Skip to content
Agentmart
Submit a tool

sichuan-shaanxi-comparison

比较四川与陕西电话网络数据在对象规模、风险标签、行为模式、共享设备规模、群体结构、时间覆盖和代表性对象上的地域差异。该 skill 只做地域对比和汇报材料,不做跨省同实体联动、跨省共享设备识别或跨省共同对端识别。

Skill by bettercallfan

IndexedMIT
Write a review

Chalk Labs

Need help deploying sichuan-shaanxi-comparison?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/bettercallfan-sichuan-shaanxi-comparison

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

比较四川与陕西电话网络数据在对象规模、风险标签、行为模式、共享设备规模、群体结构、时间覆盖和代表性对象上的地域差异。该 skill 只做地域对比和汇报材料,不做跨省同实体联动、跨省共享设备识别或跨省共同对端识别。

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/sichuan-shaanxi-comparison

What's inside

Skill name
sichuan-shaanxi-comparison
Description
比较四川与陕西电话网络数据在对象规模、风险标签、行为模式、共享设备规模、群体结构、时间覆盖和代表性对象上的地域差异。该 skill 只做地域对比和汇报材料,不做跨省同实体联动、跨省共享设备识别或跨省共同对端识别。
License
MIT
Instructions
253 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (4)

  • SKILL.md
  • router_card.json
  • sichuan_shaanxi_comparison_wrapper.py · scripts/
  • test_sichuan_shaanxi_comparison.sh · scripts/

SKILL.md (first lines)

# sichuan-shaanxi-comparison

## 作用定位

`sichuan-shaanxi-comparison` 是电话网络数据分析体系中的**地域对比分析 skill**,面向已经预处理成统一图结构的电话网络数据,专门比较四川与陕西两个地区在对象规模、风险标签、通话行为、共享设备、群体结构和代表性对象上的差异。

它用于回答:

- 四川和陕西的数据规模有什么不同?
- 两地风险对象分布有什么不同?
- 两地通话活跃度、联系人广度、夜间行为有什么不同?
- 两地共享设备和设备池风险是否不同?
- 两地群体结构和代表性对象有什么差异?
- 后续应调用哪些 skill 继续下钻?

本 skill 不输出最终定性结论,只输出基于当前数据的地域差异证据和后续研判入口。

---

## 必须注意:不要用其他 skill 替代本 skill

当前任务只要明确要求“四川-陕西对比”“四川与陕西地域对比”“两省风险特征/行为模式/群体结构差异”,必须优先运行本目录下的:

```bash
sichuan_shaanxi_comparison_wrapper.py
```

不要用 `condition-based-screening` 的两个省份筛选结果手工拼接来替代本 skill。原因是:

- `condition-based-screening` 是条件筛选工具,适合回答“满足某些条件的对象有哪些”;
- `sichuan-shaanxi-comparison` 是全量地域对比工具,适合回答“两地整体差异是什么”;
- 两者可以互补,但不能互相替代。

本 skill 生成的正式文件名必须以:

```text
sichuan_shaanxi_comparison_
```

开头。如果输出文件全是 `condition_screening_...`,说明前端没有正确执行本 skill。

---

## 适用数据

默认使用电话网络统一数据集:

```text
/mnt/datasets/phone-network/processed/unified/user_nodes.csv
/mnt/datasets/phone-network/processed/unified/call_edges.csv
/mnt/datasets/phone-network/processed/graph_views/unified/edges_phone_imei.parquet
```

在本地项目 Docker 容器中测试时,通常路径为:

```text
/workspace/imiss-deer-flow-main/datasets/phone-network/processed/unified/user_nodes.csv
/workspace/imiss-deer-flow-main/datasets/phone-network/processed/unified/call_edges.csv
/workspace/imiss-deer-flow-main/datasets/phone-network/processed/graph_views/unified/edges_phone_imei.parquet
```

如果用户没有指定数据集,优先使用:

```text
dataset=unified
```

---

## 与基础算子的关系

本 skill 是由电话网络基础图分析算子组合实现的,不是单独脱离现有体系的新逻辑。

| 分析内容 | 对应基础算子风格 |
|---|---|
| 对象规模、标签分布、省份分布 | `node_lookup + aggregation_query` |
| 通话记录规模、联系人广度、夜间占比 | `relationship_filter + aggregation_query` |
| 共享设备、设备池、跨省设备样例 | `query_shared_device + aggregation_query` |
| 代表性对象排序 | `aggregation_query + scoring_layer` |
| 群体结构指标 | `subgraph_by_nodes / aggregation_query + scoring_layer` |
| 地域差异解释 | `province filter + metric contrast + evidence ranking` |

---

## 分析口径

本 skill 默认做的是**全量地域对比**,不是条件筛选。

它会比较:

1. 对象规模和风险比例;
2. `label / sub_label` 分布;
3. 通话记录、联系人广度、夜间占比;
4. 时间覆盖与归一化行为强度;
5. 共享设备、设备池和高挂载设备;
6. 群体结构指标;
7. 两省代表性对象和共享设备样例。

由于四川和陕西数据的时间覆盖可能不同,报告中会明确给出“时间可比性提醒”。跨省比较时,应优先参考人均、日均和比例类指标,不要只看原始通话总量。

---

## 运行方式

### 前端/平台默认运行

```bash
cd /mnt/skills/custom/phone-network-analysis/sichuan-shaanxi-comparison/scripts && python3 sichuan_shaanxi_comparison_wrapper.py \
  --dataset unified \
  --province-a sichuan \
  --province-b shaanxi \
  --top-k 10
```

### 本地项目容器运行

```bash
cd /workspace/imiss-deer-flow-main/skills/custom/phone-network-analysis/sichuan-shaanxi-comparison/scripts
python3 sichuan_shaanxi_comparison_wrapper.py \

From bettercallfan/deerflow, MIT.

More from bettercallfan/deerflow

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
May 26, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from bettercallfan

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get sichuan-shaanxi-comparison running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying sichuan-shaanxi-comparison?

CallGet help
Cite this page

sichuan-shaanxi-comparison skill. Agent Mart. https://agentmart.dev/skills/bettercallfan-sichuan-shaanxi-comparison (last updated 2026-10-24)