Build Your Job Engine
You are in the market and drowning. Job boards, referrals, recruiter DMs, and a spreadsheet you stopped updating. Everything looks like a maybe, so everything gets the same effort, and the role that was actually worth it gets the same twenty minutes as the two that were never going to work.
Build Your Job Engine
You are in the market and drowning.
Job boards, referrals, recruiter DMs, and a spreadsheet you stopped updating. Everything looks like a maybe, so everything gets the same effort, and the role that was actually worth it gets the same twenty minutes as the two that were never going to work.
Details
Details
Details
Details
Details
Details
A system built for one person
The same AI-native system thesis, compressed here to run a whole job search for one person instead of a company.
One ranked list of roles worth your time
The humans behind each one
A cadence you actually run
A target-and-concession plan ready for the offer conversation when you get there. The noise gets deleted before it reaches you
You get told to network harder and apply to more. So you do, and the volume goes up while the quality stays flat. Every role gets the same effort because you have no honest way to tell them apart, and the one that mattered got twenty minutes squeezed between two that never would have worked.
The workflow that solves it, one step at a time.
Each step is the plain question you are already asking. The skills answer them in order, one handing its receipt to the next.
Names your tiers with explicit criteria, the fit signals, the anti-ICP you exclude on purpose, and a qualification framework, plus an evolution log. A category is not a definition.
Fair across channels, blank fields never scored as zero, with a why behind each account's score.
Give it a name and company, or a domain, and get contacts or firmographics back. Waterfalls across your tools.
A reusable prompt that gives every account the same shape: verdict, why, people, next move. No connectors.
A connection note plus value-first follow-ups, matched to whether the prospect is cold, engaged, or gone quiet.
Your walk-away and target, the concession ladder, their likely asks, and the holds that protect price and terms.
One ranked list of roles worth your time, the humans behind each one, a cadence you actually run, and a target-and-concession plan ready for the offer conversation when you get there. The noise gets deleted before it reaches you.
- All 6 chained skills resolve to real, scored skills.
- Has a problem, an outcome, 2+ steps, and proof from a real build.
- Ships an example chat showing the play run in Claude.
- Reads in plain operator voice, grounded in a real build.
We did not just check the structure. A judge read this play against the full text of every skill it chains (composition), then ran it on a real scenario end to end (simulated). It passed both. Test scenario: Marcus is between roles with forty tabs of postings open and no system, through to a first offer.
This play runs across the org, not inside sales.
Every function below owns a piece of the play. Skip one and it stalls where most GTM plays stall: in the handoff.
Without it: A generic reference lands as a shrug.
Without it: Every first touch starts cold in a warm market.
Without it: You negotiate scared and it shows.
Watch the skills answer in order.
Describe your situation in plain language. The right skill fires on its own and hands its receipt to the next.
Before you run it, I ran it for real.
This workflow is genericized from a real build. Here is the number it moved, and what I actually did.
WHAT I DID ›
AI-native is not how many agents you have. It is whether one of them watches the others and turns their mistakes into improvements. Build the analyst that reads the audit trail. That is the one that compounds.
Dig into the full build →A search is only as strong as what you decline
The skills hand you a scored list, the humans behind each role, and a brief per company; the offer comes from showing up to a few conversations deeply prepared instead of many half ready. Here is how to run yourself like a one-person revenue team, because in this play you are the leader and the rep.
Once a week, score the week like a pipeline: roles added, roles killed, conversations advanced, and the one account that gets the deep work next week. Anything scored a pass gets deleted, not snoozed.
- 01Train your own read before you swoon
Score the role with icp-scoring before you imagine yourself in it. The brand on the posting is not momentum, seat, or timing, and the score exists to say so.
- 02Protect the outreach blocks
Two fixed blocks a week for the linkedin-outreach cadence, held like customer meetings. A cadence you run when you feel like it is not a cadence.
- 03Rehearse the hiring-manager conversation
Before any first call, rehearse opening with their problem from the account-brief, not your resume. Say it out loud once; the difference is audible.
- 04Inspect conversion by tier
At the Friday review, check where each tier of roles converts to conversations and next rounds. If tier-one roles stall while tier-three replies, the ICP needs the edit, not the effort.
One plugin. 6 skills, bundled.
The whole playbook installs as a single plugin in Claude Code, no copy-pasting 6 times. Or grab any single step above. It runs on what you paste; connect your stack to go live.