esscott1/job-search-assistant / skills/job-search-assistant/job-fit-rubric
job-fit-rubric
VerifiedShared scoring rubric for the job-search skills, not run on its own: job-lead-intake-scan, job-lead-tier2-scoring and job-lead-manual-jd-lookup load it whenever they set a Fit Score. Defines the evidence table the model fills in and runs score.py to turn it into a deterministic 1-10 score with a readable breakdown.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.2 KB |
| score.py | script | 6.2 KB |
| test_score.py | script | 3.3 KB |
test_score.py
View on GitHub"""Checks for score.py. Run with: python3 -m pytest -q skills/job-search-assistant/job-fit-rubric"""
import pytest
from score import EvidenceError, score
def req(kind, evidence, text="quoted JD line"):
return {"text": text, "type": kind, "evidence": evidence}
def tier2(arrangement="remote", title="strong", requirements=None):
return {
"mode": "tier2",
"title_seniority": title,
"work_arrangement": arrangement,
"requirements": requirements or [req("required", "strong")] * 4 + [req("preferred", "strong")] * 2,
}
def test_perfect_remote_match_scores_10():
assert score(tier2())["score"] == 10
def test_same_input_same_output():
assert score(tier2()) == score(tier2())
def test_required_items_outweigh_preferred():
missing_required = tier2(requirements=[req("required", "none"), req("preferred", "strong")])
missing_preferred = tier2(requirements=[req("required", "strong"), req("preferred", "none")])
assert score(missing_preferred)["score"] > score(missing_required)["score"]
def test_relocation_capped_at_3_even_for_perfect_match():
result = score(tier2(arrangement="relocation_required"))
assert result["score"] == 3
assert any("relocation" in c for c in result["caps_applied"])
def test_remote_and_commutable_rank_above_relocation():
for arrangement in ("remote", "commutable_onsite", "commutable_hybrid"):
assert score(tier2(arrangement=arrangement))["score"] > score(tier2(arrangement="relocation_required"))["score"]
def test_acceptable_relocation_is_not_capped():
result = score(tier2(arrangement="relocation_acceptable"))
assert result["caps_applied"] == []
assert score(tier2(arrangement="relocation_required"))["score"] < result["score"] <= score(tier2())["score"]
def test_v1_location_names_still_read():
for old, new in (("colorado_onsite", "commutable_onsite"), ("colorado_hybrid", "commutable_hybrid")):
assert score(tier2(arrangement=old))["score"] == score(tier2(arrangement=new))["score"]
def test_low_required_coverage_capped_at_5():
reqs = [req("required", "strong"), req("required", "none"), req("required", "none")] + [req("preferred", "strong")] * 9
assert score(tier2(requirements=reqs))["score"] <= 5
def test_tier1_never_above_8():
assert score({"mode": "tier1", "title_seniority": "strong", "work_arrangement": "remote"})["score"] <= 8
def test_tier1_relocation_still_capped():
assert score({"mode": "tier1", "title_seniority": "strong", "work_arrangement": "relocation_required"})["score"] <= 3
def test_breakdown_names_version_and_caps():
text = score(tier2(arrangement="relocation_required"))["breakdown"]
assert text.startswith("Rubric v") and "relocation max 3" in text
@pytest.mark.parametrize(
"bad",
[
{"mode": "tier2", "title_seniority": "strong", "work_arrangement": "remote", "requirements": []},
{"mode": "tier2", "title_seniority": "great", "work_arrangement": "remote", "requirements": [req("required", "strong")]},
{"mode": "tier1", "title_seniority": "strong", "work_arrangement": "moon"},
{"mode": "tier2", "title_seniority": "strong", "work_arrangement": "remote", "requirements": [req("required", "maybe")]},
],
)
def test_invalid_evidence_rejected(bad):
with pytest.raises(EvidenceError):
score(bad)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |