Skip to content
Agentmart
Submit a tool

condition-based-screening

根据用户已经明确给出的筛选条件,在电话网络号码集合中执行规则过滤,找出“满足这些条件”的对象,并输出筛选链路、命中号码、命中原因和证据附件。核心任务是条件命中,不是风险排行榜;适用于用户明确提出“筛选/过滤/满足条件/按省份/按标签/按阈值/同时满足”等规则约束的场景,例如筛选夜间通话占比超过阈值、联系人广度高于阈值…

Skill by bettercallfan

IndexedMIT
Write a review

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-condition-based-screening

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

根据用户已经明确给出的筛选条件,在电话网络号码集合中执行规则过滤,找出“满足这些条件”的对象,并输出筛选链路、命中号码、命中原因和证据附件。核心任务是条件命中,不是风险排行榜;适用于用户明确提出“筛选/过滤/满足条件/按省份/按标签/按阈值/同时满足”等规则约束的场景,例如筛选夜间通话占比超过阈值、联系人广度高于阈值、共享设备数量达到阈值的号码。不用于系统自动发现最可疑号码、不生成全量 TopN 风险榜、不做综合风险排名、不承担单号码证据包、原始数据建图或地域对比。

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/condition-based-screening

What's inside

Skill name
condition-based-screening
Description
根据用户已经明确给出的筛选条件,在电话网络号码集合中执行规则过滤,找出“满足这些条件”的对象,并输出筛选链路、命中号码、命中原因和证据附件。核心任务是条件命中,不是风险排行榜;适用于用户明确提出“筛选/过滤/满足条件/按省份/按标签/按阈值/同时满足”等规则约束的场景,例如筛选夜间通话占比超过阈值、联系人广度高于阈值、共享设备数量达到阈值的号码。不用于系统自动发现最可疑号码、不生成全量 TopN 风险榜、不做综合风险排名、不承担单号码证据包、原始数据建图或地域对比。
License
MIT
Instructions
478 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (32)

  • SKILL.md
  • router_card.json
  • edges_phone_imei.csv · scripts/condition_based_screening_testdata/datasets/phone-network/processed/graph_views/unified/
  • call_edges.csv · scripts/condition_based_screening_testdata/datasets/phone-network/processed/unified/
  • user_nodes.csv · scripts/condition_based_screening_testdata/datasets/phone-network/processed/unified/
  • condition_screening_counterparts_device_case_unified_6rows.csv · scripts/condition_based_screening_testdata/outputs/
  • condition_screening_counterparts_mixed_case_unified_6rows.csv · scripts/condition_based_screening_testdata/outputs/
  • condition_screening_counterparts_night_case_unified_4rows.csv · scripts/condition_based_screening_testdata/outputs/
  • condition_screening_counterparts_unlabeled_case_unified_6rows.csv · scripts/condition_based_screening_testdata/outputs/
  • condition_screening_devices_device_case_unified_2rows.csv · scripts/condition_based_screening_testdata/outputs/
  • condition_screening_devices_mixed_case_unified_1rows.csv · scripts/condition_based_screening_testdata/outputs/
  • condition_screening_devices_night_case_unified_2rows.csv · scripts/condition_based_screening_testdata/outputs/
  • condition_screening_devices_unlabeled_case_unified_3rows.csv · scripts/condition_based_screening_testdata/outputs/
  • condition_screening_evidence_device_case_unified.xlsx · scripts/condition_based_screening_testdata/outputs/
  • condition_screening_evidence_mixed_case_unified.xlsx · scripts/condition_based_screening_testdata/outputs/
  • condition_screening_evidence_night_case_unified.xlsx · scripts/condition_based_screening_testdata/outputs/
  • condition_screening_evidence_unlabeled_case_unified.xlsx · scripts/condition_based_screening_testdata/outputs/
  • condition_screening_report_device_case_unified.md · scripts/condition_based_screening_testdata/outputs/
  • condition_screening_report_mixed_case_unified.md · scripts/condition_based_screening_testdata/outputs/
  • condition_screening_report_night_case_unified.md · scripts/condition_based_screening_testdata/outputs/
  • condition_screening_report_unlabeled_case_unified.md · scripts/condition_based_screening_testdata/outputs/
  • condition_screening_summary_device_case_unified.json · scripts/condition_based_screening_testdata/outputs/
  • condition_screening_summary_mixed_case_unified.json · scripts/condition_based_screening_testdata/outputs/
  • condition_screening_summary_night_case_unified.json · scripts/condition_based_screening_testdata/outputs/
  • condition_screening_summary_unlabeled_case_unified.json · scripts/condition_based_screening_testdata/outputs/
  • condition_screening_targets_device_case_unified_3targets.csv · scripts/condition_based_screening_testdata/outputs/
  • condition_screening_targets_mixed_case_unified_2targets.csv · scripts/condition_based_screening_testdata/outputs/
  • condition_screening_targets_night_case_unified_2targets.csv · scripts/condition_based_screening_testdata/outputs/
  • condition_screening_targets_unlabeled_case_unified_4targets.csv · scripts/condition_based_screening_testdata/outputs/
  • condition_based_screening_wrapper.py · scripts/
  • sample_screening_scope.txt · scripts/
  • test_condition_based_screening.sh · scripts/

SKILL.md (first lines)

# condition-based-screening

## 这个 skill 做什么

`condition-based-screening` 是电话网络数据中的**规则筛选型** skill。

它的核心不是“自动找最可疑对象”,而是:

> 用户已经给出明确筛选条件,系统按照这些条件过滤号码集合,找出满足条件的对象,并解释每个对象命中了哪些规则。

它回答的是:

1. 给定条件能筛出哪些号码;
2. 每个号码具体命中了哪些条件;
3. 筛选过程是否真的缩小了样本范围;
4. 命中对象是否存在共享设备、共同对端等补充证据;
5. 哪些命中对象适合继续做单号码画像、证据包或群体分析。

## 与 topn-high-risk-discovery 的强边界

必须严格区分本 skill 和 `topn-high-risk-discovery`。

| 维度 | condition-based-screening | topn-high-risk-discovery |
|---|---|---|
| 用户意图 | 用户已经给出明确规则 | 用户没有给硬性筛选规则 |
| 核心动作 | 筛选、过滤、命中解释 | 自动打分、排序、发现 |
| 典型词 | 筛选、过滤、满足条件、阈值、同时满足、按省份、按标签 | TopN、Top10、排行榜、最可疑、自动发现、优先核查 |
| 输出重点 | 命中对象、筛选链路、命中原因 | 风险排名、风险分、驱动因素 |
| 是否做综合榜单 | 不做全量风险排行榜 | 做全量或候选集风险排行榜 |

如果用户说:

- “筛选夜间通话明显异常的号码”;
- “过滤出四川省风险标签对象”;
- “找同时满足联系人广度高、共享设备多的号码”;
- “按阈值找夜间占比超过 0.35 的对象”;

应使用本 skill。

如果用户说:

- “自动找 Top10 高风险号码”;
- “生成高风险排行榜”;
- “哪些号码最可疑”;
- “综合评分排序所有号码”;

应使用 `topn-high-risk-discovery`,不是本 skill。

## 适合使用的场景

本 skill 适合规则筛选、条件命中、候选集合收缩类问题,例如:

- 筛选夜间通话占比超过阈值的号码;
- 筛选联系人广度高于阈值的号码;
- 筛选共享设备数量达到阈值的号码;
- 筛选四川省或陕西省中的特定标签对象;
- 筛选风险标签对象或未标注但满足可疑条件的对象;
- 筛选同时满足多个条件的号码;
- 验证某类目标画像在数据中是否存在;
- 输出筛选链路、命中号码、证据表和工作簿附件。

## 不适合使用的场景

以下情况不要使用本 skill:

- 用户没有给明确条件,只想让系统自动发现最可疑号码;
- 用户要求生成 TopN 高风险排行榜;
- 用户要求对全部号码做综合风险评分排序;
- 用户要求解释某一个号码为什么可疑;
- 用户要求生成单号码风险证据包;
- 用户上传原始 CSV,要求先建图;
- 用户要求四川和陕西做地域对比;
- 用户要求跨省同实体联动识别。

对应应转向:

- 自动高风险排行榜:`topn-high-risk-discovery`;
- 单号码画像:`single-number-analysis`;
- 单号码风险证据包:`risk-evidence-pack`;
- 原始数据建图:`dataset-onboarding-graph-preprocess`;
- 四川陕西地域对比:`sichuan-shaanxi-comparison`;
- 跨省可联动性判断:`dataset-quality-and-linkability-diagnostic`。

---

## 一、数据集使用规则

### 规则 1:用户明确指定数据集时,优先使用用户指定的数据集

如果用户问题或命令中明确给出:

- `--dataset-root /workspace/imiss-deer-flow-main/datasets/phone-network`
- `--dataset-root /mnt/datasets/phone-network`
- `--dataset unified`
- “使用 unified / sichuan / shaanxi 数据”

则直接按用户指定执行。

### 规则 2:用户没有指定数据集根目录时,优先使用真实 unified 预处理数据

脚本优先自动查找以下真实数据位置:

1. `PHONE_NETWORK_DATASETS_ROOT`
2. `<repo_root>/datasets/phone-network`
3. `/mnt/datasets/phone-network`
4. `/workspace/imiss-deer-flow-main/datasets/phone-network`
5. `~/imiss-deer-flow-main/datasets/phone-network`

### 规则 3:用户没有指定 dataset 时,默认使用 `unified`

前端问题中出现:

- “在现有电话网络数据里筛选”;
- “在 unified 电话网络数据里筛选”;
- “用已预处理好的数据筛选”;

都应默认理解为:

```text

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

Cite this page

condition-based-screening skill. Agent Mart. https://agentmart.dev/skills/bettercallfan-condition-based-screening (last updated 2026-10-24)