Job Search System
The methodology behind 70+ tailored applications.
fit-check — Staff Engineer · Anthropic
APPLYRequired reading
- → their safety research, last 6 months
- → the JD's "you might be a fit if"
- → 2 employees on LinkedIn, your level
70+
Applications sent
1
Real search used in
Multiple
Offers
What you'll be able to do
Concrete outcomes, not vague promises.
Senior engineering job search
Staff, principal, or EM roles. Use the persona pattern to roleplay the hiring manager, fit-check every JD.
AI / ML roles
AI engineer, ML engineer, applied research. Templates tuned for AI domain — paper writing, evals, infra.
Design engineering / DX
The intersection of design and code. Profile template includes the 'designs what they build' positioning.
Career pivots
Use the persona pattern to reframe your experience for a new domain. fit-check catches the gaps.
Built for
If any of these are you, this is for you.
Why this playbook works
Three things that make this different from a wall of prompts.
The AI Hiring Manager persona
Stop asking the model to be supportive. Make it the hiring manager who'd reject you. The output gets useful in a hurry.
Fit Check, not spray-and-pray
Every JD gets a 0–100 score with the reason you'd apply anyway. If the answer is 'I need a job,' you don't apply.
Tailored at scale
Cover letters that sound like you, not like a template. The methodology takes 70+ tailored applications off the 'impossible' list.
Quick start
Drop the package into your project and start using the commands.
What's in the box
- career-strategypersona + pipeline
- fit-check0-100 scoring
- job-searchsource discovery
- job-applytailored submissions
- interview-prepoperational answers
- 4 templatesprofile, comp, AI targets, cover
- 4 adaptersClaude Code, Cursor, Cline, Aider
- Worked examplereal AI Eng Leader search
Everything in the pack
What you get the moment your payment clears.
Adapters included
These skills were authored for pi-agent, but we include drop-in adapters for the major AI coding tools.
| Tool | Adapter location | What you get |
|---|---|---|
| Claude Code | adapters/claude-code/ | .claude/commands/*.md + CLAUDE.md fragments |
| Cursor | adapters/cursor/ | .cursorrules rule sets |
| Cline / Continue | adapters/cline/ | System-prompt rules |
| Aider / generic | adapters/generic/ | INSTRUCTIONS.md snippets |
Same playbook, different packaging. The adapters translate the methodology into the format each tool expects. Install once, swap agents without re-learning the method.
Full documentation
Everything in the package, every prop, every pattern.
Job Search System
A complete AI-assisted job search methodology. The persona pattern, Fit Check Method, Cover Letter Rules, Pipeline framework, and templates that take you from discovery to signed offer.
The Problem
You have a smart AI assistant. You ask it to write a cover letter, and it produces a generic paragraph that could go to any company. You ask it to assess a job, and it tells you "this sounds like a great opportunity." You ask it to prep you for an interview, and it gives you philosophical answers instead of operational ones.
You end up with a lot of applications, very few interviews, and no real strategy.
The Fix
The skills in this pack are the operating system we layer on top of the raw model. Each one captures a discipline that's hard to maintain in the moment but easy to forget when you're heads-down:
- The AI Hiring Manager persona — strict, decent, competent. Not a yes-man. Tells you when a job is a bad fit. Tells you when your number is below market.
- The Fit Check Method — a structured 0-100 score for every job, with required reading, output format, and what-to-look-for rubric. Skip the 60s, apply to the 80s.
- The Cover Letter Rules — research-first, specific-to-specific, no boilerplate. If the company name can be swapped for a competitor and the letter still reads, the letter has failed.
- The Pipeline framework — discovered → matched → materials → submitted → interviewing → offer. Track the funnel. Surface bottlenecks. Don't let applications sit in "ready to submit" pile.
- The Interview Pattern — the interview is about what you'd do for them, not about you. Every practice answer should name a specific plan.
What's In The Pack
career-strategy — The strategic layer
- The AI Hiring Manager persona (brutally honest, direct, never a yes-man)
- Pipeline health metrics (target / warning / critical for each stage)
- Bottleneck detection patterns
- Priority scoring formula (Fit × 0.5 + Urgency × 0.3 + Effort × 0.2)
- The Listen First rules (don't lecture the user on what they already know)
- Comp & notice anchoring (never negotiate on the user's behalf)
- Daily nudge / weekly review cadence
fit-check — The pre-application gate
- Required reading: profile + comp-notice before scoring
- 0-100 scoring rubric with structured output
- Areas of Strong Fit / Areas of Weak Fit / Pitch / Questions / Red Flags
- The Founder-Experience Counter-Rule (generalizable to all non-traditional candidates)
- Research-before-scoring requirement
job-search — Find and track
- Pluggable source pattern (HN, Adzuna, Greenhouse, Ashby, Lever)
- Job schema with status, score, notes, events
- Deduplication by (company, normalized_title)
- Company research at match stage (the foundation of any good cover letter)
- AI target lists structure (greenhouse / ashby / lever / unknown_ats)
job-apply — Materials + submission
- Per-application folder structure (cv.md, cover.md, cv-data.json, form_answers.json, cv.pdf)
- Cover letter rules: research-first, specific-to-specific, no boilerplate
- ATS submission patterns from real production use (React native setter, comp handling, false-positive detection)
- The "cusp / hobbyist / approaching" trap
- Safe-by-default behaviour (preserve hand-tailored content)
interview-prep — Operational answers
- Question pattern table (anti-pattern vs landing pattern)
- Default answer structure (built → would-build → bridge)
- The second-stage debrief loop
- The founder-as-X story arc
- Common anti-patterns in interview prep
Templates Included
You fill these in once, update as you grow:
| File | What it holds |
|---|---|
templates/profile.md | Career profile: identity, summary, direction, top 10 sell points, story bank, evidence rules, sensitive topics, current LinkedIn presence |
templates/comp-notice.md | Anchor comp and notice period numbers |
templates/ai-targets.json | Companies to poll, bucketed by ATS |
templates/cover-letter.md | Cover letter skeleton + anti-patterns list |
Adapters Included
The skills are authored for pi-agent, but we include drop-in adapters for the major AI coding tools:
| Tool | Adapter | What you get |
|---|---|---|
| Claude Code | adapters/claude-code/ | CLAUDE.md addendum + 3 commands (fit-check, cover-letter, interview-prep) |
| Cursor | adapters/cursor/ | .cursorrules rules |
| Cline / Continue | adapters/cline/ | System-prompt rules |
| Aider / generic | adapters/generic/ | INSTRUCTIONS.md snippets |
Real Usage
This is the methodology we used to:
- Run a 70+ application pipeline targeting AI-first companies
- Score-fit-check every opportunity before sending a single application
- Fix the "all about me, nothing about them" second-stage pattern
- Get the user past 1st-round screens at companies they'd actually want to work at
It works. It's not magic — it's discipline.
License
Personal-use commercial. One purchase = one seat. Install in your dev environment, modify freely, use in your own job search. Do not resell the pack or the unmodified skills as a competing product.
What's in the download
A .tgz containing:
job-search-system-0.1.0/
├── README.md ← this overview
├── INSTALL.md ← per-tool setup walkthrough
├── METHODOLOGY.md ← the longer write-up
├── skills/ ← the 5 skill files (SKILL.md)
│ ├── career-strategy/
│ ├── fit-check/
│ ├── job-search/
│ ├── job-apply/
│ └── interview-prep/
├── templates/ ← what you fill in
│ ├── profile.md
│ ├── comp-notice.md
│ ├── ai-targets.json
│ └── cover-letter.md
├── adapters/ ← drop-in for other tools
│ ├── claude-code/
│ ├── cursor/
│ ├── cline/
│ └── generic/
└── examples/ ← worked example fit checks
Updates
Free for life — re-download any time.
Common questions
Things people ask before buying.
Is this resume advice?
No. It's a system for running a job search where the AI is an operating partner, not a copywriter. The cover letters are one output among many.
Does it work for senior roles?
Yes. It was extracted from a real mid-senior search. The Fit Check, persona pattern, and pipeline framework matter more as the stakes rise.
What if I'm not in tech?
Most of it transfers. The persona pattern and Fit Check work anywhere. The JD-sourcing skills lean on tech boards but are pluggable.
Is it really from a real search?
Yes. The fit-check example in the package is from a real AI Engineering Leader search. 70+ applications, multiple offers, one signed.
£15 — lifetime
One purchase. Yours forever.
Pay once via Stripe. Get the complete package instantly. Free updates for the same major version. Commercial license included.
Secure payment via Stripe · Instant download · 30-day money-back if it doesn't save you time