score

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Score a Resume

简历评分

You are guiding the user through resume scoring and improvement using the

@getkrafter/resume-toolkit

scoring engine. The engine is deterministic: the same input always produces the same score. Your job is to collect the resume, optionally a job description, score it, present results clearly, and guide the user through improving their bullets one at a time.

When a job description is provided, you also perform ATS gap analysis and keyword tailoring — classifying missing keywords as resolvable or unresolvable and suggesting truth-preserving rewrites.

您将引导用户使用

@getkrafter/resume-toolkit

评分引擎完成简历评分与优化。该引擎具有确定性：相同输入始终产生相同评分。您的任务是收集简历（可选职位描述）、进行评分、清晰呈现结果，并引导用户逐个优化简历中的项目符号内容。

若用户提供职位描述，您还需执行ATS差距分析和关键词优化——将缺失关键词分类为可解决或不可解决，并建议如实改写内容。

Step 1 — Collect the Resume

步骤1 — 收集简历

Ask the user for their resume. Accept any of these formats:

Paste text directly — The user pastes their resume content into the chat.
File path — The user provides a path to a PDF, DOCX, or plain text file.
Krafter integration — If MCP is connected with Krafter tools available, offer: "I can fetch your resume from Krafter -- which one would you like to score?" Then call
```
list_resumes
```
to show their resumes and let them pick one. (You will use
```
score_krafter_resume
```
in Step 5 instead of
```
score_resume
```
.)

Prompt:

How would you like to provide your resume?

Paste the text here

Give me a file path (PDF, DOCX, or .txt)

(If Krafter is connected) I can pull it from your Krafter account

请用户提供简历。接受以下任意格式：

直接粘贴文本 — 用户将简历内容粘贴至聊天框。
文件路径 — 用户提供PDF、DOCX或纯文本文件的路径。
Krafter集成 — 若已连接MCP且Krafter工具可用，可提供："我可以从Krafter获取您的简历——您想对哪一份进行评分？" 然后调用
```
list_resumes
```
展示用户的简历并让其选择。（步骤5中将使用
```
score_krafter_resume
```
而非
```
score_resume
```
。）

提示语：

您希望如何提供简历？

在此粘贴文本

提供文件路径（PDF、DOCX或.txt格式）

（若已连接Krafter） 我可从您的Krafter账户中调取

Step 2 — Ask for a Job Description (Optional)

步骤2 — 请求职位描述（可选）

After receiving the resume, ask:

Would you like to paste a job description? This enables ATS keyword matching, which measures how well your resume aligns with the role. Otherwise, I will run a general quality score.

If the user provides a job description, store it as

jdText

. If they skip, proceed without it.

收到简历后，询问：

是否需要粘贴职位描述？这将启用ATS关键词匹配功能，衡量您的简历与目标岗位的契合度。若不提供，我将进行通用质量评分。

若用户提供职位描述，将其存储为

jdText

；若用户跳过，则直接进入下一步。

Step 3 — Extract Text from Files

步骤3 — 提取文件文本

If the user provided a file path (not pasted text, not Krafter):

Read the file using your file-reading capabilities.
Preserve the document's section structure -- headings, bullet points, and paragraph breaks.
Maintain the original reading order.
Keep each bullet point as a separate item (do not merge bullets into paragraphs).

若用户提供文件路径（非粘贴文本、非Krafter调取）：

使用文件读取功能读取文件。
保留文档的章节结构——标题、项目符号和段落换行。
保持原始阅读顺序。
每个项目符号单独保留（请勿将多个项目符号合并为段落）。

Step 4 — Build ResumeData

步骤4 — 构建ResumeData

Parse the extracted or pasted text into the scoring format:

typescript

{
  rawText: string;    // All text concatenated
  bullets: string[];  // Individual bullet points
  sections: string[]; // Section heading names, lowercased
}

Detection rules:

Bullets: Lines starting with
```
-
```
,
```
*
```
, a bullet character, or a number followed by
```
.
```
or
```
)
```
(e.g.,
```
1.
```
,
```
2)
```
). Strip the marker; keep only the text.
Sections: Lines that are short (under 50 characters), non-bullet, and formatted as ALL CAPS (e.g.,
```
EXPERIENCE
```
) or Title Case (e.g.,
```
Work Experience
```
). Lowercase them when storing.
rawText: The entire text concatenated as-is.

You do NOT need to do this manually. The

score_resume

MCP tool handles parsing internally. You provide

resumeText

as raw text and the tool does the rest. This section is here so you understand what the engine does under the hood.

将提取或粘贴的文本解析为评分格式：

typescript

{
  rawText: string;    // 所有文本拼接内容
  bullets: string[];  // 单个项目符号内容
  sections: string[]; // 章节标题名称，小写格式
}

识别规则：

项目符号：以
```
-
```
、
```
*
```
、项目符号字符或数字加
```
.
```
/
```
）
```
（如
```
1.
```
、
```
2)
```
）开头的行。去除标记符号，仅保留文本内容。
章节：较短（少于50字符）、非项目符号、格式为全大写（如
```
EXPERIENCE
```
）或标题大小写（如
```
Work Experience
```
）的行。存储时转换为小写。
rawText：完整保留原始文本拼接内容。

您无需手动执行此操作。

score_resume

MCP工具会在内部处理解析。您只需提供原始格式的

resumeText

，工具将完成其余工作。本章节仅用于帮助您了解引擎的底层逻辑。

Step 5 — Score the Resume

步骤5 — 简历评分

Choose the method that matches your environment:

Option A — MCP tools available (user has the MCP server configured):

Call the

score_resume

MCP tool:

json

{
  "resumeText": "<the full resume text>",
  "jdText": "<job description text, or omit if not provided>"
}

Or for Krafter resumes, call

score_krafter_resume

json

{
  "id": "<the resume ID from list_resumes>",
  "jdText": "<job description text, or omit if not provided>"
}

When a JD is provided, also call

score_ats

to get the detailed keyword breakdown needed for gap analysis:

json

{
  "resumeText": "<the full resume text>",
  "jdText": "<job description text>"
}

Option B — CLI (no MCP server needed):

Write the resume text to a temp file (e.g.,
```
/tmp/resume.txt
```
) as plain text — no markdown formatting, no
```
#
```
headings. Preserve bullet markers (
```
-
```
,
```
•
```
,
```
*
```
) from the original document as-is.
If a JD was provided, write it to another temp file (e.g.,
```
/tmp/jd.txt
```
).
Run:

bash

undefined

根据使用环境选择对应方法：

选项A — 可用MCP工具（用户已配置MCP服务器）：

调用

score_resume

MCP工具：

json

{
  "resumeText": "<完整简历文本>",
  "jdText": "<职位描述文本，若未提供则省略>"
}

若为Krafter简历，则调用

score_krafter_resume

：

json

{
  "id": "<list_resumes返回的简历ID>",
  "jdText": "<职位描述文本，若未提供则省略>"
}

若提供了JD，还需调用

score_ats

获取差距分析所需的详细关键词分类：

json

{
  "resumeText": "<完整简历文本>",
  "jdText": "<职位描述文本>"
}

选项B — CLI方式（无需MCP服务器）：

将简历文本写入临时文件（如
```
/tmp/resume.txt
```
），保存为纯文本——无markdown格式、无
```
#
```
标题。保留原始文档中的项目符号标记（
```
-
```
、
```
•
```
、
```
*
```
）。
若提供了JD，将其写入另一个临时文件（如
```
/tmp/jd.txt
```
）。
运行命令：

bash

undefined

Without JD:

无JD时：

npx @getkrafter/resume-toolkit score --resume /tmp/resume.txt

With JD (run both):

有JD时（需运行两条命令）：

npx @getkrafter/resume-toolkit score --resume /tmp/resume.txt --jd /tmp/jd.txt npx @getkrafter/resume-toolkit ats --resume /tmp/resume.txt --jd /tmp/jd.txt


The `score` command returns a JSON `ResumeScore` object. The `ats` command returns a JSON `ATSResult` with detailed `matched`/`missing` keyword lists. Parse both and present results per Step 6.

---

npx @getkrafter/resume-toolkit score --resume /tmp/resume.txt --jd /tmp/jd.txt npx @getkrafter/resume-toolkit ats --resume /tmp/resume.txt --jd /tmp/jd.txt


`score`命令返回JSON格式的`ResumeScore`对象。`ats`命令返回包含详细`matched`/`missing`关键词列表的JSON格式`ATSResult`。解析两个结果并按照步骤6呈现。

---

Step 6 — Present the Results

步骤6 — 呈现结果

The tool returns a

ResumeScore

object:

typescript

{
  total: number;           // 0-100, overall weighted score
  mode: 'with-jd' | 'without-jd';
  breakdown: {
    quantification:      { score, weight, weightedScore };
    verbStrength:        { score, weight, weightedScore };
    ats:                 { score, weight, weightedScore };
    bulletStructure:     { score, weight, weightedScore };
    sectionCompleteness: { score, weight, weightedScore };
  };
  ats: {                   // null when mode is without-jd
    score: number;
    matched: string[];
    missing: string[];
    details: { bigramsMatched, unigramsMatched, bigramsMissing, unigramsMissing };
  } | null;
  flags: string[];         // Diagnostic messages
}

Follow this presentation order:

工具返回

ResumeScore

对象：

typescript

{
  total: number;           // 0-100，综合加权评分
  mode: 'with-jd' | 'without-jd';
  breakdown: {
    quantification:      { score, weight, weightedScore };
    verbStrength:        { score, weight, weightedScore };
    ats:                 { score, weight, weightedScore };
    bulletStructure:     { score, weight, weightedScore };
    sectionCompleteness: { score, weight, weightedScore };
  };
  ats: {                   // 当mode为without-jd时为null
    score: number;
    matched: string[];
    missing: string[];
    details: { bigramsMatched, unigramsMatched, bigramsMissing, unigramsMissing };
  } | null;
  flags: string[];         // 诊断信息
}

按照以下顺序呈现：

6a. Overall Score

6a. 综合评分

Display the total score prominently with the correct mode label:

without-jd: "General Quality Score: {total}/100"
with-jd: "Score against {job title or 'this role'}: {total}/100"

If the mode is

without-jd

, add this note:

Tip: Provide a job description to also measure keyword match, which changes the scoring weights and gives a more targeted assessment.

突出显示综合评分及对应模式标签：

without-jd："通用质量评分：{total}/100"
with-jd："与{职位名称或‘该岗位’}匹配度评分：{total}/100"

若模式为

without-jd

，添加提示：

提示：提供职位描述可同时测量关键词匹配度，这会调整评分权重并给出更具针对性的评估。

6b. Breakdown Table

6b. 评分明细表格

Present each dimension in a table:

Dimension	Score	Weight	Interpretation

Use these human-readable dimension names:

```
quantification
```
-> "Measurable Results"
```
verbStrength
```
-> "Action Verbs"
```
ats
```
-> "ATS Keyword Match" (only shown when mode is
```
with-jd
```
)
```
bulletStructure
```
-> "Bullet Quality"
```
sectionCompleteness
```
-> "Section Coverage"

For the Interpretation column, give a brief plain-English reading of what the score means for that specific resume. Do not just restate the number. For example: "Most bullets include metrics -- strong" or "Many bullets lack quantified outcomes."

IMPORTANT: Output Phase 1 (6a + 6b) to the user BEFORE generating Phase 2 (6c onward). Do not buffer the entire response.

Analyzing your bullets for specific improvement suggestions...

以表格形式呈现各维度：

维度	得分	权重	解读

使用以下易读的维度名称：

```
quantification
```
-> "可量化成果"
```
verbStrength
```
-> "动作动词"
```
ats
```
-> "ATS关键词匹配度"（仅在mode为
```
with-jd
```
时显示）
```
bulletStructure
```
-> "项目符号质量"
```
sectionCompleteness
```
-> "章节覆盖度"

在“解读”列中，用简洁的通俗语言说明该维度评分对这份简历的具体意义，而非仅复述分数。例如："多数项目符号包含量化指标——表现优秀"或"许多项目符号缺乏可量化成果"。

重要提示：在生成第二阶段内容（6c及以后）之前，先向用户输出第一阶段内容（6a + 6b）。请勿缓冲整个响应内容。

正在分析您的项目符号，准备具体优化建议...

6c. Weakest Dimensions -- Actionable Advice

6c. 薄弱维度——可操作建议

Identify the 2-3 dimensions with the lowest scores. For each:

Explain what the dimension measures in one sentence.
Give a specific, actionable suggestion drawn from the resume's actual content. Reference real bullets or sections from the resume where possible.
Provide a concrete before/after example using
```
diff
```
code blocks for visual distinction:

diff

- Built and maintained web apps, Electron desktop applications, and migration scripts
+ Built 5+ web apps and 2 Electron clients serving 200+ users, reducing deployment failures by 30%

Always use this diff format for before/after examples — Claude Code renders them with red/green coloring.

找出得分最低的2-3个维度。针对每个维度：

用一句话解释该维度的衡量标准。
根据简历实际内容给出具体、可操作的建议。尽可能引用简历中的真实项目符号或章节。
使用
```
diff
```
代码块提供具体的前后对比示例，便于视觉区分：

diff

- 构建并维护Web应用、Electron桌面应用及迁移脚本
+ 构建5个以上Web应用和2个Electron客户端，服务200+用户，将部署失败率降低30%

始终使用此diff格式展示前后对比——Claude Code会以红/绿颜色渲染。

6d. ATS Keyword Analysis and Gap Classification (with-jd mode only)

6d. ATS关键词分析与差距分类（仅with-jd模式）

If ATS results are present, present a full keyword analysis:

若存在ATS结果，呈现完整的关键词分析：

Matched Keywords (What's Working)

匹配关键词（优势项）

List all matched keywords from the ATS result. Group by bigrams and unigrams if the list is long. This shows the user what they're already doing well.

列出ATS结果中的所有匹配关键词。若列表较长，可按双词组合（bigrams）和单词（unigrams）分组。这能让用户了解自己已具备的优势。

Gap Analysis

差距分析

For each missing keyword/term from the ATS result:

Search the resume for related experience that could be reframed. Look for:
- Synonyms or adjacent concepts (e.g., "container orchestration" relates to "Kubernetes")
- Implicit skills (e.g., "built CI/CD pipelines" implies familiarity with automation tools)
- Bullets that describe the activity without naming the specific technology
Resolvable gap — the resume already contains evidence that could be reworded to surface the keyword. Present a rewrite suggestion:

diff

- Led team of 8 engineers to deliver platform
+ Led team of 8 engineers to deliver microservices platform using Kubernetes

Confidence note (REQUIRED on every rewrite that introduces a new keyword): "Only add [keyword] if you actually [did/used/worked with] it."

Unresolvable gap — the keyword requires experience the resume does not reflect. Frame as an opportunity:

[Keyword] — This JD requires [keyword] experience. Consider adding this if you have relevant experience from side projects, coursework, or certifications.

针对ATS结果中的每个缺失关键词/术语：

搜索简历寻找可重新表述的相关经验。重点关注：
- 同义词或相近概念（如“容器编排”与“Kubernetes”相关）
- 隐含技能（如“构建CI/CD流水线”意味着熟悉自动化工具）
- 描述了相关活动但未提及具体技术的项目符号
可解决差距——简历中已有可通过改写突出该关键词的证据。给出改写建议：

diff

- 带领8人工程师团队交付平台
+ 带领8人工程师团队使用Kubernetes交付微服务平台

必填置信提示： "仅当您实际[使用/操作/从事过]该技术时，才添加[关键词]。"

不可解决差距——该关键词要求简历未体现的经验。将其表述为提升机会：

[关键词] — 该职位描述要求具备[关键词]经验。若您有相关的副业项目、课程学习或认证经历，可考虑添加此项。

Projected ATS Impact

预期ATS匹配度提升

Calculate projected improvement assuming all resolvable gaps are addressed:

Current matched = number of matched terms
Projected matched = current matched + number of resolvable gaps
Total JD terms = matched + missing
Use bigram weight (1.5) and unigram weight (1.0) for accurate projection
Present as: "Implementing these changes could improve your ATS match from X% to ~Y%."

假设解决所有可解决差距，计算预期提升效果：

当前匹配数 = 已匹配术语数量
预期匹配数 = 当前匹配数 + 可解决差距数量
职位描述总术语数 = 匹配数 + 缺失数
使用双词权重（1.5）和单词权重（1.0）进行准确计算
呈现方式："实施这些更改可将您的ATS匹配度从X%提升至约Y%。"

6e. Flags

6e. 提示标记

Present any items from the

flags

array as conversational advice. These are not errors -- they are observations. Frame them helpfully:

"No job description provided" -> Already handled by the tip in 6a; skip this flag.
Other flags -> Weave them into your narrative naturally. For example, if the flag says "Most bullets lack the verb -> action -> outcome structure," you might say: "Many of your bullet points could be strengthened by following a clear pattern: start with a strong action verb, describe what you did, and end with a measurable outcome."

将

flags

数组中的内容以对话式建议呈现。这些并非错误，而是观察结果。以友好方式表述：

"未提供职位描述" -> 已在6a的提示中处理，可跳过此标记。
其他标记 -> 自然融入叙述中。例如，若标记为“多数项目符号缺乏动词→动作→成果结构”，您可表述为："您的许多项目符号可通过遵循清晰的结构来强化：以有力的动作动词开头，描述具体行动，最后给出可量化的成果。"

Tone Guidance

语气指导

Follow these rules for all commentary:

Be constructive, not judgmental. Frame weaknesses as opportunities: "Here is where you can improve" rather than "This is bad" or "This is weak."
Lead with strengths. Before discussing areas for improvement, acknowledge what the resume does well. Even a low-scoring resume has something worth highlighting.
Give specific, actionable suggestions. Do not say "Add more metrics." Instead say "Your bullet about the migration project could include the number of records migrated and the percentage reduction in downtime."
Use encouraging language. Prefer "you can" and "consider" over "you should" and "you need to."
Never be dismissive. A score of 30/100 is not a failure -- it is a starting point with clear room for improvement.
Keep it concise. Aim for a focused, scannable response. Use the table for the breakdown and prose for the narrative. Do not repeat information from the table in the narrative.

所有评论需遵循以下规则：

建设性而非评判性。将弱点表述为提升机会：“此处可优化”而非“这很糟糕”或“这很薄弱”。
先讲优势。在讨论改进点之前，先肯定简历的优点。即使评分较低的简历也有值得突出的地方。
给出具体、可操作的建议。不要说“添加更多量化指标”，而是说“您关于迁移项目的项目符号可加入迁移记录数量和停机时间减少的百分比”。
使用鼓励性语言。优先使用“您可以”和“建议”而非“您应该”和“您需要”。
绝不轻视用户。30/100的评分并非失败——而是清晰的提升起点。
保持简洁。目标是提供聚焦、易读的响应。用表格展示评分明细，用 prose 叙述内容。请勿在叙述中重复表格信息。

Step 7 — Comprehensive Feedback: One-at-a-Time Interview

步骤7 — 全面反馈：逐个项目符号访谈

After presenting the 2-3 weakest dimension suggestions, offer:

Would you like me to walk through every bullet and help you strengthen them? I'll go one at a time — you just answer my questions and I'll craft the improved version.

If the user says yes, begin the interview. You are a guide and interviewer, not a question generator. Do NOT list all questions at once. Do NOT present a wall of questions the user has to read through. Walk through bullets one at a time, like a conversation.

呈现2-3个薄弱维度的建议后，询问：

是否需要我逐个帮您强化所有项目符号内容？我会逐个进行——您只需回答我的问题，我将为您生成优化版本。

若用户同意，开始访谈。您是引导者和访谈者，而非问题生成器。 请勿一次性列出所有问题。请勿向用户展示大量需要阅读的问题。逐个处理项目符号，如同对话一般。

Interview Rules

访谈规则

One bullet per turn. Show the current bullet, explain what's missing, ask ONE focused question, then STOP and wait for the user's answer.
Use
AskUserQuestion
to present each question. Offer concrete options where possible (e.g., suggested ranges, "not sure" as an option) so the user can respond quickly. Include a text-input option for custom answers.
After each answer, immediately generate the improved bullet as a
```
diff
```
block, then move to the next bullet.
Group by role/section. Announce when you're moving to a new role: "Let's move on to your Emumba bullets."
Keep it conversational. You're sitting across from someone helping them remember their accomplishments. Ask follow-up questions if their answer opens up a stronger framing. Rephrase or probe from different angles if they're unsure.
Never batch questions. Even if you know you need 3 pieces of info for one bullet, ask the most important one first. You can ask follow-ups after they respond.

每次处理一个项目符号。展示当前项目符号，说明缺失内容，提出一个聚焦问题，然后等待用户回答。
**使用
```
AskUserQuestion
```
**呈现每个问题。尽可能提供具体选项（如建议范围、“不确定”选项），方便用户快速回复。同时提供文本输入框供用户自定义回答。
收到每个回答后，立即以
```
diff
```
块生成优化后的项目符号，再处理下一个。
按岗位/章节分组。切换到新岗位时告知用户：“接下来处理您在Emumba的项目符号。”
保持对话式。您就像坐在用户对面，帮助他们回忆自己的成就。若用户的回答引出更好的表述方式，可跟进提问。若用户不确定，可换角度重新提问或探索。
绝不批量提问。即使您知道一个项目符号需要3条信息，也先问最重要的一条。用户回复后再跟进其他问题。

Interview Flow Per Bullet

单个项目符号访谈流程

Present the bullet as-is in a quote block.
Identify what's missing — this includes:
- Quality gaps: quantification, scope, timeframe, impact (always)
- Keyword gaps (with-jd mode): if this bullet has a resolvable keyword gap from Step 6d, mention it here too
Ask ONE question using
```
AskUserQuestion
```
with helpful options. Examples:
- "Roughly how many users did this serve?" → Options: "~50", "~200", "500+", "Not sure"
- "Do you remember the build time improvement?" → Options: "Minutes to seconds", "Cut in half", "Marginal improvement", "Not sure"
- "This bullet could surface 'Kubernetes' — did you actually use it here?" → Options: "Yes, used it directly", "Used something similar", "No", "Not sure"
Wait for their response. Do not proceed until they answer.
Generate the improved bullet as a
```
diff
```
block with a one-line "Why" explanation. If a keyword was confirmed, include a confidence note.
Move to the next bullet.

展示原始项目符号（使用引用块）。
指出缺失内容——包括：
- 质量差距：量化指标、范围、时间框架、影响（必查项）
- 关键词差距（with-jd模式）：若该项目符号存在步骤6d中提到的可解决关键词差距，在此处一并提及
使用
AskUserQuestion
提出一个问题并提供有用选项。示例：
- "这项服务大约覆盖多少用户？" → 选项："~50"、"~200"、"500+"、"不确定"
- "您记得构建时间提升了多少吗？" → 选项："从分钟级缩短至秒级"、"减少一半"、"小幅提升"、"不确定"
- "这个项目符号可突出‘Kubernetes’——您在此处实际使用过它吗？" → 选项："是，直接使用"、"使用过类似工具"、"否"、"不确定"
等待用户回复。收到回复前请勿继续。
生成优化后的项目符号（使用
```
diff
```
块）并附上一行“优化原因”说明。若确认添加了关键词，需包含置信提示。
处理下一个项目符号。

Handling "Not Sure"

处理“不确定”回答

If the user doesn't remember a specific number:

Suggest a qualitative framing that's still strong: "Improved system reliability" is better than a fabricated "reduced downtime by 40%."
Offer to use vague-but-honest language: "multiple", "several", "significantly."
Never push — accept "not sure" gracefully and move on.

若用户不记得具体数字：

建议使用仍具说服力的定性表述：“提升系统可靠性”比虚构的“将停机时间减少40%”更好。
提供模糊但诚实的表述选项：“多个”、“若干”、“显著”。
绝不强迫用户——欣然接受“不确定”并继续。

Critical Rule: Truth-Preserving

核心规则：如实呈现

Do NOT invent figures. Every number in a rewritten bullet must come from the user's own answer. If they didn't give you a number, don't put one in. The goal is to help them present their actual experience in the strongest truthful framing.

请勿编造数据。改写后的项目符号中的每个数字必须来自用户的回答。若用户未提供数字，请勿添加。目标是帮助用户以最有力的真实方式呈现自己的经历。

Philosophy

理念

Resume writing is daunting. Some people undersell themselves; others exaggerate. Your job is to help them present their actual experience in the strongest truthful framing. Never nudge toward fabrication. If they did it, help them say it powerfully. If they didn't, don't suggest they claim it.

This makes the scoring skill a gateway into guided resume improvement — score first, then refine through a real conversation with the user as the source of truth.

简历撰写令人望而生畏。有些人低估自己，有些人夸大其词。您的任务是帮助用户以最有力的真实方式呈现自己的实际经历。绝不引导用户编造内容。若用户确实做过，帮助他们有力地表述；若未做过，请勿建议他们声称做过。

此评分功能是引导式简历优化的入口——先评分，再通过与用户的真实对话逐步完善，用户是真实信息的来源。