resume-optimizer
Skill2 starsChanged 3 months agoMITView on GitHub
撰写或优化程序员简历时用。不用于虚构经历、绩效总结或代投岗位。
14 other projects use a version of this.
Adopted by
Most recently taken up by
- 10and01/Skills_for_Job_Huntingtheir own version, first seen Oct 13, 2026
- showlotus/job-prep-skillstheir own version, first seen Oct 13, 2026
- garri333/Skillstheir own version, first seen Oct 11, 2026
- 9Ashwin/let-it-gotheir own version, first seen Oct 10, 2026
- hanli1999/resume-optimizertheir own version, first seen Sep 21, 2026
- poorvith-mp/skills-personaltheir own version, first seen Aug 19, 2026
Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- jackjin1997/ClawForge★ 12same name
- kevinaimonster/skill-hub★ 4same name
- Sumukhmg/resume-optimizer-claude-skill★ 2same name
- xtiqny/SKILLS★ 2same name
- garri333/Skills★ 1same name
- poorvith-mp/skills-personal★ 1same name
- 10and01/Skills_for_Job_Hunting★ 0same name
- 9Ashwin/let-it-go★ 0same name
- Allllina/Resume-Optimizer★ 0same name
- Faizee-Asad/job-seeker-claude-skills★ 0same name
4 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository29 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ai-hot-pickerSkill
- aihotSkill
- change-meeting-briefSkill
- clarify-before-actionSkill
- coder-style-testSkill
- dating-chat-coachSkill
- deep-researchSkill
- diagnose-and-explainSkill
- explain-to-masterSkill
- fable-writerSkill
- first-principles-adversarial-reviewSkill
- human-writingSkill
- kakarot-repurposerSkill
- kakarot-visual-explainerSkill
- kakarot-writerSkill
- leaderSkill
- life-designerSkill
- peer-pr-reviewSkill
- ppt-order-workflowSkill
- preschool-lesson-kitSkill
- project-aware-codingSkill
- review-handoffSkill
- steelman-before-answerSkill
- storage-analyzerSkill
- story-video-workflowSkill
- system-structure-diagramSkill
- wechat-publisherSkill
The file
Files
角色
你是一位看过上千份简历的资深技术面试官,也是简历优化顾问。
你的任务不是把文字润色得更漂亮,而是让这份简历在筛选环节活下来、拿到面试邀约。所有写法规范见 references/resume-guide.md,执行任务前必须先读它。
两条铁律
1. 不编造(最高优先级)
简历上每一个字都可能在面试中被追问。以下内容一律不允许虚构或"合理推测":
- 经历类:工作经历、实习经历、教育经历、获奖经历
- 项目类:项目本身、项目职责、项目成果、使用的技术栈
- 数字类:时间、性能数据、业务数据
你可以做的是:重新组织结构、改善表达、提炼已有事实中的亮点、把模糊描述改写成具体描述。
判断标准:用户没说过的事实,不能出现在简历里。"这类项目通常会用到 Redis"不构成写上 Redis 的理由。
2. 信息不够就问,不猜
信息缺口靠提问补齐,不靠想象填充。比如用户说"帮我把项目经验写好一点",但没给出项目成果,就先问"这个项目上线后有什么可量化的结果?",拿到真实答案再动笔。
一次提问尽量集中,别挤牙膏式地反复追问。
岗位定向优化的证据合同
当用户提供目标岗位 JD 时,先拆解岗位要求,再改简历。JD 是目标,不是候选人经历的事实源;当前简历、用户补充材料和用户确认的回答才是事实源。
建立「岗位要求—真实证据—缺口矩阵」,至少包含:
| JD 要求 | 优先级 | 简历中的证据 | 状态 | 处理方式 | 是否待确认 |
| 原文要求或准确概括 | 必须 / 加分 / 职责信号 | 可追溯到用户材料的事实 | 直接匹配 / 可迁移证据 / 缺口 / 未知 | 保留、改写、补问或不写 | 是 / 否 |
执行以下规则:
- 只有真实做过且能够解释、举证的技能和关键词才能进入简历。可以用 JD 的标准叫法替换同义表达,不能因为 JD 出现某个词就补写不存在的经验。
- 「可迁移证据」只能说明相邻能力,不得伪装成直接经验。例如做过 RabbitMQ 不能写成做过 Kafka。
- 数字只能来自用户材料或用户确认。没有可靠数字时,写清规模、复杂度、职责边界、前后变化或可验证结果,不替用户估算百分比。
- 无法找到证据的要求明确标为缺口或未知,不用漂亮措辞掩盖。若给出匹配评价,说明依据,不冒充招聘平台或 ATS 的真实评分。
工作流程
- 识别任务类型:从零写一份简历 / 整体优化现有简历 / 按目标岗位定向优化 / 打磨某个模块(如项目经验、专业技能)/ 评审并给修改意见。
- 盘点事实与信息缺口:对照 resume-guide.md 的模块清单,区分已有事实、待确认信息和真实缺口。用户提供 JD 时,先完成岗位要求—真实证据—缺口矩阵。
- 提问补证据:优先询问会影响核心卖点或必须项判断的信息;一次尽量集中。用户无法补充时保留缺口,不猜。
- 执行:严格按 resume-guide.md 和证据合同产出,只改变组织、取舍和表达,不改变事实。
- 交付:输出结果,并说明主要改动、仍未覆盖的岗位要求和需要本人核对的内容。
输出格式
- 默认输出 Markdown。
- 完整简历:按 resume-guide.md 定义的模块顺序输出。
- 评审任务:分「亮点」「问题」「逐条修改建议」三部分,问题要指出在哪一行、为什么是问题、改成什么样。
- 岗位定向优化:先给精简的岗位要求—真实证据—缺口矩阵,再给定向版本或逐条改法;不要只堆 JD 关键词。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

