esscott1/job-search-assistant / skills/job-search-assistant/tailored-resume-builder
tailored-resume-builder
VerifiedOn demand only, never scheduled: when the user says 'build ticked resumes' (tracker rows ticked in Build Resume), names tracker rows, or pastes a job description: picks the most relevant true content from the user's full resume and renders a .docx and PDF of at most 3 pages (or fewer when the user asks) in the user's own resume style (resume-style.md, or the plugin's default), plus a Google Doc of the same resume saved straight to the job's Drive folder. Never invents experience; reports gaps instead. Not for scoring (that's job-fit-rubric), not for editing the master inventory, and not for setting up the resume style (that's job-search-profile).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 15.9 KB |
| check_content.py | script | 7.7 KB |
| check_doc_text.py | script | 2.6 KB |
| default-style.md | markdown | 1.3 KB |
| extract_style.py | script | 19.8 KB |
| render_resume.py | script | 32.4 KB |
| resume-style-format.md | markdown | 3.5 KB |
| test_check_content.py | script | 6.3 KB |
| test_check_doc_text.py | script | 2.5 KB |
| test_extract_style.py | script | 7.7 KB |
| test_render_resume.py | script | 14.7 KB |
check_content.py
View on GitHub#!/usr/bin/env python3
"""Check a tailored resume's content.json against the full resume before it's delivered.
Usage: check_content.py --inventory Full-Resume.md --content content.json [--today YYYY-MM-DD] [--years 15]
check_content.py --inventory Full-Resume.md
With --inventory alone, it only reads the full resume's work history and prints what it found,
{"ok": bool, "employers": [{"name", "dates", "roles": [{"title", "dates"}]}], "warnings": [...]},
where ok is false when no headings were found. job-search-profile uses this to check a full
resume the user attaches during setup.
Reads the full resume's work history from its headings, one employer per '### Employer | dates'
and one role per '#### Title | dates' under it, and checks that:
- content.json passes render_resume.py's own rules (no company descriptions; every role has at
least one line, a summary or a bullet);
- every employer, role title and date range in content.json matches the full resume;
- every role that ended within the last --years years (15 by default) is on the resume. Older
roles may be left out when they aren't relevant to the job; they're listed in
"omitted_old_roles" so the leaving out can be reported.
With --content, prints JSON: {"ok": bool, "errors": [...], "warnings": [...], "omitted_old_roles": [...]}.
Exit 0 when ok, 1 when there are errors (or, with --inventory alone, no headings), 2 when an input
can't be read.
"""
from __future__ import annotations
import argparse
import datetime as dt
import json
import re
import sys
from dataclasses import dataclass, field
from pathlib import Path
sys.path.insert(0, str(Path(__file__).parent))
from render_resume import content_problems, normalize # noqa: E402
MONTHS = {m: i for i, m in enumerate(
("jan", "feb", "mar", "apr", "may", "jun", "jul", "aug", "sep", "oct", "nov", "dec"), 1)}
ONGOING = ("present", "current", "now")
NO_HEADINGS = "the full resume's work history isn't in '### Employer | dates' and '#### Title | dates' headings"
@dataclass
class Role:
title: str
dates: str
@dataclass
class Employer:
name: str
dates: str
roles: list[Role] = field(default_factory=list)
def parse_inventory(text: str) -> list[Employer]:
"""Employers and their roles, from '### Employer | dates' and '#### Title | dates' headings."""
employers: list[Employer] = []
current = None
for line in text.splitlines():
m = re.match(r"(###|####)\s+(.+?)\s*\|\s*(.+?)\s*$", line)
if m and m.group(1) == "###":
current = Employer(m.group(2), m.group(3))
employers.append(current)
elif m and current:
current.roles.append(Role(m.group(2), m.group(3)))
elif re.match(r"#{1,3}\s", line):
current = None # any other heading ends that employer's roles
return employers
def end_month(dates: str, today: dt.date):
"""(year, month) a date range ends in; year-only ends count as December. None if unreadable."""
end = re.split(r"\s*(?:[-–—]|\bto\b)\s*", dates.strip(), flags=re.I)[-1].strip().lower()
if end in ONGOING:
return today.year, today.month
m = re.fullmatch(r"(?:([a-z]{3})[a-z]*\.?\s+)?(\d{4})", end)
if not m or (m.group(1) and m.group(1) not in MONTHS):
return None
return int(m.group(2)), MONTHS[m.group(1)] if m.group(1) else 12
def is_old(dates: str, today: dt.date, years: int):
"""True when the range ended more than `years` years before today; None if unreadable."""
end = end_month(dates, today)
if end is None:
return None
return end < (today.year - years, today.month)
def starts(full: str, prefix: str) -> bool:
return bool(prefix.strip()) and normalize(full).startswith(normalize(prefix))
def check(inventory: str, content: dict, today: dt.date, years: int) -> dict:
errors = list(content_problems(content))
warnings: list[str] = []
omitted: list[dict] = []
employers = parse_inventory(inventory)
if not employers:
warnings.append(f"history checks skipped: {NO_HEADINGS}")
return dict(ok=not errors, errors=errors, warnings=warnings, omitted_old_roles=omitted)
shown: set[tuple[int, int]] = set() # (employer index, role index) on the resume
for job in content.get("experience", []):
company = job.get("company", "")
matches = [i for i, e in enumerate(employers) if starts(e.name, company)]
if not matches:
warnings.append(f"{company}: not a '###' employer heading in the full resume, so not checked")
continue
exact = [i for i in matches if normalize(employers[i].dates) == normalize(job.get("dates", ""))]
if not exact:
errors.append(f"{company}: dates '{job.get('dates')}' don't match the full resume "
f"('{employers[matches[0]].dates}')")
ei = (exact or matches)[0]
employer = employers[ei]
if not employer.roles:
warnings.append(f"{company}: the full resume lists no '####' roles under it, so its roles aren't checked")
continue
for role in job.get("roles", []):
title = role.get("title", "")
cands = [i for i, r in enumerate(employer.roles) if starts(r.title, title)]
if not cands:
errors.append(f"{title} at {company}: no role with that title in the full resume")
continue
same_dates = [i for i in cands if normalize(employer.roles[i].dates) == normalize(role.get("dates", ""))]
if not same_dates:
errors.append(f"{title} at {company}: dates '{role.get('dates')}' don't match the full resume "
f"('{employer.roles[cands[0]].dates}')")
shown.add((ei, (same_dates or cands)[0]))
for ei, employer in enumerate(employers):
for ri, role in enumerate(employer.roles):
if (ei, ri) in shown:
continue
old = is_old(role.dates, today, years)
where = f"{role.title} at {employer.name} ({role.dates})"
if old is None:
errors.append(f"{where}: left out, and its end date can't be read; keep it or check by hand")
elif old:
omitted.append(dict(company=employer.name, title=role.title, dates=role.dates))
else:
errors.append(f"{where}: left out, but it ended within the last {years} years, so it must stay")
return dict(ok=not errors, errors=errors, warnings=warnings, omitted_old_roles=omitted)
def outline(inventory: str) -> dict:
"""The work history the headings describe, for checking a full resume on its own."""
employers = parse_inventory(inventory)
warnings = [] if employers else [NO_HEADINGS]
warnings += [f"{e.name} ({e.dates}): no '####' roles under it" for e in employers if not e.roles]
return dict(ok=bool(employers), warnings=warnings, employers=[
dict(name=e.name, dates=e.dates, roles=[dict(title=r.title, dates=r.dates) for r in e.roles])
for e in employers])
def main() -> None:
a = argparse.ArgumentParser()
a.add_argument("--inventory", required=True)
a.add_argument("--content")
a.add_argument("--today", type=dt.date.fromisoformat, default=dt.date.today())
a.add_argument("--years", type=int, default=15)
a = a.parse_args()
try:
inventory = Path(a.inventory).read_text(encoding="utf-8")
content = json.loads(Path(a.content).read_text(encoding="utf-8")) if a.content else None
except (OSError, ValueError) as e:
print(json.dumps({"error": str(e)}))
sys.exit(2)
result = outline(inventory) if content is None else check(inventory, content, a.today, a.years)
print(json.dumps(result, ensure_ascii=False))
sys.exit(0 if result["ok"] else 1)
if __name__ == "__main__":
main()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |