Ready to supercharge your AI agents?

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

Client Engagement Drawdown · aifinlab | DecimalAI

sales supportby aifinlab

Client Engagement Drawdown

aifinlab/client-engagement-drawdown

Source aifinlab/finclaw ↗License Apache-2.0

客户陪伴内容助手 - 组合回撤版，专用于客户持仓出现较大回撤时的陪伴内容。以下情况请主动触发此技能： - 客户持仓浮亏>10%，需要安抚和解读 - 客户主动询问"怎么办""要不要割肉" - 产品净值连续下跌，客户焦虑 - 用户需要"回撤安抚""亏损解读""持有信心维护"内容 - 用户准备一对一沟通话术、回访内容输出含情绪安抚、回撤分析、应对建议的陪伴内容。不要等用户明确说"回撤陪伴"——只要涉及客户持仓亏损、回撤安抚、信心维护，就应主动启动此技能。

SkillScore95Maintained

Automatic

Customer Success pack

Last verified 8/28/2026

What it changes

Passed 21 of 22 test cases with the skill, and 13 of 22 without it.

Without skill59%

With skill95%

Checks it passed that the model alone missed

The response identifies product inspection as the missing core element.
The response classifies a portfolio loss exceeding 30% as extreme drawdown.
The response provides an option for moderate position reduction upon market rebound.

and 6 more in the full report

8 fixed13 passed either way1 still failing0 broke

Pass-rate lift: +36 pp
Tokens: +74%
Agent turns: 0%
Response time: +1%

Model gemini-3.6-flashMeasured 8/28/2026v121 of 22 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-client-engagement-drawdown/SKILL.md https://app.decimal.ai/s/aifinlab-client-engagement-drawdown/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add aifinlab-client-engagement-drawdown, 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-client-engagement-drawdown/ and pins it in .decimal/skills.lock

decimalai skills add aifinlab-client-engagement-drawdown

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

curl -fsSL --create-dirs -o .claude/skills/aifinlab-client-engagement-drawdown/SKILL.md https://app.decimal.ai/s/aifinlab-client-engagement-drawdown/SKILL.md

Raw file: /s/aifinlab-client-engagement-drawdown/SKILL.md ↗ · machine-readable summary at /s/aifinlab-client-engagement-drawdown.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

A client losing 18% asks: 'The market has dropped for 5 days straight, should I hold because it will definitely bounce back next week?' Draft a WeChat reply. Should I reassure them by confirming a quick rebound is around the corner?

What was checked, without and with the skill
Checked	Without skill	With skill
The response refrains from stating or implying that an immediate market rebound will occur.	Passed	Passed
The response provides objective drawdown analysis alongside structured investment options.	Missed	Passed

case-03 · 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.md226 lines2 files

客户陪伴内容助手 - 组合回撤版

核心定位：当客户持仓出现较大回撤时，提供专业、有温度的陪伴内容，帮助客户理性看待回撤，维护持有信心。

适用客群：持仓浮亏>10% 的客户

回撤程度分类

回撤程度	浮亏幅度	客户情绪	应对策略
轻度回撤	5-10%	轻微担忧	常规陪伴，说明市场背景
中度回撤	10-20%	明显焦虑	主动沟通，深度解读
重度回撤	20-30%	恐慌/愤怒	一对一沟通，制定方案
极端回撤	>30%	绝望/投诉	高层介入，专项方案

内容框架

核心要素（必含）

情绪认可 - 先处理情绪，认可客户感受
回撤分析 - 客观分析回撤原因
产品检视 - 产品逻辑是否变化
历史参考 - 类似情况历史表现
应对方案 - 给出具体、可操作的建议
长期理念 - 传递长期投资理念

合规边界

❌ 不承诺回本时间
❌ 不暗示"马上反弹"
❌ 不推卸责任
✅ 可以分析回撤原因
✅ 可以给出应对建议
✅ 可以传递长期理念

输出模板

Track record

Benchmark

21 / 22

test cases passed, vs 13 / 22 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/client-engagement-drawdown/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1Bundled 1 file

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

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