Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add open-octo/octo-agent --skill resume-craftinggit clone --depth 1 https://github.com/open-octo/octo-agentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/open-octo/octo-agent/resume-crafting)<a href="https://agentmods.dev/skills/open-octo/octo-agent/resume-crafting"><img src="https://agentmods.dev/badge/skills/open-octo/octo-agent/resume-crafting/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/open-octo/octo-agent/resume-crafting"><img src="https://agentmods.dev/badge/skills/open-octo/octo-agent/resume-crafting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00180 | $0.01846 |
| Opus 5 | $0.00090 | $0.00923 |
| Sonnet 5 | $0.00036 | $0.00369 |
| Haiku 4.5 | $0.00018 | $0.00185 |
Grade A, and why
resume-crafting scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
简历打磨（Resume Crafting）
把"我做过什么"改写成"我做成了什么、有数字、能验证"。核心不是词藻，而是每条都回答：做了啥 → 带来什么可量化的结果。
动手前先确认
最多问 2-3 个，其余带 default：
- 目标岗位：投什么岗？（决定关键词、技能排序、哪段经历放前面）
- 有没有 JD：贴招聘要求最好——定制 vs 通用天差地别。
- 目的：整体润色 / 针对某岗位定制 / 写求职信 / 没东西可写（挖亮点）。
用户直接甩简历 + "帮我看看"，就从"逐条挑弱点 + 给改法"开始，别一上来整篇重写。
核心公式
X-Y-Z（Google 法）：做成了 X，用 Y 衡量，靠 Z 做到
[达成 X] 由 [Y 量化] 通过 [Z 动作]
- 差："管理社交媒体账号"
- 好："把 Instagram 粉丝从 5K 涨到 18K（+260%），靠日更内容日历 + 15 个达人合作，带来 200+ 线索"
STAR（讲故事版）：情境→任务→行动→结果
S 情境、T 任务、A 你具体做什么、R 可衡量的结果。用于面试口述或扩写亮点。
CAR（简历紧凑版）：挑战→行动→结果
把"职责"变成"成果"
四个坑与改法
| 坑 | 症状 | 改法 |
|---|---|---|
| 被动语态 | "负责/协助/参与了" | 用强动词：主导、交付、达成、重构 |
| 没数字 | "提升网站性能" | "加载从 8s 降到 3.2s，+60%" |
| 讲职责不讲成果 | "负责客服" | "日处理 50+ 工单，满意度 3.2→4.8/5" |
| 空泛/太长 | "和各方协作，做了很多事……" | 一句一成就，"带 15+ 跨部门干系人周会" |
强动词按类别
- 领导：主导、统筹、牵头、指挥、带（of 12 人）
- 增长：从 X 涨到 Y、提升、翻倍、规模到
- 优化：压到、缩短、提效到、自动化掉
- 创新：从 0 到 1 做出、建立、推出
- 分析：挖出、诊断出、识别出、建模
- 解决：消除、把 X 从 Y 降到 Z
找数字：五类
- 钱：带来营收、省下、管的预算
- 百分比：转化 +45%、错误率 -60%
- 时间：从 8s→2s、6 个月项目 4 个月交付、每周省 10 小时
- 规模/量：带 15 人、8 个项目并发、服务 500+ 客户、日活 10 万
- 前后对比：从 X 到 Y
没精确数字时（别编，诚实）
- 用 ~ 约：约 40%
- 用范围：8-12 人团队、月营收 5-7 万
- 保守估计：觉得 60% 就写 50%，别夸大
- 量不出产出就量投入："做了 30+ 场客户访谈""分析 500+ 数据点"
- 找相邻指标：转化量不出就量流量/互动
每条自检
- ✅ 强动词开头（不要"负责""协助"）
- ✅ 至少 1 个数字
- ✅ 有结果/影响，不是职责
- ✅ 有规模语境（人数、预算、用户量）
- ✅ 1-2 行，别超
- ✅ 和目标岗位相关
按 JD 定制
- 抓关键词：从 JD 里拉硬技能、工具、业务词、任职要求里的动词。
- 映射证据：每条关键词对应你简历里的某条成果；没有就标注"缺这块，可补 xx"。
- 重排：最贴合 JD 的经历/技能放最前，关键词在标题、技能、每条 bullet 首词里自然出现。
- 删无关：和目标无关的经历压缩或去掉。
ATS 提示：
- 能过 ATS 的：单栏、标准标题（工作经历/教育/技能）、纯文本可读、不用表格/图形/分栏、用 JD 原词。
- 中文平台差异：BOSS 直聘/拉勾更看关键词匹配 + 结构化，Word/PDF 都能解析；不要用图片版简历（解析不出）。英文 ATS 对"column/table/icon"敏感，中文相对宽容，但单栏 + 标准标题仍是稳妥做法。
求职信（Cover Letter）
短、具体、别复述简历。结构：
- 开门见山：一句说清你投的是什么 + 为什么是这家。
- 2-3 个量化证据：挑和 JD 最贴的成果，各一行。
- 结尾行动：想约时间聊聊 / 期待回复。
反例："我是一名有着多年经验的优秀人才。"（空泛） 正例："我过去三年在 XX 把转化率从 1.2% 做到 3.1%，这正好是贵司这个岗位最需要的能力。"
没东西可写怎么办（挖亮点）
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 123 lines · 180 tokens per session scan A 7dd66e42acbf
resume-crafting is a skill published in the GitHub repository open-octo/octo-agent (97 stars, last pushed yesterday), licensed MIT. It adds 180 tokens to every session and 1,846 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
meeting-notes
Use when the user asks to capture, structure, or summarize meeting notes / call notes / 1:1 discussion / standup notes. Produces a standard template with attendees, agenda, decisions, action items (owner + deadline), and open questions.
ha-settings
Manage Hope Agent application settings through conversation. Use when the user wants to view or change any app configuration: theme, language, enhanced focus indicators, proxy, temperature, notifications, tool timeout, context compaction, automatic session titles, web search, GitHub issue reporting, memory, embedding…
tg-moderator
Telegram chat moderator/companion mode. No tools, conversational only.
apple-reminders
Apple Reminders via remindctl: add, list, complete.
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.
telegram-workflow
Rules for using a personal Telegram account through claudegram, a connection that works as the account owner rather than as a bot. It covers reading chats, searching messages, drafting replies, and managing conversations and groups.