chengzicv/chengzicv-career-skills / chengzicv-job-greeting
chengzicv-job-greeting
Verified为 BOSS 直聘、猎聘、拉勾、脉脉等招聘平台生成初次打招呼、回复推进、岗位澄清、已读不回跟进和被拒反馈询问,也可基于已确认履历生成候选人专属投递侧指南。正式邮件求职信不使用本 Skill。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.2 KB |
| agents/openai.yaml | config | 327 B |
| assets/greeting-guide-template.html | other | 10.7 KB |
| references/application-side-guide.md | markdown | 8.3 KB |
| references/delivery-contract.md | markdown | 6.7 KB |
| references/follow-up-playbook.md | markdown | 12.0 KB |
| references/methodology.md | markdown | 14.6 KB |
| references/module-library.md | markdown | 3.7 KB |
| scripts/preview_audit.py | script | 4.5 KB |
scripts/preview_audit.py
View on GitHub#!/usr/bin/env python3
"""Internally audit recruiter-platform opening signals and chosen length limits."""
from __future__ import annotations
import argparse
import json
import re
import sys
FORBIDDEN_OPENINGS = (
"您好",
"你好",
"我是",
"看到贵司岗位",
"看到你们在招",
"对贵公司感兴趣",
"想应聘",
)
# 文风提示用的词表:只提示,不影响 passed。
FORMAL_WORDS = ("主导", "负责", "现任", "具备", "熟悉", "降至", "完成", "对接", "落地", "累计", "其中")
ORAL_WORDS = ("哦", "~", "~", "吧", "呢", "呀", "啦", "想了解了解", "都是我")
SELF_EVAL_WORDS = ("具备", "熟悉", "擅长", "精通", "能力强", "非常感兴趣", "经验丰富")
CJK = r"[一-鿿]"
LATIN = r"[A-Za-z]"
URL = re.compile(r"(https?://\S+|[\w.-]+\.(com|cn|io|net|org)(/\S*)?)")
LONG_SENTENCE = 45
def style_hints(text: str) -> list[str]:
"""返回文风提示:语气混用、数字格式、中英文间距、自评词、句长。"""
hints: list[str] = []
body = URL.sub("", text)
formal = sum(body.count(w) for w in FORMAL_WORDS)
# 句末单个波浪号是允许的软化写法(发给 HR 的默认结尾),不算口语混用。
checked = body.rstrip()
if checked.endswith(("~", "~")) and checked.count("~") + checked.count("~") == 1:
checked = checked[:-1]
oral = [w for w in ORAL_WORDS if w in checked]
if formal >= 2 and oral:
hints.append(f"书面正文里混了口语词:{'、'.join(oral)},全篇保持一种语气")
loose_numbers = re.findall(r"\d+(?:\.\d+)?\s*[wWkK](?![A-Za-z])|\d[\d,]*\s+\+|\d+\s*/\s*\d+", body)
if loose_numbers:
hints.append(f"数字写法像随手记:{'、'.join(loose_numbers)},改成“15 万元”“第 3 名 / 共 92 支”这类完整写法")
spaced = len(re.findall(f"{CJK} +{LATIN}|{LATIN} +{CJK}", body))
tight = len(re.findall(f"{CJK}{LATIN}|{LATIN}{CJK}", body))
if spaced and tight:
hints.append(f"中英文之间的空格时有时无(有空格 {spaced} 处、无空格 {tight} 处),统一一种")
self_eval = [w for w in SELF_EVAL_WORDS if w in body]
if len(self_eval) >= 2:
hints.append(f"自评词偏多:{'、'.join(self_eval)},能换成动作或结果就换")
sentences = [s for s in re.split(r"[。!?!?]", body) if s.strip()]
if sentences:
avg = sum(len(re.sub(r"\s", "", s)) for s in sentences) / len(sentences)
if avg > LONG_SENTENCE:
hints.append(f"平均句长约 {avg:.0f} 字,读的人要换好几口气,考虑拆句或拆成短消息气泡")
return hints
def audit(text: str, preview_length: int, max_length: int) -> dict[str, object]:
normalized = text.strip()
preview = normalized[:preview_length]
forbidden = next(
(item for item in FORBIDDEN_OPENINGS if normalized.startswith(item)), None
)
return {
"text": normalized,
"preview": preview,
"preview_length": len(preview),
"character_count": len(normalized),
"max_length": max_length,
"within_limit": len(normalized) <= max_length,
"forbidden_opening": forbidden,
"style_hints": style_hints(normalized),
"passed":bool(normalized)
and len(preview) == min(preview_length, len(normalized))
and len(normalized) <= max_length
and forbidden is None,
}
def parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser(
description="Check preview text, total Unicode characters, and weak openings."
)
parser.add_argument(
"--text",
action="append",
help="Greeting to audit. Repeat for multiple greetings; stdin is used if omitted.",
)
parser.add_argument("--preview-length", type=int, default=15)
parser.add_argument("--max-length", type=int, default=120)
return parser.parse_args()
def main() -> int:
args = parse_args()
if args.preview_length <= 0 or args.max_length <= 0:
raise SystemExit("preview and maximum lengths must be positive")
texts = args.text if args.text else [line for line in sys.stdin.read().splitlines() if line]
if not texts:
raise SystemExit("provide --text or at least one non-empty stdin line")
results = [audit(text, args.preview_length, args.max_length) for text in texts]
print(json.dumps(results, ensure_ascii=False, indent=2))
return 0 if all(item["passed"] for item in results) else 1
if __name__ == "__main__":
raise SystemExit(main())
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 |