Career Ops
Run a single slash-command hub to scan job boards, score JDs, generate tailored CVs and PDFs, and track applications through interview prep.
Overview
career-ops is an agent skill most often used in Grow (also Idea, Validate) that centralizes AI-assisted job search—JD auto-pipeline, applications tracking, and interview prep—from one Claude Code router.
Install
npx skills add https://github.com/santifer/career-ops --skill career-opsWhat is this skill?
- Router with 15+ named modes including scan, deep, batch, tracker, pipeline, apply, and auto-pipeline from raw JD text or
- Auto-pipeline detects JD keywords or URLs when no sub-command is passed
- Modes for oferta/ofertas evaluation, contacto, interview-prep, training, project, pdf, and update
- Discovery menu when invoked empty; MIT-licensed user-invocable Claude Code skill
- JD auto-detection via responsibilities, requirements, qualifications, and role phrasing
- 15+ named router modes in the command center
- Auto-pipeline when JD text or URL is passed without a sub-command
Adoption & trust: 1 installs on skills.sh; 50.7k GitHub stars; 1/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
What problem does it solve?
You are juggling portals, tailored CVs, and offer math across disconnected chats with no single workflow for scan → apply → track → prep.
Who is it for?
Solo builders and freelancers running an active job or contract search who want slash-command workflows in Claude Code.
Skip if: Teams that already use a full ATS/CRM with enforced compliance workflows, or anyone who only needs a one-off resume rewrite without tracking.
When should I use this skill?
User runs `/career-ops` with a mode (scan, deep, pdf, oferta, tracker, apply, interview-prep, etc.), empty args for discovery, or pastes JD text/URL for auto-pipeline.
What do I get? / Deliverables
You get a routed mode (or full auto-pipeline from a JD) that evaluates roles, generates artifacts, and keeps pipeline state instead of restarting each search session from scratch.
- Routed mode output (reports, tracker updates, or menu)
- Auto-pipeline evaluation and PDF-oriented artifacts when triggered by a JD
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Grow because the command center’s payoff is sustained application pipeline, follow-ups, and offer evaluation—not one-off ideation. Lifecycle fits tracking, batch apply, pipeline, tracker, and follow-up modes that compound over a job search campaign.
Where it fits
Run `scan` or `deep` to map roles and employers before committing to a niche.
Use `oferta` or `ofertas` to compare requirements and compensation against your target stack.
Keep `tracker` and `pipeline` updated while batching `apply` and `followup` touchpoints.
Invoke `interview-prep` with structured talking points before a technical or founder interview.
How it compares
Use instead of generic “write my CV” chat turns when you need repeatable scan, pipeline, and offer-evaluation modes in one skill.
Common Questions / FAQ
Who is career-ops for?
Indie and solo operators using Claude Code who want a structured job-search command center rather than scattered prompts for each portal or JD.
When should I use career-ops?
During Idea-style market scanning (`scan`, `deep`), Validate-style offer review (`oferta`, `ofertas`), and Grow lifecycle work (`tracker`, `pipeline`, `apply`, `interview-prep`, `followup`); paste a JD anytime to trigger auto-pipeline.
Is career-ops safe to install?
Review the Security Audits panel on this Prism page and treat job-search automation as sensitive—agents may need network or file access for scans and PDFs depending on how you invoke modes.
SKILL.md
READMESKILL.md - Career Ops
# career-ops -- Router ## Mode Routing Determine the mode from `$mode`: | Input | Mode | |-------|------| | (empty / no args) | `discovery` -- Show command menu | | JD text or URL (no sub-command) | **`auto-pipeline`** | | `oferta` | `oferta` | | `ofertas` | `ofertas` | | `contacto` | `contacto` | | `deep` | `deep` | | `interview-prep` | `interview-prep` | | `pdf` | `pdf` | | `training` | `training` | | `project` | `project` | | `tracker` | `tracker` | | `pipeline` | `pipeline` | | `apply` | `apply` | | `scan` | `scan` | | `batch` | `batch` | | `patterns` | `patterns` | | `followup` | `followup` | | `update` | `update` | **Auto-pipeline detection:** If `$mode` is not a known sub-command AND contains JD text (keywords: "responsibilities", "requirements", "qualifications", "about the role", "we're looking for", company name + role) or a URL to a JD, execute `auto-pipeline`. If `$mode` is not a sub-command AND doesn't look like a JD, show discovery. --- ## Discovery Mode (no arguments) Show this menu: ``` career-ops -- Command Center Available commands: /career-ops {JD} → AUTO-PIPELINE: evaluate + report + PDF + tracker (paste text or URL) /career-ops pipeline → Process pending URLs from inbox (data/pipeline.md) /career-ops oferta → Evaluation only A-F (no auto PDF) /career-ops ofertas → Compare and rank multiple offers /career-ops contacto → LinkedIn power move: find contacts + draft message /career-ops deep → Deep research prompt about company /career-ops interview-prep → Generate company-specific interview prep doc /career-ops pdf → PDF only, ATS-optimized CV /career-ops training → Evaluate course/cert against North Star /career-ops project → Evaluate portfolio project idea /career-ops tracker → Application status overview /career-ops apply → Live application assistant (reads form + generates answers) /career-ops scan → Scan portals and discover new offers /career-ops batch → Batch processing with parallel workers /career-ops patterns → Analyze rejection patterns and improve targeting /career-ops followup → Follow-up cadence tracker: flag overdue, generate drafts /career-ops update → Update career-ops system files with diff preview + compat check Inbox: add URLs to data/pipeline.md → /career-ops pipeline Or paste a JD directly to run the full pipeline. ``` --- ## Context Loading by Mode After determining the mode, load the necessary files before executing: ### Modes that require `_shared.md` + their mode file: Read `modes/_shared.md` + `modes/{mode}.md` Applies to: `auto-pipeline`, `oferta`, `ofertas`, `pdf`, `contacto`, `apply`, `pipeline`, `scan`, `batch` ### Standalone modes (only their mode file): Read `modes/{mode}.md` Applies to: `tracker`, `deep`, `interview-prep`, `training`, `project`, `patterns`, `followup` ### Modes delegated to subagent: For `scan`, `apply` (with Playwright), and `pipeline` (3+ URLs): launch as Agent with the content of `_shared.md` + `modes/{mode}.md` injected into the subagent prompt. ``` Agent( subagent_type="general-purpose", prompt="[content of modes/_shared.md]\n\n[content of modes/{mode}.md]\n\n[invocation-specific data]", description="career-ops {mode}" ) ``` Execute the instructions from the loaded mode file.