Ready to supercharge your AI agents?

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

Blacklist Screening · aifinlab | DecimalAI

legalby aifinlab

Blacklist Screening

aifinlab/blacklist-screening

Source aifinlab/finclaw ↗License Apache-2.0

黑名单筛查助手，适用于券商合规管理、客户准入、反洗钱、风险监控等场景。以下情况请主动触发此技能： - 用户提供了客户/交易对手名单，问"有没有在黑名单上""帮我筛查一下" - 用户问"黑名单筛查怎么做""命中黑名单怎么处理" - 用户需要：黑名单筛查、命中分析、处置建议 - 用户提到：黑名单、制裁名单、反洗钱、可疑名单、禁入名单 - 用户需要形成筛查报告、合规意见、处置方案不要等用户明确说"黑名单筛查"——只要涉及客户准入筛查、交易对手审查、制裁名单比对，就应主动启动此技能。

SkillScore78Maintained

Automatic

FinServ Compliance pack

Last verified 8/28/2026

What it changes

Passed 18 of 23 test cases with the skill, and 14 of 23 without it.

Without skill61%

With skill78%

Checks it passed that the model alone missed

Outputs the response using Template A structure by default.
Includes a table column displaying confidence scores for matched candidates.
States that full passport number and date of birth are required for precise matching.

and 1 more in the full report

4 fixed14 passed either way5 still failing0 broke

Pass-rate lift: +17 pp
Tokens: +108%
Agent turns: 0%
Response time: +9%

Model gemini-3.6-flashMeasured 8/28/2026v118 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-blacklist-screening/SKILL.md https://app.decimal.ai/s/aifinlab-blacklist-screening/SKILL.md

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

decimalai skills add aifinlab-blacklist-screening

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

curl -fsSL --create-dirs -o .claude/skills/aifinlab-blacklist-screening/SKILL.md https://app.decimal.ai/s/aifinlab-blacklist-screening/SKILL.md

Raw file: /s/aifinlab-blacklist-screening/SKILL.md ↗ · machine-readable summary at /s/aifinlab-blacklist-screening.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

请对以下三位新开户客户进行黑名单比对，帮我快速筛查一下他们是否有命中情况：待筛查客户： 1. 张伟，身份证 310104198506121234 2. John Smith，护照号 P8829102 3. 李明，身份证 110101199203045678 比对黑名单库： - 张伟，身份证 310104198506121234，OFAC制裁名单 - J. Smith，护照号 P8829102，内部违约黑名单 - 赵六，身份证 440301198801019999，失信被执行人请给出简要的筛查结果统计、命中明细表格以及初步的操作建议。

What was checked, without and with the skill
Checked	Without skill	With skill
Includes a table column displaying confidence scores for matched candidates.	Missed	Passed
Advises immediate business rejection for the OFAC sanction hit.	Passed	Passed

case-01 · 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.md409 linessingle file

黑名单筛查助手

你的核心职责：准确进行黑名单筛查比对，识别命中风险，形成清晰的筛查报告和处置建议，支持合规管理和风险防控。

第一步：识别输入类型，选择路径

收到用户请求后，先做两个判断：

判断 1：是否有筛查数据？

用户提供了待筛查名单、黑名单数据库 → 直接进入比对
只有待筛查对象名称 → 先说明需要的数据字段（见下方"数据需求"）
只有简短描述（如"帮我查一下这个客户"） → 可基于描述给出筛查框架，说明"需具体数据才能精准筛查"

判断 2：用户需要哪种深度？

用户意图	适用模板
"有没有命中""快速筛查"	模板 A：快速筛查
"详细分析""筛查报告"	模板 B：标准报告
"合规意见""处置方案"	模板 C：处置版
未明确说明	默认模板 A，再提供"需要详细报告可继续"

数据需求（理想字段）

待筛查对象信息：

姓名/名称（中文/英文）
证件类型、证件号码
出生日期/注册日期
国籍/注册地
地址/注册地址

黑名单数据库：

名单类型（制裁/反洗钱/禁入等）
名单来源（官方/内部/第三方）
名单更新日期
命中规则（精确/模糊）

Track record

Benchmark

18 / 23

test cases passed, vs 14 / 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/blacklist-screening/SKILL.md

View on GitHub ↗

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

Other skills for the same job

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

aifinlab/compliance-risk-alert合规风险提示助手，适用于券商合规管理、风险预警、内控建设、监管报送等场景。以下情况请主动触发此技能： - 用户提供了合规风险数据，问"有什么风险""帮我分析一下" - 用户问"合规风险怎么识别""风险提示怎么写" - 用户需要：合规风险识别、风险提示、整改建议 - 用户提到：合规风险、风险提示、内控缺陷、监管处罚、合规隐患 - 用户需要形成风险提示函、合规报告、整改方案不要等用户明确说"合规风险提示"——只要涉及合规风险识别、内控缺陷分析、监管风险提示，就应主动启动此技能。Close match+44 pp pass-rate lift

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