Jaxon1216/interview-analyzer-skill / skill/project-interview-skill
project-interview-skill
Verified基于项目描述与仓库证据生成目标简历、完整核心源码课程与项目面经,含学习路线、重点难点 HTML 专题和第一人称回答。 适用于项目分析、面试准备、简历亮点和导学材料。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 13.3 KB |
| assets/topic.html | other | 6.4 KB |
| references/examples/bullet-few-shots.md | markdown | 10.5 KB |
| references/examples/oral-style-samples.md | markdown | 4.6 KB |
| references/excellent-resumes/README.md | markdown | 1.6 KB |
| references/excellent-resumes/ai4se-agent-infra.md | markdown | 4.9 KB |
| references/excellent-resumes/deer-flow-harness.md | markdown | 5.4 KB |
| references/excellent-resumes/susu-bullet-template.md | markdown | 6.1 KB |
| references/rules/course-design.md | markdown | 9.3 KB |
| references/rules/html-teaching.md | markdown | 3.3 KB |
| references/rules/internal-terms.md | markdown | 4.6 KB |
| references/rules/interview-rubric.md | markdown | 1.7 KB |
| references/rules/oral-and-resume-patterns.md | markdown | 13.8 KB |
| references/rules/repository-investigation.md | markdown | 6.0 KB |
| references/rules/star-framework.md | markdown | 4.4 KB |
| references/templates/output-templates.md | markdown | 5.7 KB |
| scripts/build_prompt.py | script | 13.5 KB |
| scripts/check_inputs.py | script | 5.2 KB |
| scripts/validate_output.py | script | 12.8 KB |
scripts/check_inputs.py
View on GitHub#!/usr/bin/env python3
"""
Validate project narrative inputs for project-interview-skill.
Reads UTF-8 text from stdin or a file, checks for minimum signal,
and prints suggested follow-up questions in Chinese.
"""
from __future__ import annotations
import argparse
import json
import sys
from dataclasses import asdict, dataclass, field
from pathlib import Path
from typing import Iterable
MIN_DESCRIPTION_CHARS = 40
KEYWORD_HINTS = (
"指标",
"qps",
"延迟",
"用户",
"线上",
"数据",
"规模",
"难点",
"结果",
"职责",
)
@dataclass
class CheckResult:
"""Outcome of input validation."""
ok: bool
missing: list[str] = field(default_factory=list)
suggestions: list[str] = field(default_factory=list)
notes: list[str] = field(default_factory=list)
def _text_length(text: str) -> int:
"""Character count after strip."""
return len(text.strip())
def _has_any_keyword(text: str, keywords: Iterable[str]) -> bool:
lower = text.lower()
for kw in keywords:
if kw.lower() in lower:
return True
return False
def analyze(description: str, tech_stack: str | None, role_focus: str | None) -> CheckResult:
"""
Analyze user-provided fields and return gaps plus follow-up suggestions.
Args:
description: Required project description.
tech_stack: Optional technology list or sentence.
role_focus: Optional job direction (frontend/backend/AI).
Returns:
CheckResult with ok flag, missing topics, and concrete questions.
"""
missing: list[str] = []
suggestions: list[str] = []
notes: list[str] = []
desc_len = _text_length(description)
if desc_len < MIN_DESCRIPTION_CHARS:
missing.append(
f"项目描述过短(当前约 {desc_len} 字符,建议至少 {MIN_DESCRIPTION_CHARS}+ "
"并包含项目目标、机制或难点线索)"
)
if not _has_any_keyword(description, KEYWORD_HINTS) and desc_len < MIN_DESCRIPTION_CHARS * 2:
suggestions.append(
"请补充:项目解决什么问题,最值得掌握的核心机制是什么?"
)
suggestions.append(
"请补充:一个**技术或业务难点**,以及你如何验证「已解决」?"
)
if not tech_stack or not tech_stack.strip():
suggestions.append(
"技术栈未提供:若补充语言/框架/存储/消息/观测栈,面试题会更准。"
)
if not role_focus or not role_focus.strip():
suggestions.append(
"求职方向未指定:默认全栈,按仓库实际技术范围安排课程;可选指定前端或后端。"
)
suggestions.extend(
[
"可选补充一条**完整业务链路**:入口、状态变化、结果与失败边界。",
"若重新做一遍,你会在哪个**设计决策**上改变?为什么?",
"项目中**如何发布与回滚**(灰度、特性开关、数据迁移)?",
]
)
if desc_len >= MIN_DESCRIPTION_CHARS:
notes.append("项目描述长度达标;默认生成目标简历与核心课程,职责和线上指标不作为生成前提。")
ok = len(missing) == 0
return CheckResult(ok=ok, missing=missing, suggestions=suggestions, notes=notes)
def main(argv: list[str] | None = None) -> int:
"""CLI entry point."""
parser = argparse.ArgumentParser(
description="Check project description completeness for project-interview-skill."
)
parser.add_argument(
"-f",
"--file",
help="Read project description from file (UTF-8).",
)
parser.add_argument(
"--tech",
default="",
help="Optional tech stack string.",
)
parser.add_argument(
"--role",
default="",
help="Optional job focus: frontend, backend, AI, etc.",
)
parser.add_argument(
"--json",
action="store_true",
help="Print machine-readable JSON.",
)
args = parser.parse_args(argv)
if args.file:
try:
description = Path(args.file).read_text(encoding="utf-8").strip()
except OSError as exc:
print(f"Error reading file: {exc}", file=sys.stderr)
return 1
else:
description = sys.stdin.read().strip()
if not description:
print("Error: empty description. Pipe text or use --file.", file=sys.stderr)
return 1
tech = args.tech.strip() or None
role = args.role.strip() or None
result = analyze(description, tech, role)
if args.json:
print(json.dumps(asdict(result), ensure_ascii=False, indent=2))
return 0
status = "PASS" if result.ok else "NEEDS_INPUT"
print(f"[{status}] project-interview-skill input check\n")
if result.missing:
print("必须补齐:")
for item in result.missing:
print(f" - {item}")
print()
print("建议追问:")
for q in result.suggestions:
print(f" - {q}")
if result.notes:
print("\n备注:")
for n in result.notes:
print(f" - {n}")
return 0
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: 469k | 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: 321k | 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: 321k | 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: 321k | Updated | Claude CodeCodex | Verified | Install |