Use when the user wants to upload or update their resume/CV, or run "/jobfinder:profile <files>". |
Turn the user's career documents into the grounding profile that every other
jobfinder skill loads into context. $ARGUMENTS holds the file path(s).
Extract text. Run (pass every file the user gave):
uv run "${CLAUDE_PLUGIN_ROOT}/scripts/ingest.py" $ARGUMENTS
The script prints each document's text under an === filename === header and
saves a copy to ~/.jobfinder/profile/raw/. If a file errors (scanned/image
PDF, .doc, password-protected), relay the script's guidance and continue
with the files that worked.
If the user gave no files, list what's already in
~/.jobfinder/profile/raw/ and ask which document to add, or offer to let
them describe their background in chat instead.
Merge, don't clobber. If ~/.jobfinder/profile/profile.json already
exists, Read it first and merge the new documents into it (add new roles,
skills, updated preferences) rather than replacing it.
Write profile.json to ~/.jobfinder/profile/profile.json — structured
facts you'll reuse:
target_roles, seniorityskills (each with brief evidence from the documents)experience (roles, employers, dates, key achievements — quantified where
the source quantifies them)locations (preferred Australian locations; note remote/hybrid appetite)salary_expectation_aud (min, ideal)work_rights (e.g. citizen / PR / visa — only what the documents state)constraints and red_lines (things to avoid)Write profile.md to ~/.jobfinder/profile/profile.md — a concise
(~1500 token) context card that other skills load. It is the grounding, so
keep it dense and factual: target roles, top skills with one-line evidence,
seniority, Australian location preferences, salary expectation (AUD),
work rights, and hard constraints.
Confirm. Show the user the profile.md card and ask them to correct
anything wrong or missing. Only record facts supported by the documents or
the user — never invent experience, credentials, or work rights.
Next step. Point them to /jobfinder:search <what you're looking for>.