0 Fork 0

Files

T

dennisthiessenandClaude Opus 5 a0ec2fedb5 feat: NVIDIA Sr DevOps application, drop cohort caps, fix Workday/decision-log bugs

Scout run 2026-09-04 (36 companies, 778 eligible) plus the NVIDIA package it
surfaced, and the tooling and policy fixes found along the way.

Application
- NVIDIA Senior DevOps Engineer, Zurich (JR2024256): submitted 2026-09-05.
  Evidence Fit 64/100 Stretch, hard gate FAIL x2, channel Weak. Sent on an
  explicit user override with the working model unresolved, so hybrid-vs-onsite
  is a live screening topic. 2pp resume + 1pp cover letter, both validators
  PASS, 0 boxes, 0 Tier 1 findings open.

Policy
- Drop the 7 Core / 2 Adjacent / 1 Stretch cohort caps. They had no derivation
  and were overridden whenever they bound, and the cohort was confounded: it
  tested fit class while holding channel constant at Weak across all six
  applications. Keep the recording, drop the rationing.
- Channel replaces the slot budget as the rationed variable: no application
  goes out cold when a named contact is published and reachable.
- Propagated through shared_ops, session_file_template, cohort_tracker
  (counts, never counts-against-a-target) and application_cohort.json.

Tool fixes
- fetch_workday emitted 404 URLs for every Workday company (NVIDIA, Novartis,
  Equinor): externalPath is site-relative and needs the locale + site prefix.
  6/6 short-form 404, 3/3 long-form 200. 773 dead links repaired across 42
  archived reports.
- find_decision_url silently de-linked decisions on two boards, which is why
  ruled-out roles kept resurfacing as undecided. RUAG rotates its UUID on
  repost; BIS migrated its vacancy URL scheme, orphaning 5 decisions including
  a live application. Fixed as a two-tier match, not a slug key -- slugs
  collide (two live RUAG reqs shared one).

Knowledge base
- claims.json: add Bash / shell scripting, the third canonical gap of this
  shape after Ansible and Linux administration.
- bundle_data_platform: BS-4 was framed as a delivered observability stack over
  what claims.json calls a proof of concept -- the defect the 2026-08-21 sweep
  was told to look for.
- CLAUDE.md and AGENTS.md: correct the RUAG Data Lakehouse shortlist claim,
  which the JD does not support and which both files still asserted.
- resume_template: comment-guard the missing babel/ngerman language block.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QFb8tTCig5r1KzkQiNXcYt

2026-09-05 13:24:44 +02:00

4.1 KiB

Raw Blame History

Shared Operations — All Application Skills

Canonical Evidence Preflight

Before generation, editing or critique:

Read resume_builder/canonical/claims.json completely.
Read config.md and AGENTS.md corrections/status.
Run python resume_builder/helpers/validate_resume_system.py.
Treat canonical claims as higher authority than extractions, experience files, bundles, sessions or outputs.
Never use a file under output/ as source content for a new application. Consult resume_builder/canonical/historical_outputs.json.
Omit or ask about anything absent, ambiguous or unverified.

JD Integrity

Use the real posting text verbatim.
A URL is not a JD; retrieve the visible posting body first.
Do not reconstruct, infer or complete a missing posting.
If the real JD cannot be obtained, stop and ask the user to paste it.
Record source, retrieval method, retrieval date and posting status in the session.
Recheck that a live role still exists before investing in a package.

For JavaScript-heavy boards, use the in-app Browser skill or the existing Playwright environment under job_scout. Save the retrieved text in the output folder.

Fit Before Writing

Read resume_builder/reference/application_strategy.md and critique_framework.md. Complete the Evidence Fit and hard-gate assessment before planning bullets.

Core: proceed.
Adjacent: proceed selectively and state the serious gap.
Stretch: confirm user intent before full generation and state the gap plainly. There is no cohort capacity to check -- the slot caps were dropped 2026-09-05 (application_strategy.md).
No-go: record the decision; do not generate a package unless the user explicitly overrides after seeing the gate.

Audience and Cover-Letter Decisions

Select International Tech, Swiss/DACH or Employer-specific format before writing. International Tech is default.

Apply cl_reference.md and record Cover Letter Decision: YES/NO. A deliberately omitted letter is a valid complete package.

Session Files

Store each application at output/<Folder>/session_<name>.md; use session_file_template.md for new sessions.

Derive <name> from company and role using lowercase underscores. Related files use the same key:

session_<name>.md
e2e_<name>_resume.tex
optional e2e_<name>_cover_letter.tex
critique_<name>.md

To find a session from a .tex path, strip e2e_ and the document suffix, search the same folder, then output/**/session_*<company>*.md.

Re-read the session at the start of each phase and resume from its Status. Do not restart completed work.

Folder Creation

At the start of an approved application:

Create output/<Folder>/.
Copy the verbatim JD into it.
Create the session file.
Copy resume.cls and the selected template only when generation begins.

Do not copy a prior application resume.

Validation and Visual QA

After creating or editing a document:

Run python resume_builder/helpers/validate_resume_system.py --document <file.tex>.
Compile with the local LaTeX distribution.
Inspect the PDF at normal size.
Extract text with pdftotext and verify heading/employer/title/date order.
Check page count, clipping, overlap, page breaks and contact information.

Character counts may diagnose an unwieldy bullet, but there are no target character bands and no page-fill quota.

Finalization

After explicit approval:

Verify the session, resume source/PDF and critique exist.
Verify the cover-letter source/PDF only when the session decision is YES.
Run the canonical validator again on every submitted document.
Copy final PDFs to Dennis_Thiessen_Resume.pdf and, when applicable, Dennis_Thiessen_Cover_Letter.pdf.
Record submission date, fit class, Evidence Fit, hard gate, channel and outcome status.
Add the application to the active cohort with cohort_tracker.py add.

Progress and Recovery

Give short progress updates at major steps. Before ending or clearing context, update session Status and the Active Sessions pointer. If interrupted, add a Resume Point describing completed work and the exact next action.

4.1 KiB Raw Blame History