AI Agent Workflow Collection

Generate Day-5/7/10 follow-up bump messages for any pending roles. Triggers on "what bumps today", "Day-5 bumps", "follow-ups due", "/bump", "/bump X", or "what should I follow up on today". Reads the dashboard, finds roles in the bump window or past Day-10 final-action threshold, and drafts the appropriate bump message per role per follow-up.yaml templates.

Quick dashboard health and status overview — checks the Agent Monitor API (port 4820), reports session/agent/event counts from /api/stats, confirms WebSocket connectivity, validates hook configuration in ~/.claude/settings.json, and shows data freshness (last event timestamp). Use to verify the monitoring system is operational.

Run the daily Phase 1 sweep for senior product leadership roles. Triggers on "run today's sweep", "Phase 1", "find new roles", "/sweep", "what's new today", "morning sweep", "scan LinkedIn for product roles". Sources roles from LinkedIn AND directly from major ATS domains (Greenhouse, Lever, Workday, Ashby, etc.) via Google site: search, pulls JD bodies via the apply-link redirect or direct fetch, scores each role 1-10 against the user's ICP and scoring weights, dedupes against the existing dashboard, and produces a Tier-1 / Tier-2 / Skip greenlight summary. Stops before Phase 2 - waits for the user's per-role greenlight.

Build a Phase 2 outreach packet for a single greenlit role. Triggers on "build packet for X", "tailor CV for X", "Phase 2", "packet X", "/packet", or any request to prepare an application for a specific company / role. Pulls the full JD via the ATS redirect, identifies the right contacts, generates a JD-tailored CV (docx + PDF) per the discipline rules, drafts channel-appropriate outreach (Connect+Note + longer DM), and saves the packet under outreach/{slug}/. Stops before Phase 3 - waits for the user's explicit "send" approval.

Walk through Phase 3 send for a single greenlit packet. Triggers on "send X", "Phase 3 X", "/send X", "fire X", "let's send X", or "ready to send X". Opens the right LinkedIn surface for each channel (Connect+Note dialog, DM thread, InMail compose), types the drafted message into the field, and stops with the cursor positioned for the user to click Send. Never sends autonomously. Walks the user through each channel in priority order; after each user-confirmed send, updates the dashboard from "drafted" to "pending" with sendDate today.

Build a meeting / interview prep packet for a booked conversation on a specific role. Triggers on "prep me for X", "build prep packet for X", "interview prep X", "/prep ", "screening call prep", "panel prep", "final round prep". Pulls role context from the dashboard, researches the named interviewer (LinkedIn, TheOrg, Crunchbase, web), refreshes company intel, generates the scope-disambiguation question, first-90-days narrative (with branches if scope is ambiguous), questions to ask, one-line answers to likely questions back, comp posture, friction flags, and a wrap-up signal checklist. Saves three artifacts: full markdown, interactive HTML, and a one-page scannable card. Supports rounds screen / working-session / panel / final / exec / reference-check-prep. User-invoked only, never auto-fires.

Process post-call notes from a meeting prepared via phase-4-prep. Triggers on "debrief X", "log my call with X", "/debrief X", "/debrief ", "I just talked to here are my notes", or pasting raw call notes after a Phase-4-prepped meeting. Captures intel learned in the call (scope answer, comp signals, process commitments, friction flags, anchors that landed), updates the dashboard, identifies the next-action (prep next round / send thank-you and wait / send requested materials / passive watch / mark rejected / escalate to different contact), and prompts for memory writes when patterns emerge. User-invoked only, never auto-fires.

Score a single role against the user's ICP and scoring weights. Triggers on "score this role", "score this JD", "is this a fit", "rate this", "/score", or pasting a JD URL with no other context. Pulls the JD body if needed, applies dimensional scoring per scoring.yaml, returns a 1-10 score with per-dimension breakdown and tier classification. Lightweight, no packet generation.