Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Write a sharp, achievement-led resume/CV that passes ATS and earns the interview. Use when asked to write or rewrite a resume or CV, turn experience into a resume, or tailor a resume to a job. Produces a clean, single-column, ATS-friendly resume — summary, experience as quantified accomplishment bullets, skills, and education — ready to export as a designed PDF.
.claude/skills/mohitagw15856-resume/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 32% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 66% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 33% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 29% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 18% | 0% |
> resume 的简体中文翻译 — 英文版本为规范版本。
一份简历只有约 7 秒钟的人工浏览时间,以及一次 ATS 扫描。所以它必须易于扫读、以成就为主线、关键词对齐——而不是职位描述的复述。这个技能把你的经历转化为量化的成就要点,采用单栏结构(ATS 安全),并针对目标职位定制。可用 Paper 或 Modern PDF 主题导出,获得排版效果。
你经常只会拿到零散笔记、不完整的经历,或者仅仅一个目标职位。无论如何都要交付一份完整、可直接使用的简历——不要停下来提问,也不要留下 [公司名]、[补充数据] 这类占位符。缺少细节时,根据素材和目标职位推断一个具体、合理的内容,并把所有推断内容标注为(推测——请确认),让用户知道需要核实。一个具体且有标注的推测,永远好过一个空白或一个追问。
每项成就都要量化。优先使用用户提供的真实数字——用户给出的数据要原样使用。只有当指标确实缺失时,才把职责转写为以结果为导向的成就(写结果,例如"上线移动应用 v1,并获得第一批用户");只有在能给出站得住脚的保守估计时才补充数字,并标注(推测——请确认)。绝不能在真实的简历上悄悄编造或夸大数字——一个未标注的虚构指标,比缺失指标更糟糕。
只输出成品简历(及其简短的定制说明)——不要开场白,不要"这是您的简历",不要对自己做了什么发表元评论。
单栏、ATS 友好的简历,按以下顺序:
目标职位] · 城市 / 远程] · 邮箱] · 电话] · LinkedIn/作品集]
概要——2–3 行:你是谁、你最有力的证明、你的目标方向。不要"结果导向的专业人士"之类的空话。
工作经历——倒序时间。每个职位: 职位],公司] · 起止时间]
技能——分组呈现、关键词丰富,呼应职位描述的用语(ATS 靠它们匹配)。
教育背景——学位、院校、年份;证书。
定制说明(单独给用户):织入了职位描述中的哪些关键词,以及需要在求职信中弥补的差距。
以成就为主线、ATS 感知的简历实践(倒序时间、量化影响要点、关键词对齐)。
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-20 | pass→pass | 12,158 | 15,929 | +31% | 1 | 1 | 0% | 1,523 | 2,846 | +87% | 0 | 0 | — |
case-01 | fail→fail | 27,400 | 23,297 | -15% | 1 | 1 | 0% | 3,262 | 4,390 | +35% | 0 | 0 | — |
case-02 | fail→fail | 20,653 | 28,790 | +39% | 1 | 1 | 0% | 2,565 | 4,545 | +77% | 0 | 0 | — |
case-03 | fail→pass | 30,106 | 28,135 | -7% | 1 | 1 | 0% | 3,851 | 5,098 | +32% | 0 | 0 | — |
case-04 | pass→pass | 19,968 | 21,199 | +6% | 1 | 1 | 0% | 2,378 | 3,367 | +42% | 0 | 0 | — |
case-05 | pass→fail | 31,025 | 20,643 | -33% | 1 | 1 | 0% | 3,519 | 3,736 | +6% | 0 | 0 | — |
case-06 | fail→fail | 26,646 | 22,290 | -16% | 1 | 1 | 0% | 2,846 | 3,871 | +36% | 0 | 0 | — |
case-07 | fail→pass | 27,021 | 23,860 | -12% | 1 | 1 | 0% | 3,020 | 4,999 | +66% | 0 | 0 | — |
case-08 | fail→fail | 22,277 | 17,853 | -20% | 1 | 1 | 0% | 2,907 | 4,003 | +38% | 0 | 0 | — |
case-09 | fail→fail | 16,396 | 9,800 | -40% | 1 | 1 | 0% | 2,307 | 2,833 | +23% | 0 | 0 | — |
case-10 | fail→pass | 25,979 | 23,652 | -9% | 1 | 1 | 0% | 2,921 | 3,879 | +33% | 0 | 0 | — |
case-11 | fail→fail | 30,233 | 29,541 | -2% | 1 | 1 | 0% | 3,235 | 4,700 | +45% | 0 | 0 | — |
case-12 | pass→pass | 21,093 | 22,421 | +6% | 1 | 1 | 0% | 2,219 | 3,402 | +53% | 0 | 0 | — |
case-13 | fail→fail | 23,225 | 17,831 | -23% | 1 | 1 | 0% | 2,426 | 2,870 | +18% | 0 | 0 | — |
case-14 | pass→pass | 18,443 | 12,317 | -33% | 1 | 1 | 0% | 1,865 | 2,238 | +20% | 0 | 0 | — |
case-15 | pass→pass | 15,891 | 24,809 | +56% | 1 | 1 | 0% | 2,396 | 3,866 | +61% | 0 | 0 | — |
case-16 | pass→pass | 28,566 | 24,450 | -14% | 1 | 1 | 0% | 3,499 | 4,701 | +34% | 0 | 0 | — |
case-17 | fail→pass | 27,392 | 27,616 | +1% | 1 | 1 | 0% | 3,189 | 4,123 | +29% | 0 | 0 | — |
case-18 | fail→pass | 14,029 | 8,337 | -41% | 1 | 1 | 0% | 1,406 | 1,659 | +18% | 0 | 0 | — |
case-19 | pass→pass | 20,890 | 19,063 | -9% | 1 | 1 | 0% | 2,380 | 3,536 | +49% | 0 | 0 | — |
case-21 | pass→pass | 25,461 | 21,797 | -14% | 1 | 1 | 0% | 2,542 | 3,149 | +24% | 0 | 0 | — |
case-22 | pass→pass | 26,776 | 41,261 | +54% | 1 | 1 | 0% | 3,945 | 5,770 | +46% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +18 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.