← 返回 Skills 市场
ivangdavila

Career

作者 Iván · GitHub ↗ · v1.0.2
cross-platform ✓ 安全检测通过
1596
总下载
4
收藏
7
当前安装
2
版本数
在 OpenClaw 中安装
/install career
功能描述
Learns your career context. Guides decisions on paths, transitions, negotiations, and growth based on what it discovers about you.
使用说明 (SKILL.md)

Quick Reference

Scenario File Key Trap
Big career decisions decisions.md Answering without context
Changing roles/industries transitions.md "Grass is greener"
Salary & offer talks negotiations.md Accepting first offer
Promotions & development growth.md Visibility blindness
Building connections networking.md Transactional mindset

Adaptive Career Profile

This skill evolves. Observe what matters, detect patterns, personalize guidance.

User profile in ~/career/memory.md. Create on first use:

## Values
\x3C!-- Format: "value (level)" — e.g., autonomy over salary (confirmed) -->

## Strengths
\x3C!-- Format: "skill: level (source)" — e.g., writing: strong (observed) -->

## Constraints
\x3C!-- Format: "constraint (confirmed)" — e.g., location: Madrid only -->

## Context
\x3C!-- Format: "fact (stated)" — e.g., senior dev 4 years -->

## Goals
\x3C!-- Format: "goal (level)" — e.g., wants to lead team (exploring) -->

Levels: stated → pattern → confirmed. Only store after explicit yes.

Core Loop

  1. Discover — Extract career context from any question
  2. Pattern — After 2+ signals, propose confirmation
  3. Store — Only confirmed insights go to memory.md
  4. Apply — Use profile to personalize all guidance

Universal Traps

  • Sunk cost — "I've invested 5 years" ≠ reason to stay
  • False binary — "Stay or quit" ignores negotiate, pivot, transition
  • Projection — Their values, not yours or society's
  • Timing blindness — Market conditions matter; some moves have windows
  • Prestige capture — Optimizing for status vs actual satisfaction
安全使用建议
This skill is internally consistent: it gives career advice and keeps a small, local profile file (~/career/memory.md) of confirmed facts to personalize future guidance. Before installing or using it, consider: 1) the agent will analyze conversational context broadly — confirm before saving anything sensitive (the skill says to only store after explicit yes); 2) the memory file is stored on your machine and can contain personal details — inspect, move, or delete it if you want; 3) the skill has no network calls or credentials declared, but if you see behavior that tries to send this file out or asks for unrelated secrets, stop using it. If you want tighter control, ask the skill author to make the memory location configurable or to add explicit commands for exporting/deleting the memory.
功能分析
Type: OpenClaw Skill Name: career Version: 1.0.2 The skill is designed to provide career guidance and maintain a user profile. Its primary function involves writing user-derived career context to `~/career/memory.md` as instructed in `SKILL.md`. This file write operation is explicitly for the stated purpose of building an 'Adaptive Career Profile' and includes a safeguard requiring 'explicit yes' from the user before storing information. All other `.md` files contain only informational content. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts with harmful objectives within the skill's instructions. The file access is plausible and necessary for the skill's stated functionality.
能力评估
Purpose & Capability
The name and description (learning career context and giving tailored guidance) match the actual behavior: instruction-only guidance files and a single local profile file for remembered facts. There are no unrelated dependencies or credentials requested.
Instruction Scope
The SKILL.md instructs the agent to 'extract career context from any question' and to create/update ~/career/memory.md with confirmed items. This is coherent with a personalization feature, but the phrase 'any question' is somewhat broad — it implies the agent will analyze conversational context widely and may solicit or infer personal data. The SKILL.md does state 'Only store after explicit yes,' which constrains writes, but enforcement relies on the agent following the instructions.
Install Mechanism
No install spec and no code files to execute — instruction-only skill. There is nothing to download or write at install time, which is the lowest-risk model.
Credentials
The skill declares no required environment variables, no credentials, and no config paths beyond a single user-local memory file. The requested access (writing a profile to ~/career/memory.md) is proportionate to the stated purpose.
Persistence & Privilege
The skill persists user-confirmed profile data to ~/career/memory.md. It is not always-enabled and does not request system-wide privileges or modify other skills. Users should note that the memory file lives on disk and may contain sensitive career information; the SKILL.md relies on explicit confirmation before storing, but does not prescribe how to delete or export that file.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install career
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /career 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.2
Restructured with auxiliary files for specific scenarios
v1.0.0
Initial release
元数据
Slug career
版本 1.0.2
许可证
累计安装 7
当前安装数 7
历史版本数 2
常见问题

Career 是什么?

Learns your career context. Guides decisions on paths, transitions, negotiations, and growth based on what it discovers about you. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 1596 次。

如何安装 Career?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install career」即可一键安装,无需额外配置。

Career 是免费的吗?

是的,Career 完全免费(开源免费),可自由下载、安装和使用。

Career 支持哪些平台?

Career 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Career?

由 Iván(@ivangdavila)开发并维护,当前版本 v1.0.2。

💬 留言讨论