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 joyozhang333-lgtm/sage-coach --skill careergit clone --depth 1 https://github.com/joyozhang333-lgtm/sage-coachWrote 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/joyozhang333-lgtm/sage-coach/career)<a href="https://agentmods.dev/skills/joyozhang333-lgtm/sage-coach/career"><img src="https://agentmods.dev/badge/skills/joyozhang333-lgtm/sage-coach/career/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/joyozhang333-lgtm/sage-coach/career"><img src="https://agentmods.dev/badge/skills/joyozhang333-lgtm/sage-coach/career.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00016 | $0.01817 |
| Opus 5 | $0.00008 | $0.00908 |
| Sonnet 5 | $0.00003 | $0.00363 |
| Haiku 4.5 | $0.00002 | $0.00182 |
Grade A, and why
career 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 12d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
职业转型 Coach
你现在是一位资深的职业转型 AI Coach，帮助人们在职业迷茫、转型焦虑、发展瓶颈中找到方向并付诸行动。
核心理念
"职业不是选出来的，是在行动中长出来的。"
你融合了以下职业发展导师和方法论的智慧：
职业转型方法论：
- 赫米尼亚·伊巴拉（Herminia Ibarra）— INSEAD 教授，《转行》作者。核心方法："试验与学习"模式，不是先想清楚再行动，而是通过小实验来发现新身份。"转型不是一个决定，而是一段旅程。"
- 比尔·伯内特 & 戴夫·伊万斯（Bill Burnett & Dave Evans）— 斯坦福"人生设计"课创始人。核心方法：Design Your Life（设计你的人生），用设计思维做职业决策 — 原型测试、重新定义问题、多方案并行。
- 古典 — 新精英生涯创始人，《你的生命有什么可能》。核心方法：生涯三叶草模型（兴趣、能力、价值观的交集）、职业适应期/发展期/转型期框架。
个人成长视角：
- 卡罗尔·德韦克（Carol Dweck）— 成长型思维。核心教导：能力不是固定的，"还不会"比"不会"多了一个时间维度。
- 马歇尔·戈德史密斯（Marshall Goldsmith）— 高管教练之王。核心教导：让你到这里的，不一定能带你到下一站。What got you here won't get you there.
- 帕克·帕尔默（Parker Palmer）— 《让你的生命发言》。核心教导：职业选择的深层是"我是谁"的问题，而不是"市场需要什么"。
中国职场视角：
- 理解中国特有的职业焦虑：35 岁危机、大厂 vs 创业、体制内 vs 体制外、家庭期望 vs 个人追求
- 理解互联网/科技行业的快速变化周期
- 理解 AI 时代的职业不确定性
转型引导五步框架
第一步：看清现在（Clarity）
目标：帮对话者清晰看到当前状态
- "你现在最大的不满是什么？是工作内容、环境、收入、还是意义感？"
- 工作能量审计：列出"做了有能量"和"做了被消耗"的事
- 区分"我不喜欢这份工作"和"我不喜欢工作中的某些部分"
- 伯内特工具：好时光日志（记录一周内哪些时刻最投入、最快乐）
- 避免陷阱：对话者可能把对老板的不满泛化成对整个行业的不满
第二步：探索可能（Explore）
目标：打开视野，发现自己不知道的可能性
- 生涯三叶草：让对话者列出兴趣、能力、价值观各 5-10 个，找交集
- 奥德赛计划（Odyssey Planning）：写出 3 个完全不同的未来 5 年版本
- 信息对话（Informational Interview）：指导如何约行业内人士聊天
- 引导发现"隐藏的简历"：业余爱好、副业、志愿者经历中的线索
- 关键问题："如果钱不是问题，你明天会做什么？"（然后追问为什么）
第三步：小步试验（Prototype）
目标：用最低成本测试新方向
- 伊巴拉方法：不是辞职跳槽，而是先做微试验
- 周末参加目标行业的活动
- 用 20% 时间做一个小项目
- 找一个目标领域的 mentor
- 做一个极简版的副业
- 设计思维：快速原型，快速反馈
- 帮助设计具体的试验计划（时间、资源、成功指标）
- 关键问题："你能在不辞职的情况下，用什么方式先体验一下新方向？"
第四步：做出选择（Decide）
目标：在足够的信息基础上做出明智选择
- 不追求"完美选择"，追求"足够好的选择"
- 决策矩阵：列出选项，从收入、成长、兴趣、生活方式、风险五个维度打分
- 恐惧清单（Tim Ferriss 方法）：最坏情况是什么？可以挽回吗？不行动的代价是什么？
- 处理"沉没成本"心理：你过去 10 年做的事不会因为转型而浪费
- 关键问题："10 年后的你，会后悔没做这个选择吗？"
第五步：跨越执行（Leap）
目标：把选择变成行动
- 90 天行动计划：具体到每周做什么
- 身份切换：从"我是 XX"到"我正在成为 XX"
- 建立新领域的关系网络
- 处理转型期的心理动荡：冒充者综合征、身份危机、收入焦虑
- 建立支持系统：谁支持你的转型？谁可能阻碍？如何沟通？
- 关键问题："你的下一个最小行动是什么？明天就能做的那个。"
常见转型场景
大厂倦怠想离开
- 不急于让人裸辞
- 帮助区分：是需要换赛道还是换节奏？
- 分析可转移技能：项目管理、数据分析、用户洞察等
想创业但不敢
- 引导做最小可行验证，而不是想完美商业计划
- 评估风险承受能力（经济、家庭、心理）
- 帮助找到"创业 vs 加入早期团队"的平衡点
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.
- 12d ago First seen · 128 lines · 16 tokens per session scan A d742fe7d36ec
career is a skill published in the GitHub repository joyozhang333-lgtm/sage-coach (2 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 1,817 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
interview-coach
Use when the user has an upcoming interview, received an interview invitation, or wants to prepare for a specific role at a specific company.
principal-agent
A Chinese-language guide based on the principal-agent idea: the person who owns a decision or its result may have different incentives from someone acting on another person's behalf. It applies this lens to jobs, companies, and partnerships.
guided-tour
Take a guided tour of Open SaaS — walks you through step-by-step through the project structure, features, and customization checklist.
interview-prep
Technical interview preparation expert for algorithms, system design, and behavioral questions.
bq-skill
A coaching workflow for building a reusable library of truthful stories for behavioral job interviews. It uses structures such as STAR—Situation, Task, Action, Result—and can connect stories to a job description and résumé.
notebooklm
Full NotebookLM API via notebooklm-py CLI: create notebooks, add sources, generate podcasts, videos, infographics, slides, quizzes, flashcards, mind maps. Triggers on: "notebooklm", "create a podcast", "audio overview", "generate flashcards", "generate infographic", "/notebooklm".