Evidence-first resume kit

This repository turns verified career evidence into role-specific LaTeX resumes and, when useful, cover letters. It is designed to prevent a common failure mode of AI-assisted applications: making a document sound closer to the job description by silently overstating skills, scope, titles, or outcomes.

The workflow separates three questions that should never be confused:

1. Evidence Fit: does the candidate actually meet the role, including hard gates?
2. Document Quality: does the resume communicate the supported evidence clearly?
3. Channel Strength: is the application cold, referred, or supported by a warm contact?

A polished resume cannot repair a failed qualification gate. A strong fit can still be hidden by a weak document. The system records both.

Source hierarchy

source documents
    -> structured extractions
    -> canonical claims registry
    -> experience records and role bundles
    -> session plan
    -> generated resume / optional cover letter

resume_builder/canonical/claims.json is the highest-authority career source. Generated files under output/ are never treated as evidence. historical_outputs.json records whether an older package is safe to consult, must be revalidated, or must not be reused.

Default application strategy

• Target Staff/Senior Data Engineering first.
• Use ML Platform/MLOps, data platform, analytics, and semiconductor profiles only where direct evidence covers the actual requirements.
• Treat direct LLM engineering, formal model evaluation, Terraform-heavy SRE, and similar missing required experience as gates rather than keyword opportunities.
• Record fit and outcomes without application quotas; a fit classification is a preparation signal.
• Add a warm-channel action for core applications.

The default document is a two-page International Tech resume for US-tech/FAANG-style roles in Europe. A Swiss/DACH policy overlay is available for employers that expect local conventions. Cover letters are conditional, not automatic.

Workflow

Add evidence

1. Put employment records, project material, papers, or notes under knowledge_base/.
2. Run setup-extract to create a source-grounded extraction.
3. Review it, then run setup-build-kb to update canonical claims, experience files, bundles, and support data.

Apply to a role

1. Run make-resume with the real JD.
2. Review the requirement table and fit gate before approving content generation.
3. Generate and validate the LaTeX resume.
4. Run make-cl only when the session records a justified YES decision.
5. Run critique for separate Evidence Fit, Document Quality, and Channel Strength findings.
6. Run edit-resume for approved repairs.

The skills live in .agents/skills/. Each application receives a session file under output/<Role>/ that preserves the JD, fit decision, claim IDs, content plan, validation results, and application status.

Validation

Validate the knowledge system:

python resume_builder/helpers/validate_resume_system.py

Validate a generated document:

python resume_builder/helpers/validate_resume_system.py --document output/Role/resume.tex

Track the uncapped application record (use summary --all for older applications too):

python resume_builder/helpers/cohort_tracker.py summary

job_scout/state/applications.json owns current status and event history. The old cohort JSON and resume_builder/reference/current_applications.md are generated views. Update status without erasing interview history:

python resume_builder/helpers/cohort_tracker.py update --id <application-id> --date YYYY-MM-DD --event interview_held --note "Interview completed"
python resume_builder/helpers/cohort_tracker.py update --id <application-id> --date YYYY-MM-DD --outcome withdrawn_by_candidate --note "Reason"
python resume_builder/helpers/application_records.py --check

Use application_records.py --render to recover stale generated views. A classification that differs from its numeric rubric needs --fit-override-reason; it is never silently relabelled.

Character counts are available only as readability diagnostics. There are no fixed character bands, equal-length bullet rules, or page-fill quotas.

Run the offline regression suite with python -m unittest discover -s tests -v. The application registry and its import history are versioned; seen-state and generated PDFs are not. package_manifest.py --check checks source/class content and any recorded PDFs that are present. Missing local PDFs are permitted. After inspecting changes, run package_manifest.py to refresh source hashes, or add --record-pdfs to explicitly record current PDF hashes. These snapshots detect edits; they do not certify that an existing PDF was built from a particular source.

Scout writers are serialized with job_scout/state/scout.lock. After a crash, remove a stale lock only after verifying no scout process is still running. Successful reports, including --new-only and --only=..., mark their delivered results seen without changing other companies.

Output and prerequisites

The system writes .tex source only. Compile locally with a LaTeX distribution such as MiKTeX, TeX Live, or MacTeX. Generated resumes should also be checked through PDF rendering and text extraction before submission.

See DOCS.md for the architecture and policy reference.

License

MIT; see LICENSE.