agentleFS
Miracle-AlignerMiracle-Aligner/job-search-hq/CLAUDE.md

job-search-hq

CLAUDE.md1 starsChanged 5 months agoMITView on GitHub

An agent-maintained job-search CRM. A single JSON board is the source of truth, a self-contained static HTML file is the viewer, config files hold the knobs, and a suite of Claude Code skills do the work. No frameworks, zero runtime deps (Python stdlib only; dev/CI tooling may add dev-only deps). - data/vacancies.json — source of truth, a v2 envelope: { "schemaVersion": 2, "vacancies": [ … ] }. Gitignored (real data). The committed demo is data/vacancies.sample.json (synthetic, regenerated by scripts/make_demo.py). scripts/board.py…

The file

We split this CLAUDE.md into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Pipeline-locked statuses are sacred: Never overwrite applied, hr_screen, tech_interview, final, offer, rejected during a sweep.

    line 45

≈ “Common” is an estimate: at least 1 in 5 of the 28,029 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

Job Search HQ — Claude Code project context

An agent-maintained job-search CRM. A single JSON board is the source of truth, a self-contained static HTML file is the viewer, config files hold the knobs, and a suite of Claude Code skills do the work. No frameworks, zero runtime deps (Python stdlib only; dev/CI tooling may add dev-only deps).

Where things live

  • data/vacancies.json — source of truth, a v2 envelope: { "schemaVersion": 2, "vacancies": [ … ] }. Gitignored (real data). The committed demo is data/vacancies.sample.json (synthetic, regenerated by scripts/make_demo.py). scripts/board.py is the one place that knows the shape.
  • job-search-hq.html — the viewer. Carries the data + app config baked into <script type="application/json"> blocks (sentinel-bounded) so file:// works anywhere. Always baked from the sample — real data only ever lands in the gitignored job-search-hq.local.html (via serve.py).
  • config/ — app.json · scoring.json · platforms.json · sources.json. One source of truth per concern; *.local.json (gitignored) overrides merge on top.
  • schema/vacancy.schema.json — the data contract. validate.py checks against it (via the stdlib mini-validator in scripts/schema_check.py).
  • profile/ — candidate.md + profile.json (gitignored real; *.example.* committed) and cv/ (gitignored CVs). Read by assessment skills at scoring time.
  • docs/ — schema.md, rubric.md (generated by gen_rubric.py), scheduling.md.
  • scripts/ — serve.py (live server) · build.py (validate+bake) · bake.py · validate.py · score.py · migrate.py · init.py · make_demo.py · gen_rubric.py · board.py · config_util.py · schema_check.py.
  • .claude/skills/ — the skills (see below). tests/ — stdlib unittest.

Conventions

  • Single source of truth per concern. Data → data/. Config → config/. Schema → schema/. Don't duplicate constants across Python/JS/CSS — bake.py injects {app, scoring, platforms} into the HTML so the UI can't drift.
  • Never commit real data. Real data/vacancies.json, profile/candidate.md, profile/profile.json, profile/cv/*, config/*.local.json, and job-search-hq.local.html are gitignored. Work against the *.sample/*.example files. The committed HTML and the Pages demo are sample-only.
  • After editing data, run python3 scripts/build.py --real (validates real data + rebakes the gitignored local snapshot). build.py with no args rebuilds the committed demo from the sample (what CI's drift check runs).
  • Score via the script. Pick 5 honest sub-scores per docs/rubric.md, then python3 scripts/score.py compute <tech> <comp> <level> <company> <appeal> [risk]. Weights/tiers come from config/scoring.json. Tier is derived — never hand-set.
  • Pipeline-locked statuses are sacred. Never overwrite applied, hr_screen, tech_interview, final, offer, rejected during a sweep.
  • altLinks are verified, not synthesised — every URL must return a role-relevant 200.
  • Escape untrusted text in the viewer (esc/safeUrl/sanitizeRich); statusDetail is the one field allowed a small formatting-tag allowlist.

Running

Nothing to install. Stdlib only.

  • Live (recommended): python3 scripts/serve.py → http://127.0.0.1:8765/job-search-hq.html. The viewer detects /api/vacancies and auto-saves every change (atomic write, ETag/409 concurrency guard, schema-validated on PUT).
  • Read-only: open job-search-hq.html via file:// — the demo renders from the baked block.
  • Tests: python3 -m unittest discover -s tests.

Skills overview

SkillPurpose
build-profileCreate/refresh profile/candidate.md + profile.json (interview or parse CV/LinkedIn).
ingest-cvParse a CV in profile/cv/ → structured data linked from the profile.
add-vacancyIngest one URL / bulk list / aggregator → score → append. Honors crossLink.
refresh-listingsSweep the sources in config/sources.json (Claude in Chrome) → hand to add-vacancy.
recheck-statusesMark dead postings closed; pipeline-locked statuses stay.
update-statusMove a role through the pipeline; timestamp statusDetail; offer interview prep.
interview-prepResearch + build a prep brief → events[].prep.
cover-letterTailored, human-sounding cover letter → coverLetter.
add-sourceAdd/edit/disable a source in config/sources.json.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.