Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

客户诉求抽取 Skill · aifinlab | DecimalAI

sales supportby aifinlab

客户诉求抽取 Skill

aifinlab/customer-intent-extraction

Source aifinlab/finclaw ↗License Apache-2.0

用于工单/对话诉求抽取的客户诉求抽取原子 skill，适用于通用行业信息抽取场景。

SkillScore74Maintained

Automatic

Support pack

Last verified 8/28/2026

What it changes

Passed 17 of 23 test cases with the skill, and 4 of 23 without it.

Without skill17%

With skill74%

Checks it passed that the model alone missed

The JSON includes top-level key source_info.
The sentiment section contains sentiment_score.
The JSON output contains top-level key priority.

and 16 more in the full report

13 fixed4 passed either way6 still failing0 broke

Pass-rate lift: +57 pp
Tokens: +115%
Agent turns: 0%
Response time: +5%

Model gemini-3.6-flashMeasured 8/28/2026v117 of 23 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/aifinlab-customer-intent-extraction/SKILL.md https://app.decimal.ai/s/aifinlab-customer-intent-extraction/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add aifinlab-customer-intent-extraction, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/aifinlab-customer-intent-extraction/ and pins it in .decimal/skills.lock

decimalai skills add aifinlab-customer-intent-extraction

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/aifinlab-customer-intent-extraction/SKILL.md https://app.decimal.ai/s/aifinlab-customer-intent-extraction/SKILL.md

Raw file: /s/aifinlab-customer-intent-extraction/SKILL.md ↗ · machine-readable summary at /s/aifinlab-customer-intent-extraction.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 13

Prompt

对话纪录：'用户：上次承诺的 50 元代金券还没发到我账户里，请帮忙查一下。客服：收到，请提供一下账户名。用户：账户名是 user_test01。' 请给出抽取 JSON。

What was checked, without and with the skill
Checked	Without skill	With skill
The entities field identifies user_test01 as customer information.	Missed	Passed
The JSON includes top-level key source_info.	Missed	Passed

case-22 · gemini-3.6-flash · 8/28/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md162 linessingle file

客户诉求抽取 Skill

数据来源

本 Skill 支持多种客户交互数据输入格式，核心数据来源包括：

1. 对话数据

客服对话：在线客服对话记录、电话客服录音转写
聊天记录：即时通讯聊天记录、社交媒体对话
邮件往来：客户邮件、回复邮件
工单系统：工单描述、工单回复、工单处理记录

2. 文本数据格式

纯文本格式：.txt 文件，UTF-8编码
结构化文档：JSON格式对话数据、CSV格式工单数据
数据库文本字段：从数据库直接读取的文本内容
API接口数据：通过API获取的对话和工单数据

3. 元数据信息

客户信息：客户ID、客户类型、客户等级
时间信息：对话时间、工单创建时间、处理时间
渠道信息：对话渠道、工单来源、联系方式
标签信息：预设标签、分类标签、优先级标签

4. 数据格式要求

文件路径：本地文件路径或网络文件URL
文件编码：UTF-8、GBK、GB2312等
数据完整性：需要包含完整的对话上下文

说明：本 Skill 不包含数据采集功能，需要用户提供清洗后的对话和工单数据。建议数据包含完整的对话上下文，以便进行准确的诉求抽取。

功能

本 Skill 提供全面的客户诉求抽取能力，涵盖多种抽取功能：

1. 诉求类型识别

咨询类诉求：产品咨询、服务咨询、政策咨询
投诉类诉求：服务投诉、产品质量投诉、流程投诉

Track record

Benchmark

17 / 23

test cases passed, vs 4 / 23 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

aifinlab / finclaw

skills/customer-intent-extraction/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

客户诉求抽取 Skill

数据来源

1. 对话数据

2. 文本数据格式

3. 元数据信息

4. 数据格式要求

功能

1. 诉求类型识别

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills