career

Ecosystem entry point — conferences, communities, job boards, hackathons, investors, LinkedIn import. Lower-stress, high-leverage exploration that maps the surface around a domain. All outputs land in <WORKING_FOLDER>/domain-notes/<slug>/.

Discovery entry point — enumerate companies in a domain, find peers of a seed, scope by remote-friendliness or geography, or chunk a broad topic. All discovery skills write to <WORKING_FOLDER>/domain-notes/ for downstream /career:suggest to consume.

Audit public brand surfaces — website, GitHub, Hugging Face, LinkedIn — against ground-truth direction. Surfaces drift, gaps, and stale surfaces. Recommendations only.

Capture entry point — voice memo or text. Transcribes if audio, classifies, proposes route, then on confirmation executes the route (task creation, CRM update, follow-up draft, ground-truth delta proposal). Always confirms before any side-effect.

Side-by-side comparison of job offers (or role opportunities) across comp, growth, and fit dimensions.

Cost-routing + semantic-recall management. Sync the workspace into Pinecone, query it, or inspect the routing decision for a given task.

Generate a cover letter for a specific application, grounded in the user's actual experience.

External CRM adapters. Sync markdown CRM with Airtable or Attio (two-way), or migrate one-shot between backends. Markdown stays the source of truth.

Surface relevant conferences/events for the user's discipline, goals, and travel constraints.

Surface candidate courses that address the user's top skill gaps.

Build an interview prep brief for a specific round — likely questions, answers anchored in the user's experience, and company-specific research.

Quick-log a CPD (continuing professional development) activity — article, talk, book, course session, mentoring, etc.

Register a new role of interest — for tracking, applying, or salary benchmarking.

One-page pre-call brief — talking points in user's voice, questions to ask, fallback pitch, success criterion. Reads ground-truth + research briefs. Writes to <WORKING_FOLDER>/meetings/.

Onboard the user to a career workspace — capture profile, write plugin config, install companion plugins. Variant-aware (career-os | career-planning | job-search | salary-research).

Outreach loop entry point — find contact, draft, send, log, and track status. Subcommand-driven. Uses Hunter for contact discovery and email-skills for sending. Always confirms before sending.

Summarise the current job-application pipeline — by stage, recency, and next actions.

Weekly planning + logging entry point. Reads workspace state to propose a week of actions, or reads diffs at end of week to produce a wrap-up. Delegates time-blocks/tasks to schedule-manager when installed.

Quarterly career self-review — plan vs actual across goals, CPD, skills, applications.

Reconciliation pass — surface drift between ground-truth.md, CRM rows, and recent activity. Every finding cites a specific source row. Never silently overwrites ground-truth — proposes edits the user reviews.

Run a single research brief on a company. Use for ad-hoc deep-dives on one angle (e.g. just remote-friendliness, or just glassdoor signal) without paying the cost of a full six-brief run.

Orchestrate a full six-brief deep-dive on a target company — overview, financials, recruitment, remote-friendliness, glassdoor, cultural-fit — then synthesise a top-level SUMMARY with best/worst signals, candidate interview questions, and a fit-with-ground-truth verdict.

White-hat salary benchmarking for a (geography, role) pair. Cached so repeat calls don't re-fetch.

Refresh skills/gaps.md by diffing current skill inventory against target-role profile. Carries plan notes forward.

Recommendation entry point — given ground-truth and discovery notes, suggest companies (with anti-loop), roles, skills to close, projects to ship, or consulting packages. All suggestions write a dated file to <WORKING_FOLDER>/recommendations/.

Generate a resume variant tailored to a specific role/JD. Never invents experience.

Update the status of a job application in the pipeline — stage change, interview scheduled, rejection, offer, follow-up.

Maintains the job-application pipeline database (`data/processes.json`). Use for any read/write operation on the pipeline — status updates, queries, rollups, integrity checks.

Autonomous career strategy subagent. Coordinates multi-step planning — diffing gaps against goals, sequencing CPD, proposing role moves, and drafting narrative arcs. Use for multi-file, multi-step career planning operations.

Audit the user's public brand surfaces — personal site, GitHub, Hugging Face, LinkedIn — against ground-truth direction. Surfaces drift (site says X, ground-truth says Y) and gaps (no project shipped in domain Z). Produces an actionable update list.

Produce a Company Financials research brief — funding rounds, valuation, revenue (if disclosed), burn / runway, profitability signal, public-market metrics. Use when the user needs a numbers-only read for negotiation, due-diligence, or to gauge runway risk. Reads templates/research-briefs/company-financials.md and writes to <WORKING_FOLDER>/research/companies/<slug>/company-financials.md. Numbers are sourced or marked "not disclosed" — never estimated.

Produce a Company Overview research brief for a target company — name, locations, headcount, funding rounds at a glance, founder story, competitive landscape, vision, differentiators. Use when the user wants a top-level read on a potential employer or consulting client. Reads the template at templates/research-briefs/company-overview.md and writes to <WORKING_FOLDER>/research/companies/<slug>/company-overview.md. Cites at least 3 sources. Skipped fields are marked unknown, never fabricated.

Produce a Cultural Fit research brief — pairs the user's stated operating style and constraints (read from ground-truth.md) against the company's apparent operating mode (from public signals). Output is a match-map plus blunt friction list. Use after the other briefs are in hand. Requires populated ground-truth.md. Reads templates/research-briefs/cultural-fit.md and writes to <WORKING_FOLDER>/research/companies/<slug>/cultural-fit.md.

Produce a Glassdoor / employee-sentiment research brief — overall ratings, sub-ratings, tenure data with red-flag detection scoped to the relevant team, compensation data, theme analysis of top complaints and positives, recent direction inflections. Aggregate sentiment, not a recap of individual reviews. Use to gauge whether public employee discourse aligns or contradicts the company's outward image. Reads templates/research-briefs/glassdoor-signal.md and writes to <WORKING_FOLDER>/research/companies/<slug>/glassdoor-signal.md.

Produce a Recruitment Profile research brief — careers page, open roles (filtered by target function if provided), LinkedIn presence, headcount trend, hiring signals, recruiter activity, and known interview-process patterns from public sources. Use when the user wants to assess whether a company is actually hiring people like them, vs. posting ghost roles. Reads templates/research-briefs/recruitment-profile.md and writes to <WORKING_FOLDER>/research/companies/<slug>/recruitment-profile.md.

Produce an honest Remote Friendliness research brief — does the company actually hire from the user's location, or is the "remote-first" claim marketing? Cross-references stated policy against live job postings, time-zone requirements, hiring entities, and existing employees in the user's region. Critical for non-US/EU users. Reads templates/research-briefs/remote-friendliness.md and writes to <WORKING_FOLDER>/research/companies/<slug>/remote-friendliness.md.

Sweep all (or a filtered subset of) email addresses in the workspace CRM and re-verify them via Hunter Email-Verifier. Use periodically — people change jobs, addresses go stale, accept-all status changes. Updates the `verified` and `last-verified` columns in `crm/contacts.md` and prints a summary of what flipped.

For broad domains ("AI", "fintech", "climate"), segment into sub-niches first, then drill down per segment using discover-by-domain. Writes a parent index plus per-segment notes. Use when discover-by-domain bails out.

Given one seed company, find peers along an explicit similarity axis (product, customer, tech stack, business model, culture). Writes to <WORKING_FOLDER>/domain-notes/like-<seed-slug>.md. Reads outreach.md to mark contact status. Use when the user has a known reference point and wants more of the same shape.

Two-way sync between markdown CRM (crm/companies.md, crm/opportunities.md, crm/outreach.md) and Airtable. Reads CRM_ADAPTER=airtable. Markdown stays the source of truth — Airtable is a mirror with a diff back. Conflicts surfaced for user resolution, never auto-merged.

Two-way sync between markdown CRM and Attio. Same shape as crm-adapter-airtable but mapped to Attio's object model (Companies, People, Deals, Notes). Markdown stays canonical; Attio is a working surface. Conflicts surfaced, never auto-merged.

One-shot migration between CRM backends. Markdown → Airtable, markdown → Attio, Airtable → markdown, Attio → markdown, or Airtable ↔ Attio. Use when first adopting an external CRM, when leaving one, or when swapping providers. Snapshot-style, not incremental.

Scan the user's existing Claude Code plugins and MCP servers to detect capabilities the career plugin needs (email send, transcription, calendar/tasks, semantic store, CRM). For each capability, decide whether to reuse an already-installed plugin/MCP, install a recommended companion plugin, or add an MCP server. Writes the resolution map to ${CAREER_DATA_DIR}/config.json under a `capabilities` block. Invoked from /career:onboard before install-companion-plugins so we don't double up on capabilities the user already has.

Enumerate the main companies in a defined niche (e.g. "agentic AI for policy simulation", "open-source LLM tooling"). Writes to <WORKING_FOLDER>/domain-notes/<domain-slug>.md. Reads outreach.md to flag already-contacted companies. Use as the first step before /career:suggest companies — populate the domain knowledge once, suggest from it many times.

Enumerate companies in a domain operating in or hiring within a specific geography (city, country, region). Writes to <WORKING_FOLDER>/domain-notes/geo-<geo-slug>-<domain-slug>.md. Reads outreach.md to mark contact status.

Enumerate companies in a domain that are genuinely remote-friendly to USER_LOCATION (not just "remote-OK" with US-only fine print). Writes to <WORKING_FOLDER>/domain-notes/remote-<domain-slug>.md. Honest negatives over hopeful positives.

Generate an outreach email draft grounded in ground-truth.md, the company research brief, the target contact, and a chosen template (cold-pitch / warm-followup / consulting-pitch / job-followup / interview-followup). Always saves to drafts/ and presents to the user for review. Never sends. send-outreach is a separate skill that requires explicit confirmation.

Enrich an existing CRM contact with Hunter Combined-Enrichment — pulls role, seniority, department, social handles, and the contact's company facts in one call. Use to flesh out a thinly-populated CRM row before drafting outreach or prepping for a meeting. Operates on an email address from the CRM; updates the row in place.

Enumerate communities (LinkedIn groups, Slack channels, Discords, professional orgs, mailing lists) for a domain. Each entry includes activity-level signal and alignment to ground-truth. Writes to <WORKING_FOLDER>/domain-notes/<domain-slug>/communities.md.

Enumerate conferences and events at the intersection of a domain, geography, and date range. Reads ground-truth for goals/travel constraints. Writes to <WORKING_FOLDER>/domain-notes/<domain-slug>/conferences.md. Surfaces CFP windows separately so the user can submit, not just attend.

Find the right person to contact at a target company using Hunter.io. Use when the user needs decision-maker / hiring-manager / founder contact details before drafting an outreach. Returns ranked candidates with confidence scores; optionally appends to the workspace CRM. Hunter MCP is required.

Given a person's name and their company (name or domain), return Hunter's best guess at their email address with a confidence score. Use when the user already knows who they want to reach and just needs the address. Differs from find-contact (which lists candidates at a company) — this is targeted at a single named person.

Enumerate hackathons relevant to a domain. Per spec, hackathons are often a direct line to founders — surface ones that double as outreach surface, not just coding events. Writes to <WORKING_FOLDER>/domain-notes/<domain-slug>/hackathons.md.

Enumerate specialist job boards relevant to a domain (and optionally the user's location/remote preference). Filters out generic boards (LinkedIn, Indeed) by default — surfaces only niche-aligned sources. Writes to <WORKING_FOLDER>/domain-notes/<domain-slug>/jobs-boards.md.

Read or edit the workspace's ground-truth.md — the source-of-truth profile every Career-OS skill reads first. Use when the user says "update my profile", "I changed roles", "I'm looking for X now", or after a major life/career change. Idempotent and diff-friendly. Never silently overwrites.

Parse a LinkedIn data export ZIP — positions, connections, messages, profile — and land structured markdown/CSV in <WORKING_FOLDER>/linkedin/. Surfaces follow-up candidates (recent connections + recent message threads) for the user to consider routing to outreach.

Offer to install Claude Code plugins that complement the career plugin. Use during /career:onboard, or whenever the user wants to enable a downstream capability (transcription for voice ingest, schedule-manager for calendar/tasks, email-skills for outreach send, social-feedback for company sentiment research, decision-evaluation-framework for offer comparisons, private-misc for Pinecone wiring). Lists each, explains what it unlocks in the career plugin, and lets the user accept/decline per plugin.

Manually log an outreach that was sent outside the plugin (e.g. a LinkedIn message, an in-person conversation, an email sent from a phone). Appends a row to crm/outreach.md without invoking any send. Use this to keep the outreach log honest as the spine of the recommendation engine.

Map VCs and angels active in a domain. Output is usable as introducer surface — for each investor, surface portfolio companies that overlap with the user's target list. Writes to <WORKING_FOLDER>/domain-notes/<domain-slug>/investors.md.

Produce a one-page pre-call brief — 5 talking points in user's voice, 3 questions to ask, 1 "if cornered" framing, 1 "what success looks like" line. Reads ground-truth + any existing research briefs. Saves to <WORKING_FOLDER>/meetings/<YYYY-MM-DD>-<company>-prep.md.

Provision a new career workspace on disk. Use when the user wants to start a new career-os, career-planning, job-search, or salary-research project. Accepts a workspace name and a variant (career-os | career-planning | job-search | salary-research). Default variant is `career-os` — the unified employment + freelance workspace. Scaffolds the workspace, personalises CLAUDE.md from the user's global memory, and (by default) creates a GitHub repo.

Incremental sync of working-folder/ into a Pinecone index for semantic recall. Embeds only changed files (mtime + content hash). Index name from config. Delegates first-time MCP setup to private-misc:personal-context-injection. Idempotent.

Lightweight capture for inline text or short voice notes — same classification + routing pipeline as voice-ingest, but optimized for "one thought, drop it in" rather than full memos. Voice routes through the transcription companion; text skips straight to classify + propose route.

Cost-routing helper. Reads RESEARCH_MODEL from config and decides whether a bulk-research call should run on Claude or be delegated to a cheaper model (DeepSeek Pro/Flash via OpenRouter). Reserves Claude for ground-truth, meeting-prep, draft-outreach, recommendation engine. Skills that produce many cheap research artifacts (discovery, ecosystem, financials briefs) call this first.

Given a classified inbox entry (from voice-ingest or text input), execute the proposed route — create tasks, update CRM rows, draft follow-ups, propose ground-truth edits. Always confirms each side-effect before committing. Marks the inbox entry routed when done.

White-hat salary benchmarking for a (geography, role) pair. Cached at cache/salary-<geo>-<role>.md so repeat calls don't re-fetch. Public sources only — postings, Levels.fyi, Glassdoor, Payscale, BLS/Eurostat, SEC, Blind/Fishbowl as signal. Confidence-tagged per data point.

Reconciliation pass. Reads ground-truth.md + crm/companies.md + crm/opportunities.md + crm/outreach.md and surfaces discrepancies. Never silently overwrites — every finding is a proposed delta the user reviews. Writes to <WORKING_FOLDER>/reconcile/<YYYY-MM-DD>-findings.md.

Query Pinecone (or fallback to grep-over-markdown) for context relevant to a task. Returns ranked snippets with cited paths. Used by suggest-companies, meeting-prep, weekly-plan, self-healing-context when CONTEXT_STORE=pinecone. Caller decides what to do with results.

Send a previously-drafted outreach email. Reads a draft file from drafts/, presents it one final time to the user, requires explicit "yes, send" confirmation, then delegates to the email-skills companion plugin (personal or business sender per draft frontmatter). On send, updates the draft frontmatter to status=sent and appends a row to crm/outreach.md. Never sends without explicit confirmation.

Diff current skill inventory against target-role/domain profile. Categorises gaps as critical/material/met. Carries plan notes forward across refreshes. Writes skills/gaps.md. Different shape from suggest-skills (which is forward-looking against a horizon) — this is the inventory delta.

Rank companies from a domain note (or set of notes) for the user, applying anti-loop logic against outreach.md. Hard-excludes recently-contacted; rank-downs stalled; surfaces freshness so the logic is visible. Writes to <WORKING_FOLDER>/recommendations/companies-<date>.md.

For users with a freelance-brand in ground-truth, propose narrow consulting offers (problem framed, scope outlined, rough investment indicated) targeted at a domain or company. Writes to <WORKING_FOLDER>/recommendations/consulting-packages-<date>.md.

Suggest concrete projects (build / write / contribute) the user could ship to close a skill gap, demonstrate a capability, or create a hook for outreach to a target company. Writes to <WORKING_FOLDER>/recommendations/projects-<date>.md.

Given ground-truth and (optionally) a target company or domain, suggest role titles/shapes to target. Distinguishes "roles that exist on the market" from "roles I should pitch creating". Writes to <WORKING_FOLDER>/recommendations/roles-<date>.md.

Identify skill gaps between ground-truth and target roles/companies/domain. Distinguishes "must close to be considered" from "would round out the profile". Writes to <WORKING_FOLDER>/recommendations/skills-<date>.md.

Produce a resume variant tailored to a specific role/JD. Reads master resume + ground-truth + JD; rewrites bullets to surface relevant experience and mirror JD phrasing where truthful. Never invents experience. Writes to resume/variants/<company>-<role>.md with a tailoring summary.

Update the status of an existing outreach log row. Use when a contact replies, books a meeting, the meeting happens, the conversation stalls, or the opportunity closes. Records state-change date without rewriting history. The recommendation engine reads these statuses to enforce anti-loop discovery.

For CONTEXT_STORE=pinecone — verify the index against the local workspace. Flags vectors whose source file was deleted, renamed, or content-changed (hash mismatch), and surfaces vectors whose content contradicts current ground-truth (stale claims, closed engagements, outdated targets). Proposes deletes/re-embeds; never silently mutates the index.

First-run scaffold of a vector-store namespace dedicated to application/outreach tracking. Creates the `applications` namespace in the configured index, sets the metadata schema (company, role, status, applied_date, last_touch, source_path, stage), seeds it from crm/outreach.md + crm/opportunities.md, and registers it in config. Idempotent — re-running detects existing namespace and offers reseed or skip.

Validate a single email address via Hunter Email-Verifier. Use when the user has an address (handed to them, scraped, guessed) and wants a deliverability + confidence read before sending outreach. Returns Hunter's verdict (deliverable / risky / undeliverable / unknown), score, and the disposable / role / accept-all flags. Does not write to the CRM unless asked.

Accept an audio file path, transcribe via the claude-transcription companion, classify the transcript (quick-note / retrospective / strategic-dump / unclear), and propose a route. Never auto-routes — always confirms with user. Lands transcript + audio link in <WORKING_FOLDER>/inbox/<YYYY-MM-DD-HHMM>.md.

End-of-week wrap-up. Reads outreach diffs since last log, reads the week's plan, asks user what worked, what didn't, what's next. Produces a wrap-up doc. Delegates to schedule-manager wrapup-style if available. Saves to <WORKING_FOLDER>/plans/<YYYY-MM-DD>-week-log.md.

Read crm/outreach.md + crm/opportunities.md + recent recommendations, propose 5–7 actions for the week (mix of research, outreach, follow-up, meetings, ecosystem). Delegates actionable items to schedule-manager:batch-create-tasks and time-blocked work to schedule-manager:batch-create-events. Confirms before any external write.

Flat/local-mode workspace hygiene. Sort loose files into canonical folders (research/, domain-notes/, inbox/, crm/, resume/, snippets/, branding/, cache/), find near-duplicates by name+hash, flag stale inbox entries (>14d), and re-root mis-placed files. Proposes a plan, applies only on confirm. No-op when CONTEXT_STORE != markdown.