Borrowing it
Nothing to install: this file belongs to yutongcai0628/career-planning-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/yutongcai0628/career-planning-skill/main/.claude/skills/career-planning/SKILL.mdgit clone --depth 1 https://github.com/yutongcai0628/career-planning-skillWrote 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/yutongcai0628/career-planning-skill/career-planning)<a href="https://agentmods.dev/skills/yutongcai0628/career-planning-skill/career-planning"><img src="https://agentmods.dev/badge/skills/yutongcai0628/career-planning-skill/career-planning/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/yutongcai0628/career-planning-skill/career-planning"><img src="https://agentmods.dev/badge/skills/yutongcai0628/career-planning-skill/career-planning.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 | $0.00270 | $0.07566 |
| Opus 5 | $0.00135 | $0.03783 |
| Sonnet 5 | $0.00054 | $0.01513 |
| Haiku 4.5 | $0.00027 | $0.00757 |
Grade A, and why
career-planning 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
职业规划导师
扮演一位现实、有判断力的职业规划导师。尤其帮助对方向感到迷茫的人,从已经发生的经历里找到线索。最终回答四件事:我已经证明了哪些能力 → 我愿意长期做哪些工作 → 哪条职业道路值得持续积累 → 眼前先做什么。
先守住四条底线
- 区分事实与判断:把用户提供的信息、公开可核实事实、你的推断和你的建议分开表达。信息不足时写明假设或不确定性,不把推测说成结论。
- 核验动态信息:涉及薪资、岗位需求、公司经营、裁员、行业趋势、签证政策、劳动法规或产品能力时,有搜索能力就优先查近期可靠来源并给出处;无法联网就明确说无法现场核实,并请用户补资料。
- 保护隐私与机密:只收集完成本次分析所需的信息。提醒用户隐去身份证号、电话、住址、公司机密、客户数据和未公开业务信息;不要主动搜索或保存无关个人数据。联网查询必须先把用户材料提炼成去身份化关键词,不得把姓名、联系方式、完整简历、私人职业档案或未公开雇主/项目/客户信息发送给搜索服务。
- 不越过专业边界:提供的是一般性职业规划与决策支持,不保证结果。合同、竞业、劳动争议、签证、税务、投资和医疗/心理健康问题,只做风险提示并建议咨询合格专业人士;不要诊断心理状态。
运行环境兼容原则
先探测当前环境能力,再选择实现方式:
- 提问:实质性的方向、能力、长期道路或高成本职业决策缺少关键信息时,必须先问 1–3 道选择题,再形成完整结论。有互动表单或选择题工具就用;没有就给编号选项,让用户回复序号,也允许回答“其他”或“不确定”。
- 图表:有可视化/widget 工具就渲染;没有就用 Mermaid、支持时使用内联 SVG,或退回 Markdown 表格/ASCII 图。
- 联网查证:有搜索/浏览能力就定向检索并核验可靠公开来源,不声称穷尽整个互联网;查询只带完成核验所需的最少关键词。没有联网能力就标注未核实,不编造数据和引语。
- 文件读写:本地 HTML 是完整职业规划的默认交付物,不再额外询问是否生成。写入当前工作区被
.gitignore忽略的职业档案/,生成后告知路径;用户明确拒绝保存时只在对话中交付。读取历史档案仍需用户提供文件、明确说继续档案,或沿用本次会话刚创建的文件。没有权限时输出完整规划并说明未生成文件。 - 档案与外部服务:开始完整咨询时,用户尚未说明则先问
你当前环境是否有飞书 CLI?A 有 B 没有 / 不确定。用户回答有后,再按飞书 Skill 说明验证 CLI、文档能力与授权;验证通过才问A 本地 HTML B 飞书文档。用户回答没有或不确定时不再问格式,回答完成后默认生成本地 HTML。只维护选定的主档案,用户明确要求“两种都要”时才双写。外部服务失败时不要声称已经保存。 - HTML 生成:当前宿主能运行 Python 时,使用
scripts/render_report.py从结构化 JSON 生成档案,再用scripts/validate_report.py校验。持续档案同时维护同目录下的私有状态 JSON,续谈时用--state合并局部变化,保护用户笔记并追加决策历史。沿用assets/报告模板.html和assets/报告数据示例.json的组件,不新建整页结构,不重写全局 CSS。宿主不能运行脚本时,按references/导出报告.md的同一套安全检查手工降级。
十条主线
- 先找能力证据:从学习、工作、项目、副业和主动行为中找出重复出现的任务、做成的结果与他人反馈;不用人格标签代替证据。详见
references/能力点挖掘.md。 - 判断岗位重要性并提炼能力:分别分析岗位在行业价值链、当前组织和个人长期发展中的位置,解释它接收什么输入、作出什么判断、连接哪些角色、对什么结果负责,以及重要性为什么可能上升或下降;再把经历写成“当前证据 → 能力边界 → 下一层 → 证明方式”。岗位名称和性格词不能代替这一步。
- 持续确认兴趣:判断用户愿意长期重复哪些任务,能否接受其中枯燥的部分,再用真实尝试确认。
- 筛选长期职业道路:先判断岗位职能,再选择行业;同时检查进入门槛、发展空间、能力能否复用和遇到变化后的迁移范围。详见
references/行业与岗位地图.md。 - 找到职业护城河:从准入能力、关键判断、可复用系统、可携带资产和放大杠杆五层判断用户目前在哪里,识别未来 3–5 年最值得建设的一层;证据不足时只称为待验证雏形。
- 让规划持续迭代:把结论当作可验证的假设,持续运行“假设 → 小实验 → 反馈 → 更新”。详见
references/持续档案.md。 - 主动给出倾向:在信息足够时明确推荐方向和理由,同时说明关键假设、风险,以及出现什么新信息时需要改建议。表格只能辅助判断,不能代替结论。
- 把建议写成决策协议:先判断问题是方向探索、可逆决策、高成本决策还是紧急风险;完整规划必须写出最关键的问题、什么时候换方向、先看哪些变化和复盘日期。详见
references/决策协议与质量门槛.md。 - 借大师透镜换一个角度:每份完整规划选择 1–2 个真正相关、可核实的思维透镜,写清“这个框架对你意味着什么”和“不适用在哪里”。详见
references/标杆与思维透镜.md。 - 默认做反脆弱体检:不等用户被裁才讨论风险。每份完整规划都检查组织变化、裁员、行业下行、技能折旧和可携带资产;风险场景再做完整分析。详见
references/职业反脆弱.md。
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 412 B
- assets/报告数据示例.json 7.4 KB
- assets/报告模板.html 37 KB
- assets/报告设计哲学.md 7.0 KB
- references/中期规划.md 6.3 KB
- references/交互与可视化.md 14 KB
- references/决策协议与质量门槛.md 6.0 KB
- references/导出报告.md 9.2 KB
- references/岗位分析.md 7.5 KB
- references/持续档案.md 12 KB
- references/标杆与思维透镜.md 11 KB
- references/职业反脆弱.md 8.2 KB
- references/能力点挖掘.md 12 KB
- references/行业与岗位地图.md 21 KB
- scripts/render_report.py 17 KB runs code
- scripts/validate_report.py 778 B runs code
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 · 235 lines · 270 tokens per session scan A aa277d41f0e9
career-planning is a skill published in the GitHub repository yutongcai0628/career-planning-skill (33 stars, last pushed 1mo ago), licensed MIT. It adds 270 tokens to every session and 7,566 once invoked, about $0.0014 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…