equity-researcher

Name: equity-researcher
Author: lzwme

160stars33forks

How to install equity-researcher?

lzwme/finance-quant-skills/equity-researcher

$npx -y skills add lzwme/finance-quant-skills --skill equity-researcher

Installs into the current project.

Summary

机构级投研报告生成技能。覆盖中国A股、港股、美股上市公司。输出模式：1）投资速览：3-5页，含公司概览、核心财务指标、估值倍数、投资逻辑与风险因素；2）深度研报：≥25页，含行业分析、产业链图谱、三表模型、DCF估值、情景分析与敏感性测试。触发条件：1）直接请求：分析/看看/研究/调研/介绍一下 + 公司名或股票；2）投资询问：你怎么看/能不能买/值得投吗/帮我看看/扒一扒 + 公司或股票；3）关键词：研报、投资简报、投资速览、公司一页纸、深度研报、深度研究、深度分析、个股分析、一页纸、速览、公司速览、投研报告；4）股票代码：标准格式（如 600519.

Files · 1

View on GitHub

SKILL.md

1	# Equity Research Skill
2
3	This skill generates institutional-grade investment research in two modes: Tear Sheet (3-5 page PDF, single session) and Equity Report (≥25 page PDF, 3-task architecture with financial model). Both modes share the same analytical philosophy — the difference is depth, scope, and delivery structure.
4
5	Your first job: figure out what the user wants. Then carry the Core Principles into the next file.
6
7	---
8
9	## Phase 0.0: Router — Intent Clarification + Output Type Detection
10
11	### Step 1: Detect Language
12
13	Detect the user's language from their message. Use that language for ALL follow-up questions and the final report.
14
15	\| User Language \| `report_language` \|
16	\|---------------\|-------------------\|
17	\| Chinese (any) \| `zh` \|
18	\| English \| `en` \|
19	\| Mixed / unclear \| Match the dominant language in user's message \|
20
21	### Step 2: Classify Intent (3 Tiers)
22
23	Not every company analysis request needs a full report. Before committing resources, determine what the user actually wants.
24
25	\| Tier \| User Signal Examples \| Action \|
26	\| ---------------------------------------------- \| ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- \| ------------------------------------------------------------------------------- \|
27	\| Tier A: Explicit report keyword \| "tear sheet", "one pager", 投资速览, 投资简报, "research report", "deep dive", "equity report", 研报, 深度研究, 深度分析 \| → Skip to Step 3 (output type is clear) \|
28	\| Tier B: Company analysis — ambiguous depth \| "帮我分析一下[公司]", "analyze [company]", "帮我看看[股票]", "look into [stock]", "了解一下[公司]", "what do you think of [company]", 个股分析, 公司分析, or just a stock code (e.g. AAPL, 600519) \| → Ask user (Step 2a) \|
29	\| Tier C: Simple question \| "XX公司是做什么的", "what's [company]'s market cap", "when is [stock]'s next earnings" \| → Do NOT trigger this skill. Answer conversationally. No report generation. \|
30
31	### Step 2a: Clarify Intent (Tier B only)
32
33	When the user's request is ambiguous (Tier B), ask them what level of output they want. Do not assume they want a full report — that wastes their time and tokens.
34
35	Present 3 clear options (in the user's language):
36
37	Chinese example:
38	> 我可以用以下几种方式帮你分析 [公司名]:
39	>
40	> 1. 投资速览 (Tear Sheet) — 3-5页专业机构级投资简报，包含估值、催化剂、产业链、情景分析等，适合快速决策参考
41	> 2. 深度研究报告 (Equity Report) — ≥25页机构级深度研报，包含完整财务模型、DCF估值、敏感性分析等，适合深入研究
42	> 3. 简单回答 — 不生成报告，直接用对话回答你的问题，最节省时间
43	>
44	> 你想要哪种？
45
46	English example:
47	> I can analyze [company] at different levels of depth:
48	>
49	> 1. Tear Sheet — A concise 3-5 page professional investment brief with valuation, catalysts, supply chain, and scenario analysis
50	> 2. Full Equity Report — An in-depth ≥25 page institutional report with a complete financial model, DCF valuation, and sensitivity analysis
51	> 3. Quick answer — No report generation, just a conversational response to your question
52	>
53	> Which would you prefer?
54
55	If user chooses option 3: Answer their question conversationally. Do NOT proceed with this skill. End here.
56
57	### Step 3: Determine Output Type
58
59	\| User Choice / Signal \| Output Type \| Variable \|
60	\|---------------------\|-------------\|----------\|
61	\| Tear Sheet / 投资速览 / option 1 \| Tear Sheet \| `output_type = TEAR_SHEET` \|
62	\| Equity Report / 深度研究 / option 2 \| Equity Report \| `output_type = EQUITY_REPORT` \|
63	\| Explicit "tear sheet", "one pager", 投资速览, 投资简报, 公司一页纸, "quick glance", "investment memo" \| Tear Sheet \| `output_type = TEAR_SHEET` \|
64	\| Explicit "research report", "full report", "deep dive", "equity report", 研报, 深度研究, 深度分析 \| Equity Report \| `output_type = EQUITY_REPORT` \|
65
66	Once output_type is set, record it. This variable determines which mode-specific file to read next.
67
68	---
69
70	### Step 3a: Equity Report Valuation Depth Selection (only when `output_type = EQUITY_REPORT`)
71
72	When the user wants an equity report, ask one more question before starting analysis. The report can be built at two valuation depths — this significantly affects time and complexity.
73
74	Present the choice (in the

People who liked this also viewed

6 picks

Type

equity-researcher

160stars33forks

View on GitHub

How to install equity-researcher?

lzwme/finance-quant-skills/equity-researcher

$npx -y skills add lzwme/finance-quant-skills --skill equity-researcher

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Equity Research Skill
2
3	This skill generates institutional-grade investment research in two modes: Tear Sheet (3-5 page PDF, single session) and Equity Report (≥25 page PDF, 3-task architecture with financial model). Both modes share the same analytical philosophy — the difference is depth, scope, and delivery structure.
4
5	Your first job: figure out what the user wants. Then carry the Core Principles into the next file.
6
7	---
8
9	## Phase 0.0: Router — Intent Clarification + Output Type Detection
10
11	### Step 1: Detect Language
12
13	Detect the user's language from their message. Use that language for ALL follow-up questions and the final report.
14
15	\| User Language \| `report_language` \|
16	\|---------------\|-------------------\|
17	\| Chinese (any) \| `zh` \|
18	\| English \| `en` \|
19	\| Mixed / unclear \| Match the dominant language in user's message \|
20
21	### Step 2: Classify Intent (3 Tiers)
22
23	Not every company analysis request needs a full report. Before committing resources, determine what the user actually wants.
24
25	\| Tier \| User Signal Examples \| Action \|
26	\| ---------------------------------------------- \| ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- \| ------------------------------------------------------------------------------- \|
27	\| Tier A: Explicit report keyword \| "tear sheet", "one pager", 投资速览, 投资简报, "research report", "deep dive", "equity report", 研报, 深度研究, 深度分析 \| → Skip to Step 3 (output type is clear) \|
28	\| Tier B: Company analysis — ambiguous depth \| "帮我分析一下[公司]", "analyze [company]", "帮我看看[股票]", "look into [stock]", "了解一下[公司]", "what do you think of [company]", 个股分析, 公司分析, or just a stock code (e.g. AAPL, 600519) \| → Ask user (Step 2a) \|
29	\| Tier C: Simple question \| "XX公司是做什么的", "what's [company]'s market cap", "when is [stock]'s next earnings" \| → Do NOT trigger this skill. Answer conversationally. No report generation. \|
30
31	### Step 2a: Clarify Intent (Tier B only)
32
33	When the user's request is ambiguous (Tier B), ask them what level of output they want. Do not assume they want a full report — that wastes their time and tokens.
34
35	Present 3 clear options (in the user's language):
36
37	Chinese example:
38	> 我可以用以下几种方式帮你分析 [公司名]:
39	>
40	> 1. 投资速览 (Tear Sheet) — 3-5页专业机构级投资简报，包含估值、催化剂、产业链、情景分析等，适合快速决策参考
41	> 2. 深度研究报告 (Equity Report) — ≥25页机构级深度研报，包含完整财务模型、DCF估值、敏感性分析等，适合深入研究
42	> 3. 简单回答 — 不生成报告，直接用对话回答你的问题，最节省时间
43	>
44	> 你想要哪种？
45
46	English example:
47	> I can analyze [company] at different levels of depth:
48	>
49	> 1. Tear Sheet — A concise 3-5 page professional investment brief with valuation, catalysts, supply chain, and scenario analysis
50	> 2. Full Equity Report — An in-depth ≥25 page institutional report with a complete financial model, DCF valuation, and sensitivity analysis
51	> 3. Quick answer — No report generation, just a conversational response to your question
52	>
53	> Which would you prefer?
54
55	If user chooses option 3: Answer their question conversationally. Do NOT proceed with this skill. End here.
56
57	### Step 3: Determine Output Type
58
59	\| User Choice / Signal \| Output Type \| Variable \|
60	\|---------------------\|-------------\|----------\|
61	\| Tear Sheet / 投资速览 / option 1 \| Tear Sheet \| `output_type = TEAR_SHEET` \|
62	\| Equity Report / 深度研究 / option 2 \| Equity Report \| `output_type = EQUITY_REPORT` \|
63	\| Explicit "tear sheet", "one pager", 投资速览, 投资简报, 公司一页纸, "quick glance", "investment memo" \| Tear Sheet \| `output_type = TEAR_SHEET` \|
64	\| Explicit "research report", "full report", "deep dive", "equity report", 研报, 深度研究, 深度分析 \| Equity Report \| `output_type = EQUITY_REPORT` \|
65
66	Once output_type is set, record it. This variable determines which mode-specific file to read next.
67
68	---
69
70	### Step 3a: Equity Report Valuation Depth Selection (only when `output_type = EQUITY_REPORT`)
71
72	When the user wants an equity report, ask one more question before starting analysis. The report can be built at two valuation depths — this significantly affects time and complexity.
73
74	Present the choice (in the

People who liked this also viewed

6 picks

Type