Back to Details

asu-resume-skill

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

ASU 式真实技术履历生成 Skill

ASU-style Real Technical Resume Generation Skill

生成“第一眼信息量爆炸，第二眼仍能逐条对应真实经历”的中文技术履历。默认面向小红书长图、技术主页和内部展示；用户明确要求求职版时，降低戏剧化措辞并保留相同事实
Generate Chinese technical resumes that are "information-dense at first glance, and still correspond to real experiences item by item on second glance". Default for Xiaohongshu long images, technical homepages and internal displays; when users explicitly request a job-seeking version, reduce dramatic wording while retaining the same facts

默认交付

Default Deliverables

  1. resume-data.json
    ：真实来源驱动的结构化履历。
  2. resume.html
    ：自包含、适合浏览器长图截图的网页。
  3. resume.pdf
    ：2–3 页 A4 PDF。
  4. xiaohongshu-copy.md
    ：基于真实经历的发布配文。
  1. resume-data.json
    : Structured resume driven by real sources.
  2. resume.html
    : Self-contained webpage suitable for full-page browser screenshots.
  3. resume.pdf
    : 2–3 page A4 PDF.
  4. xiaohongshu-copy.md
    : Publishing copy based on real experiences.

生成原则

Generation Principles

真实骨架直接保留

Retain Real Skeleton Directly

用户授权提供的以下信息可以原样使用：
  • 姓名、学校、学位、公司、部门、岗位和日期；
  • 真实项目名、技术方案、论文/专利/分享；
  • 文档中明确出现且口径可解释的指标；
  • 用户本人对内部职责的一手陈述。
不要自动把真实名称改成“某公司”“某学校”，也不要在每项后添加“虚构”。只有用户要求匿名化时才替换。
The following information authorized by users can be used as-is:
  • Name, school, degree, company, department, position and dates;
  • Real project names, technical solutions, papers/patents/shares;
  • Metrics clearly stated in documents with interpretable caliber;
  • First-hand statements from users about internal responsibilities.
Do not automatically change real names to "a certain company" or "a certain school", nor add "fictional" after each item. Only replace when users request anonymization.

只增强表达，不创造事实

Only Enhance Expression, Do Not Create Facts

允许：
  • 把真实技术过程整理成 
    输入 -> 表征 -> 规划 -> 工具 -> 状态 -> 评测
    链路；
  • 将同一项目里的真实模型、框架、训练策略和部署组件集中呈现；
  • 使用 
    Workflow / ReAct / Harness / Context Engineering / Benchmark / ModelOps
    等与项目相符的术语；
  • 用“从模型节点到 Agent 系统再到长程续跑”等宏观主线概括真实演进；
  • 通过标题、排比、节奏和技术名词密度制造幽默反差。
禁止：
  • 增加不存在的学历、Title、Offer、薪资、项目、开源角色或业务结果；
  • 把 
    参与
    改成 
    主导/Owner/核心作者
    ；
  • 把规划中的工作写成已经落地；
  • 改写原始分母或把不同指标相加；
  • 用公司、项目 Star 或团队成果暗示个人完成全部结果。
Allowed:
  • Organize real technical processes into 
    Input -> Representation -> Planning -> Tools -> State -> Evaluation
    links;
  • Concentrate real models, frameworks, training strategies and deployment components from the same project;
  • Use terms consistent with the project such as 
    Workflow / ReAct / Harness / Context Engineering / Benchmark / ModelOps
    ;
  • Summarize real evolution with macro mainlines like "from model nodes to Agent systems to long-term continuous operation";
  • Create humorous contrast through titles, parallelism, rhythm and density of technical terms.
Prohibited:
  • Add non-existent educational backgrounds, titles, offers, salaries, projects, open-source roles or business results;
  • Change "participated" to "led/Owner/core author";
  • Present planned work as implemented;
  • Rewrite original denominators or add different metrics together;
  • Use company, project stars or team achievements to imply personal completion of all results.

角色强度按来源写

Write Role Strength According to Sources

  • 来源写“独立负责” → 优先写 
    模块级 Owner / 端到端链路 Owner / 从 0→1
    ，同时限定到具体模块；
  • 来源写“主要负责” → 可写 
    策略架构 Owner / 方向负责人
    ，正文保留具体责任边界；
  • 来源写“参与推进/共建” → 写成 
    系统级共建者 / 核心参与者
    ，不伪造为全局 Owner；
  • 来源写“计划/未来方向” → 标成 
    当前方向 / 规划中
    ，不能改成上线结果。
每个重点项目都要先做一次“Owner 化拆分”：寻找本人真正独立完成或主要负责的最小闭环，例如 
数据治理链路
、
策略架构
、
量化部署
、
分布诊断
。可对这个闭环使用 Owner 和 0→1，但不能把词的作用域外扩到整个公司平台。
  • Source states "independently responsible" → Prioritize writing 
    module-level Owner / end-to-end link Owner / from 0→1
    , while limiting to specific modules;
  • Source states "mainly responsible" → Can write 
    strategy architecture Owner / direction leader
    , with specific responsibility boundaries retained in the main text;
  • Source states "participated in promotion/co-construction" → Write as 
    system-level co-builder / core participant
    , do not forge as global Owner;
  • Source states "plan/future direction" → Mark as 
    current direction / in planning
    , cannot be changed to launched results.
Each key project must first undergo an "Ownerization split": find the smallest closed loop that the user truly independently completed or was mainly responsible for, such as 
data governance link
, 
strategy architecture
, 
quantitative deployment
, 
distribution diagnosis
. Owner and 0→1 can be used for this closed loop, but the scope of these terms cannot be expanded to the entire company platform.

学校 Title 增强

School Title Enhancement

对教育经历必须查学校官网、教育主管部门或正式高校联盟页面，提取真实但高势能的机构标签：
  • 建设序列：
    双一流 / 原 211 / 部市共建 / 研究型大学
    ；
  • 历史定位：
    本国第一所大学 / 创校年份
    ；
  • 高校联盟：
    Group of Eight / C9 / Russell Group
    等真实成员关系；
  • 学位事实：本科、硕士、联合培养和学位授予方必须分开，不能把地理位置或合作项目写成不存在的学位。
标题采用 
学校名｜机构 Title 1｜机构 Title 2｜学位
，把来源 URL 写入 
source_note
。不得将澳洲学历写成“美本”，也不得把部市共建写成“中央部委直属”。
For educational experiences, must check school official websites, education authorities or formal university alliance pages to extract real but high-potential institutional labels:
  • Construction sequence: 
    Double First-Class / Former 211 / Jointly Built by Ministry and Municipality / Research University
    ;
  • Historical positioning: 
    First university in the country / Founding year
    ;
  • University alliances: Real membership relations such as 
    Group of Eight / C9 / Russell Group
    ;
  • Degree facts: Undergraduate, master's, joint training and degree-granting institutions must be separated, cannot write geographical location or cooperation projects as non-existent degrees.
The title adopts 
School Name | Institutional Title 1 | Institutional Title 2 | Degree
, and write the source URL into 
source_note
. Do not write Australian degrees as "US undergraduate", nor write jointly built by ministry and municipality as "directly under central ministries".

视觉与措辞

Visuals and Wording

生成前阅读 
references/style-guide.md
。必须具备：
  • 蓝色衬线分区标题、浅红/浅蓝/浅绿经历条；
  • 公司、部门、日期、方向标签同一行；
  • 项目固定使用“背景 / 指标与效果 / 我的职责 / 技术关键词”；
  • 每个重点项目至少 5–10 个与来源一致的专业术语；
  • 能从来源成立的项目必须出现限定 Scope 的 
    Owner
    、
    0→1
    与端到端闭环；不能成立时改用 
    共建者/核心参与者
    ；
  • 责任 bullet 优先使用技术链、失败分类、数据闭环或架构演进；
  • 教育、实习/工作、技术项目与沉淀、奖项与技能等完整分区；
  • 不添加水印、免责声明或“虚构”标记。
Read 
references/style-guide.md
before generation. Must have:
  • Blue serif section titles, light red/light blue/light green experience bars;
  • Company, department, date, direction tags on the same line;
  • Projects fixed use "Background / Metrics and Effects / My Responsibilities / Technical Keywords";
  • Each key project has at least 5–10 professional terms consistent with the source;
  • Projects that can be established from the source must include 
    Owner
    , 
    0→1
    and end-to-end closed loop with limited Scope; if not applicable, use 
    co-builder/core participant
    instead;
  • Responsibility bullets prioritize using technical chains, failure classification, data closed loops or architecture evolution;
  • Complete sections such as education, internship/work, technical projects and precipitation, awards and skills;
  • Do not add watermarks, disclaimers or "fictional" marks.

工作流

Workflow

1. 完整读取经历来源

1. Complete Reading of Experience Sources

读取用户提供的简历、飞书文档、截图或个人主页。长文档先取目录，再按章节完整读取。对每段经历记录：
  • 事实身份：组织、部门、岗位、日期；
  • 角色边界：独立负责、主要负责、参与或规划；
  • 项目目标、技术难点、方案链路；
  • 指标、基线、结果与时间窗口；
  • 模型、框架、训练、部署、数据与评测术语；
  • 分享、专利、奖项和公开材料。
对每所学校额外检索官网、教育主管部门和正式高校联盟页，形成 
Title -> 官方原文 -> URL
三列事实表，再选择 2–4 个最强且不重复的标签进入简历。
Read resumes, Feishu documents, screenshots or personal homepages provided by users. For long documents, first take the table of contents, then read completely by chapter. Record for each experience:
  • Factual identity: Organization, department, position, dates;
  • Role boundaries: Independently responsible, mainly responsible, participated or planned;
  • Project objectives, technical difficulties, solution links;
  • Metrics, baselines, results and time windows;
  • Model, framework, training, deployment, data and evaluation terms;
  • Shares, patents, awards and public materials.
For each school, additionally search official websites, education authorities and formal university alliance pages to form a three-column fact table of 
Title -> Official Original Text -> URL
, then select 2–4 strongest and non-repetitive tags to include in the resume.

2. 建立来源映射

2. Establish Source Mapping

每个可见 bullet 使用：
json
{
  "text": "通过结构化短 COT、真实执行 GRPO 与 AWQ 量化构建 NL2SQL 训练部署链路。",
  "verification": "source_grounded",
  "source_note": "晋升文档 / NL2SQL 章节"
}
文档中没有的内容不得补写。若是用户口述但无法公开核验，使用 
verification: user_attested
。
Each visible bullet uses:
json
{
  "text": "Build NL2SQL training and deployment link through structured short COT, real execution GRPO and AWQ quantization.",
  "verification": "source_grounded",
  "source_note": "Promotion Document / NL2SQL Chapter"
}
Do not add content not present in the document. If it is user口述 but cannot be publicly verified, use 
verification: user_attested
.

3. 提炼技术主线

3. Refine Technical Mainline

优先选择能覆盖多段经历的真实演进，例如：
多模态内容理解 → Workflow 模型节点 → Search/通用 Agent → Context/Memory/Harness → 长程 Coding Agent
主线可以宏大，但每个节点必须在正文中有对应项目。
Prioritize selecting real evolution that can cover multiple experiences, such as:
Multimodal content understanding → Workflow model nodes → Search/general Agent → Context/Memory/Harness → Long-term Coding Agent
The mainline can be grand, but each node must have a corresponding project in the main text.

4. 生成 Owner / 0→1 / Scope 叙事

4. Generate Owner / 0→1 / Scope Narrative

每个项目生成三层表达：
  1. Owner 作用域
    ：本人独立或主要负责的最小闭环；
  2. 0→1 动作
    ：从无到有建立的模型、策略、训练、部署或评测链路；若只是优化存量系统，改写为 
    X→Y 架构演进
    ；
  3. 大 Scope
    ：列出该闭环真实覆盖的 Data / Model / Training / Serving / Agent / Eval 层，不把邻接团队成果算作个人成果。
示例：
text
NL2SQL ModelOps 全链路 Owner：从 0→1 打通 Executable SQL Cleaning -> Structured Short COT -> GRPO Execution Reward -> AWQ -> SGLang Serving，覆盖数据、训练、强化学习、量化与推理部署。
Generate three levels of expression for each project:
  1. Owner Scope
    : The smallest closed loop that the user independently or mainly responsible for;
  2. 0→1 Action
    : Establishing model, strategy, training, deployment or evaluation link from scratch; if only optimizing existing systems, rewrite as 
    X→Y Architecture Evolution
    ;
  3. Large Scope
    : List the real Data / Model / Training / Serving / Agent / Eval layers covered by this closed loop, do not count adjacent team results as personal results.
Example:
text
NL2SQL ModelOps Full Link Owner: From 0→1,打通 Executable SQL Cleaning -> Structured Short COT -> GRPO Execution Reward -> AWQ -> SGLang Serving, covering data, training, reinforcement learning, quantization and inference deployment.

5. 堆叠专业名词

5. Stack Professional Terms

从来源中提取名词，不自行随机添加：
  • 模型与表征：CLIP、BERT、LanguageBind、VideoLLaVA；
  • 训练：LoRA、Full SFT、DPO、GRPO、Short COT；
  • 推理部署：AWQ、vLLM、SGLang、Prefill、Decoding；
  • Agent：ReAct、Tool Use、Session、Memory、Context Engine、Checkpoint；
  • 评测：Suite、Case、Grader、Transcript、Outcome、Artifact。
同一个 bullet 中术语之间必须有真实逻辑关系，不能只列名词。
Extract terms from sources, do not add randomly:
  • Models and representation: CLIP, BERT, LanguageBind, VideoLLaVA;
  • Training: LoRA, Full SFT, DPO, GRPO, Short COT;
  • Inference deployment: AWQ, vLLM, SGLang, Prefill, Decoding;
  • Agent: ReAct, Tool Use, Session, Memory, Context Engine, Checkpoint;
  • Evaluation: Suite, Case, Grader, Transcript, Outcome, Artifact.
Terms in the same bullet must have real logical relationships, cannot just list nouns.

6. 生成与校验

6. Generation and Verification

按 
references/resume-schema.md
生成 JSON，然后运行：
bash
python3 scripts/render_resume.py \
  --input /absolute/path/resume-data.json \
  --html /absolute/path/resume.html \
  --pdf /absolute/path/resume.pdf

python3 scripts/validate_resume.py \
  --data /absolute/path/resume-data.json \
  --html /absolute/path/resume.html \
  --pdf /absolute/path/resume.pdf
校验后把 PDF 每页转为 PNG，检查中文缺字、裁切、分页失衡和水印残留。网页版需做一次浏览器全页截图检查。
Generate JSON according to 
references/resume-schema.md
, then run:
bash
python3 scripts/render_resume.py \
  --input /absolute/path/resume-data.json \
  --html /absolute/path/resume.html \
  --pdf /absolute/path/resume.pdf

python3 scripts/validate_resume.py \
  --data /absolute/path/resume-data.json \
  --html /absolute/path/resume.html \
  --pdf /absolute/path/resume.pdf
After verification, convert each page of PDF to PNG, check for missing Chinese characters, cropping, unbalanced pagination and residual watermarks. For the webpage version, perform a full-page browser screenshot check.

附带资料

Attached Materials

  • references/style-guide.md
    ：版式和高密度技术措辞规则。
  • references/resume-schema.md
    ：来源驱动 JSON 格式。
  • assets/resume_template.html
    ：自包含中文模板。
  • scripts/render_resume.py
    ：HTML/PDF 生成器。
  • scripts/validate_resume.py
    ：来源标记、指标和文件完整性检查。
  • evals/evals.json
    ：中文测试任务。
  • references/style-guide.md
    : Layout and high-density technical wording rules.
  • references/resume-schema.md
    : Source-driven JSON format.
  • assets/resume_template.html
    : Self-contained Chinese template.
  • scripts/render_resume.py
    : HTML/PDF generator.
  • scripts/validate_resume.py
    : Source marking, metrics and file integrity check.
  • evals/evals.json
    : Chinese test tasks.