基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/pynbj1001/alpha-sense --skill writing-skills命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
贝叶斯 Lollapalooza 投资追踪器。当用户提到"@贝叶斯 [公司]""贝叶斯追踪""持续跟踪某个标的""用贝叶斯更新概率""多因子共振概率跟踪"时触发本技能。本技能能够设定、更新、查看多个投资标的的贝叶斯后验概率,七个维度(价格、基本面、新闻、宏观、技术面、行业格局、外生冲击)的信号综合驱动,突破临界点时主动提醒。
乱世投资策略——AI革命与地缘裂变时代的全球配置筛选与检验框架。当用户提到"@乱世""@策略""投资筛选""检验标的""当前环境该不该买""乱世怎么配置""地缘风险下的投资"时触发本技能。综合周金涛周期框架、佩雷丝技术革命理论、李蓓宏观对冲体系、王川指数型投资理念、达利欧债务周期、反向策略六大框架。
董德志(国信证券宏观与固收首席分析师)的债券投资分析框架。 核心工具:「货币+信用」风火轮(四象限判断债市牛熊)、「名义增速定利率」、利率箱体理论、多资产交叉验证。 当用户提到「@债券大师」「@董德志」「@固收」「@利率研判」「@风火轮」「@债市判断」「@信用利差」时触发本技能。 适用场景:中国债市趋势研判、利率中枢定位、信用债策略、大类资产配置。
| name | writing-skills |
| description | Use when creating new skills, editing existing skills, or verifying skills work before deployment |
Writing skills IS Test-Driven Development applied to process documentation.
You write test cases (pressure scenarios), watch them fail (baseline behavior without skill), write the skill (documentation), watch tests pass (agents comply), and refactor (close loopholes).
Core principle: If you didn't watch an agent fail without the skill, you don't know if the skill teaches the right thing.
A skill is a reference guide for proven techniques, patterns, or tools.
Skills are: Reusable techniques, patterns, tools, reference guides
Skills are NOT: Narratives about how you solved a problem once
| TDD Concept | Skill Creation |
|---|---|
| Test case | Pressure scenario with subagent |
| Production code | Skill document (SKILL.md) |
| Test fails (RED) | Agent violates rule without skill |
| Test passes (GREEN) | Agent complies with skill present |
| Refactor | Close loopholes while maintaining compliance |
---
name: skill-name-with-hyphens
description: Use when [specific triggering conditions and symptoms]
---
# Skill Name
## Overview
Core principle in 1-2 sentences.
## When to Use
Bullet list with SYMPTOMS and use cases / When NOT to use
## Core Pattern
Before/after comparison
## Quick Reference
Table or bullets for scanning
## Common Mistakes
What goes wrong + fixes
Description = When to Use, NOT What the Skill Does
# ❌ BAD: Summarizes workflow
description: Use when executing plans - dispatches subagent per task with code review
# ✅ GOOD: Just triggering conditions
description: Use when executing implementation plans with independent tasks in the current session
Why: If description summarizes workflow, Claude will follow the summary instead of reading the full skill content.
NO SKILL WITHOUT A FAILING TEST FIRST
Write skill before testing? Delete it. Start over.
RED Phase:
GREEN Phase:
REFACTOR Phase:
❌ Narrative Example — "In session 2025-10-03, we found..."
❌ Multi-Language Dilution — example-js.js, example-py.py, example-go.go
❌ Generic Labels — helper1, helper2, step3
Creating skills IS TDD for process documentation.
Same Iron Law: No skill without failing test first.
Same cycle: RED (baseline) → GREEN (write skill) → REFACTOR (close loopholes).