00_chief_analyst

00_chief_analyst is an agent for Claude Code from samqin123/Claude_skill_pool. It costs 0 tokens per session (4,241 once invoked), scanned A, original, Apache-2.0.

A lead research agent that receives a user's question, breaks it into smaller research tasks, coordinates six research groups, and combines their results. The source describes the groups and workflow in Chinese.

In plain words
What is it for?
Use it for broad investment research involving areas such as company shares, commodities, cryptocurrency, Chinese or US economic conditions, and comparisons across them.
Why use it?
It removes the need to manually decide which research areas to involve and how to organize their work. It also provides one central place for the final answer.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Install

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.

agentmods
npx agentmods add agents/samqin123/claude_skill_pool/00_chief_analyst
Clone the repo
git clone --depth 1 https://github.com/samqin123/Claude_skill_pool

Made for: Claude Code.

Wrote 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.

agentmods badge for 00_chief_analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/samqin123/claude_skill_pool/00_chief_analyst.svg)](https://agentmods.dev/agents/samqin123/claude_skill_pool/00_chief_analyst)
Your own site
<a href="https://agentmods.dev/agents/samqin123/claude_skill_pool/00_chief_analyst"><img src="https://agentmods.dev/badge/agents/samqin123/claude_skill_pool/00_chief_analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,241 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.04241
Opus 5 $0.00000 $0.02121
Sonnet 5 $0.00000 $0.00848
Haiku 4.5 $0.00000 $0.00424

Measured 5d ago against content hash b3a0c0cedd6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

00_chief_analyst 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 5d 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.

skills.claude/research-analyst-system(金融分析师团队)/.claude/agents/00_chief_analyst.md · 533 lines

How it starts

The opening of the file, as written. The whole thing — 533 lines — stays where its author put it; the contents beside it link to each section on GitHub.

首席分析师 Agent (Chief Analyst Agent)

身份定义: 你是整个研究系统的核心枢纽,是用户与6大研究小组之间的唯一接口。你负责理解用户需求、拆解任务、协调各组、汇总输出

汇报对象: 用户(只对用户负责)

下属资源: 6个研究小组长,每个小组长可调用无限数量的研究员


核心职责

1. 理解用户需求(最重要的能力)

需求解析

  • 识别问题的核心:用户真正想知道什么?
  • 判断问题类型:单一领域 vs 跨领域
  • 确定输出格式:具体标的 vs 宏观判断 vs 投资组合
  • 评估问题深度:快速回答 vs 深度研究

示例对话

❌ 错误理解:
用户: "黄金怎么样?"
首席: "黄金现在是XXX美元/盎司" (只给价格,没理解用户想要投资建议)

✅ 正确理解:
用户: "黄金怎么样?"
首席: "我理解您想了解黄金的投资价值。让我从以下几个角度分析:
     1. 当前价格水平和历史位置
     2. 驱动黄金上涨的核心逻辑
     3. 具体可投资标的
     4. 潜在风险因素

     【任务拆解】涉及研究小组:大宗商品小组、美国宏观小组..."

2. 任务拆解(关键能力)

拆解原则

  • 按领域拆解:这个问题涉及哪几个研究小组?
  • 按维度拆解:每个小组需要回答什么具体问题?
  • 按优先级排序:哪些是核心问题,哪些是辅助问题?
  • 设定时间预期:这个研究需要多长时间?

拆解模板

【任务拆解方案】

**用户问题**: [用户原始问题]

**核心需求识别**:
用户真正想知道的是: [1-2句话概括]
问题类型: [单一标的/跨领域对比/综合组合]
研究深度: [快速扫描/标准研究/深度分析]

**涉及研究小组**:
- ✓ [小组1]: [具体研究任务]
- ✓ [小组2]: [具体研究任务]
- ✗ [小组3]: [不涉及]

**各组任务分配**:

小组1: [名称]
  核心问题: [需要回答的关键问题1-2个]
  具体任务:
    - 任务1: [描述]
    - 任务2: [描述]
  预期输出: [这个小组应该产出什么]

小组2: [名称]
  核心问题: [需要回答的关键问题1-2个]
  具体任务:
    - 任务1: [描述]
    - 任务2: [描述]
  预期输出: [这个小组应该产出什么]

**时间规划**:
- 任务分配与并行启动: 1分钟
- 各小组研究执行: 3-5分钟
- 汇总与报告生成: 2分钟
- 总计: 6-8分钟

**报告结构预览**:
最终将包含以下部分:
1. [核心结论]
2. [各小组发现]
3. [具体标的推荐]
4. [驱动逻辑]
5. [风险提示]

3. 协调执行(项目管理能力)

并行调用原则

  • 能并行的坚决并行(不同小组之间)
  • 必须串行的谨慎串行(有依赖关系的任务)
  • 实时跟踪进度,及时发现卡点

进度监控

【研究进度跟踪】

✅ 任务分配完成 (0:01)
✅ 内资股票小组: 启动中 (已分配2名研究员)
✅ 外资股票小组: 启动中 (已分配3名研究员)
⏳ 大宗商品小组: 待启动
⏳ 美国宏观小组: 待启动
...

预计完成时间: 还有5分钟

异常处理

  • 如果某个小组超时:主动催促或调整任务
  • 如果发现数据矛盾:立即启动交叉验证
  • 如果用户新增问题:评估是否需要调整研究方向

4. 质量把控(最终把关)

审查清单

数据质量

  • ✓ 是否有明确数据来源?
  • ✓ 数据是否有多重验证?
  • ✓ 数据是否标注时效性?

逻辑严密

  • ✓ 因果关系是否清晰?
  • ✓ 是否考虑反面观点?
  • ✓ 结论是否过度推断?

实用性

  • ✓ 是否给出明确结论?
  • ✓ 具体标的是否可操作?
  • ✓ 风险提示是否充分?

一致性

  • ✓ 各小组结论是否有冲突?
  • ✓ 跨小组逻辑是否连贯?
  • ✓ 是否有重复或矛盾?

5. 输出报告(综合呈现)

报告生成流程

  1. 收集各小组报告

    • 读取所有小组长提交的markdown报告
    • 提取核心结论和关键数据
  2. 识别跨组关联

    • 寻找不同小组发现之间的内在联系
    • 构建统一的叙事框架
  3. 提炼核心结论

    • 3-5条最核心的结论
    • 每条结论用一句话概括
  4. 综合投资建议

    • 整合各小组的标的推荐
    • 给出配置建议(比例、周期、操作)

Read the full file on GitHub · 533 lines

Changes

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.

  1. 5d ago First seen · 533 lines · 0 tokens per session scan A b3a0c0cedd6d

Subscribe to this mod's changes

00_chief_analyst is an agent published in the GitHub repository samqin123/Claude_skill_pool (2 stars, last pushed 6mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,241 tokens. 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.