china-housing-forecast-lite-skill

Name: china-housing-forecast-lite-skill
Author: luyou666

27stars0forks

How to install china-housing-forecast-lite-skill?

luyou666/china-housing-forecast-lite-skill/china-housing-forecast-lite-skill

$npx -y skills add luyou666/china-housing-forecast-lite-skill --skill china-housing-forecast-lite-skill

Installs into the current project.

Summary

Use this skill to produce concise, evidence-driven forecasts for Chinese residential real estate markets. Keep the analysis centered on housing-market data: price trend, transaction volume, inventory or listings, valuation, credit conditions, policy changes, and district segmenta

Files · 1

View on GitHub

SKILL.md

1	# 中国房地产趋势预测 Skill / China Real Estate Trend Forecast Skill
2
3	Use this skill to produce concise, evidence-driven forecasts for Chinese residential real estate markets. Keep the analysis centered on housing-market data: price trend, transaction volume, inventory or listings, valuation, credit conditions, policy changes, and district segmentation.
4
5	Do not turn the forecast into a broad macroeconomic report, crawler system, or machine-learning system. Economic cycle and population flow are important overlays, but they remain a small adjustment within +/-8 points.
6
7	Standard disclaimer for formal outputs: 仅供交流学习娱乐，不提供投资建议，所有解释权归作者所有。
8
9	## When to Use
10
11	Use this skill when the user asks about:
12
13	- Housing price trends in a Chinese city or district
14	- New-home or second-hand-home market forecasts
15	- Whether a market is stabilizing, bottoming, or still declining
16	- Whether now is suitable for self-use purchase or investment
17	- 3/6/12/24 month probability forecasts
18	- Risk checks for core areas, suburbs, new districts, or satellite cities
19
20	## Fresh Data Retrieval Rule
21
22	When the user question includes any of the following, prioritize latest public data retrieval before scoring:
23
24	- 最新
25	- 当前
26	- 现在
27	- 今年
28	- 最近
29	- 当下
30	- 未来几个月
31	- 未来 3 个月
32	- 未来 6 个月
33	- 未来 12 个月
34	- 某城市是否见底
35	- 现在是否适合买房
36	- 当前是否适合投资
37
38	If the runtime supports web search, perform fresh public data retrieval. Use only publicly accessible sources. Do not bypass paywalls, login restrictions, anti-bot systems, or captchas.
39
40	If the runtime does not support web search:
41
42	1. State clearly that latest data cannot be fetched automatically.
43	2. Ask the user to provide data, or continue with a low-confidence framework analysis.
44	3. Mark the missing items as Data Gap.
45	4. Do not fabricate current or latest data.
46
47	## Traceable Source Requirement
48
49	For formal forecasts using fresh data:
50
51	- Show source name, data date, and freshness status.
52	- Prefer traceable official or industry sources.
53	- Include source links or identifiable publication names if available.
54	- Do not claim to have used latest data unless the source date is visible.
55	- If the source cannot be opened and only a snippet is available, treat it as weak evidence.
56	- If a key data point has unclear source or unclear date, mark it as Data Gap or Stale and lower confidence.
57
58	## Fresh Data Retrieval Workflow
59
60	1. Define scope:
61	- City
62	- District
63	- New home / second-hand home / both
64	- Forecast horizon
65	- User purpose: self-use / investment / research / risk check
66
67	2. Search latest data:
68	- Price data
69	- Transaction volume
70	- Inventory / listings
71	- Mortgage rate / LPR / credit policy
72	- Local purchase restrictions, provident fund, subsidies, purchase support, destocking or acquisition policies
73	- Population inflow / outflow
74	- Income, employment, and economic-cycle data
75
76	3. Assign data quality:
77	- Use `data_sources.md` A/B/C/D reliability levels.
78
79	4. Check freshness:
80	- Use `data_sources.md` freshness standards.
81
82	5. Resolve conflicts:
83	- If sources conflict, explain methodology differences.
84
85	6. Mark gaps:
86	- If key data is missing, mark Data Gap and apply `scoring_model.md` confidence caps.
87
88	7. Score and forecast:
89	- Use `scoring_model.md` for core scoring, probability mapping, economic/population adjustment, and horizon adjustment.
90
91	8. Cross-check:
92	- Use Minimal Multi-Agent Mode and Bear Case Review.
93
94	9. Output:
95	- Use `output_template.md`.
96
97	## Required Data
98
99	### Housing Market Data
100
101	- New-home and second-hand-home price trend
102	- Transaction volume and listing volume
103	- Inventory or months of supply
104	- Discount rate and price-cut ratio if available
105	- Rental yield or price-to-income ratio if available
106	- Mortgage rate, credit availability, and down-payment policy
107	- Local purchase restrictions, tax policy, provident fund policy, and housing support policy
108	- District-level split between core areas, mature urban areas, outer suburbs, new districts, and satellite cities
109
110	### Economic Cycle Data
111
112	- GDP growth or regional GDP growth
113	- Unemployment rate
114	- Resident disposable income growth
115	- Consumer confidence if available
116	- PMI or local industrial activity if available
117
118	### Population Flow Data
119
120	- Permanent population change
121	- Net population inflow or outflow
122	- Young population share if available
123	- Household registration change if available
124	- Employment inflow if available
125
126	If data is missing, do not block the forecast. Mark Data Gap and lower confidence according to `scoring_model.md`.
127
128	## Economic Cycle and Population Flow Overlay
129
130	Economic cycle and population flow correct the final judgment but do not replace the core housing model.
131
132	- Economic expansion can improve income expectations, employment stability, and purchase confidence.
133	- Economic downturn can weaken income expectations, raise employment pressure, and reduce willingness to add leverage.
134	- Net population inflow supports long-term demand, especially in core districts.
135	- Net population outflow weakens long-term demand, especially in non-core areas and high

luyou666Publisher · 1 listing

Preview

luyou666/china-housing-forecast-lite-skill

# 中国房地产趋势预测 Skill / China Real Estate Trend Forecast Skill

Use this skill to produce concise, evidence-driven forecasts for Chinese residential real estate markets. Keep the analysis centered on housing-market data: pri

Do not turn the forecast into a broad macroeconomic report, crawler system, or machine-learning system. Economic cycle and population flow are important overlay

Standard disclaimer for formal outputs: 仅供交流学习娱乐，不提供投资建议，所有解释权归作者所有。

Repoluyou666/china-housing-forecast-lite-skill

LicenseMIT

TypeSkills

CategoryData

UpdatedMay 2026

Repo stars27

First seenJul 22, 2026

People who liked this also viewed

6 picks

Type

china-housing-forecast-lite-skill

27stars0forks

View on GitHub

How to install china-housing-forecast-lite-skill?

luyou666/china-housing-forecast-lite-skill/china-housing-forecast-lite-skill

$npx -y skills add luyou666/china-housing-forecast-lite-skill --skill china-housing-forecast-lite-skill

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# 中国房地产趋势预测 Skill / China Real Estate Trend Forecast Skill
2
3	Use this skill to produce concise, evidence-driven forecasts for Chinese residential real estate markets. Keep the analysis centered on housing-market data: price trend, transaction volume, inventory or listings, valuation, credit conditions, policy changes, and district segmentation.
4
5	Do not turn the forecast into a broad macroeconomic report, crawler system, or machine-learning system. Economic cycle and population flow are important overlays, but they remain a small adjustment within +/-8 points.
6
7	Standard disclaimer for formal outputs: 仅供交流学习娱乐，不提供投资建议，所有解释权归作者所有。
8
9	## When to Use
10
11	Use this skill when the user asks about:
12
13	- Housing price trends in a Chinese city or district
14	- New-home or second-hand-home market forecasts
15	- Whether a market is stabilizing, bottoming, or still declining
16	- Whether now is suitable for self-use purchase or investment
17	- 3/6/12/24 month probability forecasts
18	- Risk checks for core areas, suburbs, new districts, or satellite cities
19
20	## Fresh Data Retrieval Rule
21
22	When the user question includes any of the following, prioritize latest public data retrieval before scoring:
23
24	- 最新
25	- 当前
26	- 现在
27	- 今年
28	- 最近
29	- 当下
30	- 未来几个月
31	- 未来 3 个月
32	- 未来 6 个月
33	- 未来 12 个月
34	- 某城市是否见底
35	- 现在是否适合买房
36	- 当前是否适合投资
37
38	If the runtime supports web search, perform fresh public data retrieval. Use only publicly accessible sources. Do not bypass paywalls, login restrictions, anti-bot systems, or captchas.
39
40	If the runtime does not support web search:
41
42	1. State clearly that latest data cannot be fetched automatically.
43	2. Ask the user to provide data, or continue with a low-confidence framework analysis.
44	3. Mark the missing items as Data Gap.
45	4. Do not fabricate current or latest data.
46
47	## Traceable Source Requirement
48
49	For formal forecasts using fresh data:
50
51	- Show source name, data date, and freshness status.
52	- Prefer traceable official or industry sources.
53	- Include source links or identifiable publication names if available.
54	- Do not claim to have used latest data unless the source date is visible.
55	- If the source cannot be opened and only a snippet is available, treat it as weak evidence.
56	- If a key data point has unclear source or unclear date, mark it as Data Gap or Stale and lower confidence.
57
58	## Fresh Data Retrieval Workflow
59
60	1. Define scope:
61	- City
62	- District
63	- New home / second-hand home / both
64	- Forecast horizon
65	- User purpose: self-use / investment / research / risk check
66
67	2. Search latest data:
68	- Price data
69	- Transaction volume
70	- Inventory / listings
71	- Mortgage rate / LPR / credit policy
72	- Local purchase restrictions, provident fund, subsidies, purchase support, destocking or acquisition policies
73	- Population inflow / outflow
74	- Income, employment, and economic-cycle data
75
76	3. Assign data quality:
77	- Use `data_sources.md` A/B/C/D reliability levels.
78
79	4. Check freshness:
80	- Use `data_sources.md` freshness standards.
81
82	5. Resolve conflicts:
83	- If sources conflict, explain methodology differences.
84
85	6. Mark gaps:
86	- If key data is missing, mark Data Gap and apply `scoring_model.md` confidence caps.
87
88	7. Score and forecast:
89	- Use `scoring_model.md` for core scoring, probability mapping, economic/population adjustment, and horizon adjustment.
90
91	8. Cross-check:
92	- Use Minimal Multi-Agent Mode and Bear Case Review.
93
94	9. Output:
95	- Use `output_template.md`.
96
97	## Required Data
98
99	### Housing Market Data
100
101	- New-home and second-hand-home price trend
102	- Transaction volume and listing volume
103	- Inventory or months of supply
104	- Discount rate and price-cut ratio if available
105	- Rental yield or price-to-income ratio if available
106	- Mortgage rate, credit availability, and down-payment policy
107	- Local purchase restrictions, tax policy, provident fund policy, and housing support policy
108	- District-level split between core areas, mature urban areas, outer suburbs, new districts, and satellite cities
109
110	### Economic Cycle Data
111
112	- GDP growth or regional GDP growth
113	- Unemployment rate
114	- Resident disposable income growth
115	- Consumer confidence if available
116	- PMI or local industrial activity if available
117
118	### Population Flow Data
119
120	- Permanent population change
121	- Net population inflow or outflow
122	- Young population share if available
123	- Household registration change if available
124	- Employment inflow if available
125
126	If data is missing, do not block the forecast. Mark Data Gap and lower confidence according to `scoring_model.md`.
127
128	## Economic Cycle and Population Flow Overlay
129
130	Economic cycle and population flow correct the final judgment but do not replace the core housing model.
131
132	- Economic expansion can improve income expectations, employment stability, and purchase confidence.
133	- Economic downturn can weaken income expectations, raise employment pressure, and reduce willingness to add leverage.
134	- Net population inflow supports long-term demand, especially in core districts.
135	- Net population outflow weakens long-term demand, especially in non-core areas and high

luyou666Publisher · 1 listing

Preview

luyou666/china-housing-forecast-lite-skill

# 中国房地产趋势预测 Skill / China Real Estate Trend Forecast Skill

Use this skill to produce concise, evidence-driven forecasts for Chinese residential real estate markets. Keep the analysis centered on housing-market data: pri

Do not turn the forecast into a broad macroeconomic report, crawler system, or machine-learning system. Economic cycle and population flow are important overlay

Standard disclaimer for formal outputs: 仅供交流学习娱乐，不提供投资建议，所有解释权归作者所有。

Repoluyou666/china-housing-forecast-lite-skill

LicenseMIT

TypeSkills

CategoryData

UpdatedMay 2026

Repo stars27

First seenJul 22, 2026

People who liked this also viewed

6 picks

Type