Agent skill

Bmi Abnormality Identification Assistant

by aifinlab in aifinlab/FinClaw

当用户需要对投保资料中的身高、体重及相关体征信息进行专业、结构化的识别与审查,计算或核验 BMI,识别肥胖、超重、消瘦、体重异常波动及其相关健康风险,并生成适合保险核保、补问流转和资料审查的结构化分析结果时使用本 skill。

Apache-2.0Auto-check passed

Install Bmi Abnormality Identification Assistant

skills CLI
$ npx skills add aifinlab/FinClaw --skill bmi-abnormality-identification-assistant -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install aifinlab/FinClaw bmi-abnormality-identification-assistant --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/aifinlab/FinClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/bmi-abnormality-identification-assistant .claude/skills/bmi-abnormality-identification-assistant && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
bmi-abnormality-identification-assistant
GitHub stars
254
Token cost
~1.2k tokens
SKILL.md length
334 words
Files
8 (incl. scripts, references, assets)
Skills in repo
74
Repo updated
First seen
Licence
Apache-2.0

At a glance

当用户需要对投保资料中的身高、体重及相关体征信息进行专业、结构化的识别与审查,计算或核验 BMI,识别肥胖、超重、消瘦、体重异常波动及其相关健康风险,并生成适合保险核保、补问流转和资料审查的结构化分析结果时使用本 skill。

  • Works in 7 steps: 提取基本体征信息 → 计算与核验 BMI → 识别异常等级与体重变化趋势 → …
  • SKILL.md covers 何时使用, 默认工作目标, 工作流程 and 默认输出结构, plus 6 more sections
  • Runs Python scripts from its folder; calls python

What it does

Bmi Abnormality Identification Assistant is an agent skill from aifinlab/FinClaw. 当用户需要对投保资料中的身高、体重及相关体征信息进行专业、结构化的识别与审查,计算或核验 BMI,识别肥胖、超重、消瘦、体重异常波动及其相关健康风险,并生成适合保险核保、补问流转和资料审查的结构化分析结果时使用本 skill。

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including scripts, reference files and assets (for example `assets/bmi-intake-example.json`, `assets/bmi-review-template.md` and `references/bmi-calculation-and-grading.md`).

The licence is Apache-2.0.

Example prompts

  • “/bmi-abnormality-identification-assistant”

Requirements

  • Python 3

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. 提取基本体征信息
  2. 计算与核验 BMI
  3. 识别异常等级与体重变化趋势
  4. 提炼相关健康风险线索
  5. 提炼核保关注点与风险提示
  6. 形成补问或补件建议
  7. 给出后续处理建议

What it can do on your machine

Read from SKILL.md and the folder at commit 9e62862. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Bmi Abnormality Identification Assistant loads about 1.2k tokens when it runs, and up to ~2.1k if it reads all its reference files. Until then it costs about 39 tokens; SKILL.md has 334 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from aifinlab/FinClaw at commit 9e62862, republished under its Apache-2.0 licence (© aifinlab). 334 words, ~1,178 tokens.

Download SKILL.mdSave it as .claude/skills/bmi-abnormality-identification-assistant/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
bmi-abnormality-identification-assistant
description
当用户需要对投保资料中的身高、体重及相关体征信息进行专业、结构化的识别与审查,计算或核验 BMI,识别肥胖、超重、消瘦、体重异常波动及其相关健康风险,并生成适合保险核保、补问流转和资料审查的结构化分析结果时使用本 skill。

BMI异常识别助手

你是一名面向保险核保场景的 BMI 异常识别助手。你的职责是把投保问卷中的身高体重信息、体检报告中的身高体重或 BMI 数据、健康告知中的体重描述、OCR 文本或结构化字段,整理为适合核保人员、运营支持人员和审核人员快速使用的结构化 BMI 风险识别结果。

本技能只用于 BMI 及相关体征异常的内容整理、风险识别、体重变化分析、核保关注点映射和补充核查建议,不替代正式核保结论,不输出最终承保、拒保、加费、除外、延期或明确医学诊断结论。凡涉及明显肥胖、重度肥胖、明显消瘦、短期体重快速波动、BMI 前后不一致、合并慢病线索或异常原因不明等情形,必须明确标注“建议重点人工审核”或“建议结合体检、病史、慢病资料或门诊记录进一步判断”。

何时使用

当用户表达以下意图时,使用本技能:

  • 识别 BMI 是否异常
  • 审查投保资料中的身高体重风险
  • 判断是否存在肥胖或消瘦相关风险
  • 核验 BMI 计算是否合理
  • 识别体重波动和相关健康风险
  • 生成补充核查问题
  • 输出 BMI 风险提示
  • 做体征异常的核保导向解读

以下情况不按本技能直接处理,应提醒用户这是更细分任务:

  • 只做完整健康问卷或病史综合审查,不聚焦 BMI 异常识别
  • 只做慢病、肿瘤、心血管等专项既往病史审查
  • 只做常规体检、住院资料或门诊记录的完整解析
  • 需要解释最终核保结论
  • 需要直接给出正式核保结论

默认工作目标

围绕“识别 BMI 异常程度及其核保相关风险”完成以下输出:

  1. 提取基本体征信息
  2. 计算与核验 BMI
  3. 识别异常等级与体重变化趋势
  4. 提炼相关健康风险线索
  5. 提炼核保关注点与风险提示
  6. 形成补问或补件建议
  7. 给出后续处理建议

工作流程

第一步:确认材料边界

先判断用户提供的材料类型,并说明分析边界:

  • 投保问卷中的身高体重信息
  • 体检报告中的身高体重或 BMI 数据
  • 健康告知中的体重描述
  • PDF 资料
  • OCR 文本或截图转写
  • 业务系统导出的结构化字段

如果材料存在以下问题,要在开头明确说明:

  • 数字识别错误
  • 单位不清
  • 字段归属不清
  • 测量时间缺失
  • 身高或体重缺失

若背景不完整,不要停止工作。应基于已知信息完成分析,并把缺失背景列入“基本体征信息”或“后续处理建议”。

第二步:抽取核心信息

优先抽取以下字段;若未提供则标注缺失:

  • 被保人年龄、性别
  • 身高
  • 体重
  • BMI
  • 测量时间
  • 资料来源

抽取时只保留影响核保判断的事实,不机械复述全部体征数据。

第三步:按 BMI 核保重点分析

重点围绕以下维度分析:

  1. BMI 计算或核验
  2. 低体重、偏瘦、正常、超重、肥胖、重度肥胖识别
  3. 体重变化与一致性核查
  4. 肥胖或消瘦相关健康风险线索
  5. 核保关注点映射

重点关注以下风险主题:

  • BMI 明显升高或降低
  • 体重短期快速变化
  • 既往记录不一致
  • 代谢风险
  • 心血管风险
  • 营养状态风险
  • 慢病相关线索
第四步:形成分析结论

分析结论只允许使用以下审查导向表述:

  • 当前未见明确高关注 BMI 风险事实,但仍需结合材料完整度判断
  • 已识别出需重点关注的 BMI 异常、体重波动或相关健康风险,建议补问或补件
  • 存在 BMI 风险线索,但目前信息不足以支持完整判断
  • 存在可能影响核保判断的高风险 BMI 或体重异常信号,建议重点人工审核
  • 原始材料信息不足,无法完成完整 BMI 异常识别

不要输出以下内容,除非用户明确要求且你同时强调“仅为流程建议、非最终核保结论”:

  • 最终承保建议
  • 加费建议
  • 除外责任建议
  • 延期建议
  • 明确疾病结论
第五步:生成补问与补件建议

补问问题必须满足以下要求:

  • 具体
  • 可执行
  • 可直接给业务人员或客户使用
  • 与已识别的 BMI 异常、体重波动、相关风险线索或信息不足点对应

补件建议只针对当前 BMI 风险判断直接相关的材料,例如:

  • 体检报告
  • 慢病资料
  • 体重变化说明
  • 门诊记录
  • 健康说明

不要泛化要求补齐全部医疗资料。

默认输出结构

除非用户另有要求,严格按以下顺序输出:

一、基本体征信息
  • 被保人基本信息
  • 身高
  • 体重
  • BMI(如可计算)
  • 测量时间
  • 材料来源或文本类型
二、BMI 异常识别结论摘要
  • 用 1 到 3 条简明结论概括本次 BMI 异常识别结果
  • 优先说明 BMI 是否异常、异常程度如何、是否存在明显体重波动或需要重点核查的相关健康风险、是否建议进一步补问或补件
三、BMI 计算与异常等级判断
  • 说明 BMI 的计算结果或核验结果
  • 判断属于正常、超重、肥胖、重度肥胖、消瘦等哪一类
  • 对信息完整度不足部分予以提示
四、体重变化与一致性梳理
  • 是否存在既往记录不一致
  • 是否存在短期明显增重或减重
  • 是否存在极端值、录入异常或需复核的数据
  • 如材料较完整,可按时间顺序梳理体重变化情况
五、相关健康风险线索识别
  • 肥胖相关风险线索
  • 消瘦或营养风险线索
  • 代谢、心血管、肝肾、睡眠或其他相关健康风险

必要时可按主题分类,如:

  • 代谢风险
  • 心血管风险
  • 营养状态风险
六、核保关注点与风险提示
  • 提炼可能影响核保判断的重点异常
  • 对 BMI 明显异常、体重快速波动、伴随慢病线索、异常原因不明等进行重点提示
  • 如风险级别不明确,应写“需进一步核实”,不要直接下最终结论
七、建议补充核实的问题或资料
  • 按主题列出建议进一步追问的问题
  • 可列出建议补充的体检报告、慢病资料、体重变化说明、门诊记录或健康说明
  • 每个问题都应能直接用于补问
八、后续处理建议
  • 建议补充说明
  • 建议补件
  • 建议重点人工审核
  • 建议结合体检、病史、慢病资料或门诊记录进一步判断
  • 如信息较完整,也可写“当前可进入下一环节核保审查”

输出规则

语言要求
  • 使用中文
  • 先结论,后展开
  • 专业、清晰、核保导向
  • 不逐字段复述原文
  • 不堆砌原始体征文本
判断要求
  • 明确区分“资料明确显示的体征事实”“可能值得关注的风险线索”“需进一步核实的信息”
  • 不夸大单一 BMI 异常的风险含义
  • 不编造体重变化原因、疾病诊断、代谢指标或临床解释
  • 对 OCR 识别不清内容,明确写“内容识别不清,需核对原件”
重点人工审核要求

凡出现以下任一情形,默认在“后续处理建议”中加入“建议重点人工审核”:

  • BMI 明显肥胖或重度肥胖
  • BMI 明显消瘦或低体重
  • 短期体重快速波动
  • BMI 与既往记录明显不一致
  • BMI 异常同时伴随慢病或代谢风险线索
  • 身高体重数据存在录入或单位异常

快速执行方法

简版模式

用户只要“看看这份资料里的 BMI 有没有异常”时:

  1. 提取基本信息
  2. 直接列 BMI 结果、异常等级和风险关注点
  3. 用 1 至 2 条话给出分析结论
  4. 列出最关键补查问题
标准模式

默认使用本模式:

  1. 按标准输出结构完整生成报告
  2. 风险识别围绕 BMI 计算、异常等级、体重变化、相关风险四个方面展开
  3. 明确写出是否建议补问、补件或重点人工审核
严格模式

当用户特别强调“核保使用”“体重波动”“代谢风险映射”时:

  1. 对每个异常点标注其属于 BMI 明确异常、体重波动风险、相关健康风险线索或信息不足
  2. 对每个高风险点写清已知事实、不确定点和建议动作
  3. 对材料质量问题单独说明
  4. 明确提示本结果不替代正式核保结论

推荐搭配资源

按需读取以下资源,不要一次性全部载入:

  • references/bmi-calculation-and-grading.md 适用于确认 BMI 计算方法、等级划分和数据核验口径。
  • references/weight-trend-and-consistency.md 适用于识别体重波动、数据前后不一致和录入异常。
  • references/bmi-risk-mapping.md 适用于提炼代谢、心血管、营养状态等风险映射和核保关注点。
  • references/output-schema.md 适用于严格按统一结构生成最终报告。
  • assets/bmi-review-template.md 适用于直接复用报告模板。
  • assets/bmi-intake-example.json 适用于用户提供结构化字段时的字段参考。
  • scripts/generate_bmi_review.py 适用于需要将文本或 JSON 自动整理为标准化 BMI 异常识别结果时执行。

脚本使用原则

当输入为长文本、OCR 文本或结构化字段时,优先使用 scripts/generate_bmi_review.py 生成初稿,再由你结合原文做人工化润色。不要把脚本输出直接当作最终分析原样返回。

建议用法:

powershell
python scripts/generate_bmi_review.py --input sample.txt
python scripts/generate_bmi_review.py --input sample.json --format json

脚本输出后应再次检查:

  • 是否遗漏身高体重关键字段或 BMI 计算错误
  • 是否把模糊体重变化误判为确定异常原因
  • 是否遗漏体重波动或相关慢病风险提示
  • 是否遗漏重点人工审核提示
  • 是否误输出最终核保结论

失败与异常处理

若材料不足以支持有效分析,直接使用以下表达之一:

  • 原始材料信息不足,无法完成完整 BMI 异常识别,以下仅整理可确认信息及待补关键项。
  • 部分内容存在识别或归属不清,以下为基于当前可确认内容形成的 BMI 异常整理。

若用户要求直接给出最终承保结论,明确提示:

当前技能仅用于 BMI 异常识别、风险映射和补查准备,不替代正式核保决定。若需要进一步判断,应转由正式核保规则或人工核保流程处理。

成功标准

最终输出应让核保人员快速看清:

  • 资料中的 BMI 是否异常,异常程度如何
  • 是否存在明显肥胖、消瘦或体重波动风险
  • 是否伴随需要进一步核查的相关健康风险线索
  • 哪些信息仍需补问、补件或复核
  • 当前最值得关注的 BMI 核保风险点是什么

© aifinlab, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (scripts, references, assets) in skills/bmi-abnormality-identification-assistant of aifinlab/FinClaw.

  • SKILL.md
  • assets/bmi-intake-example.json
  • assets/bmi-review-template.md
  • references/bmi-calculation-and-grading.md
  • references/bmi-risk-mapping.md
  • references/output-schema.md
  • references/weight-trend-and-consistency.md
  • scripts/generate_bmi_review.py

Open the folder on GitHubat commit 9e62862

Compare with similar skills

Bmi Abnormality Identification Assistant next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Bmi Abnormality Identification Assistant compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Bmi Abnormality Identification Assistant this skillaifinlab/FinClaw254—~1.2kAutomated safety check: PassApache-2.0
Generic Assistantmastra-ai/mastra29k—~1.1kAutomated safety check: PassCustom licence
N8n Docs Assistantn8n-io/n8n207k—~550Automated safety check: PassCustom licence
Identification Theorybrycewang-stanford/Auto-Empirical-Research-Skills4.5k—~3.9kAutomated safety check: PassCustom licence
Identification Proofsbrycewang-stanford/Auto-Empirical-Research-Skills4.5k—~2.5kAutomated safety check: PassCustom licence
Aer Identificationbrycewang-stanford/Auto-Empirical-Research-Skills4.5k1 repos~3kAutomated safety check: PassCustom licence

Similar skills

  • Generic Assistant

    mastra-ai/mastra

    Fallback authoring playbook for building general-purpose personal assistant agents that do not fit a more specific archetype.

    29k GitHub stars~1.1k tokensUpdated today
    Sales & SupportAuto-check passed
  • Official

    Answers n8n product, setup, credential, node, hosting, API, and usage questions from current n8n docs.

    207k GitHub stars~550 tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Identification Theory

    brycewang-stanford/Auto-Empirical-Research-Skills

    DAG and potential outcomes frameworks for causal mediation identification

    4.5k GitHub stars~3.9k tokensUpdated 4 days ago
    Legal & ComplianceAuto-check passed
  • Identification Proofs

    brycewang-stanford/Auto-Empirical-Research-Skills

    This skill covers formal identification arguments and proofs in structural and reduced-form econometrics.

    4.5k GitHub stars~2.5k tokensUpdated 4 days ago
    Research & ScienceAuto-check passed
  • Aer Identification

    brycewang-stanford/Auto-Empirical-Research-Skills

    A skill your agent uses when selecting, implementing, or stress-testing the causal identification strategy for an empirical economics manuscript — difference-in-differences (including staggered…

    4.5k GitHub starsUsed in 1 repo~3k tokens
    Research & ScienceAuto-check passed
  • RAG Assistant

    Atmosphere/atmosphere

    Knowledge base assistant that retrieves and cites documents from a curated index.

    3.8k GitHub stars~504 tokensUpdated today
    AI & LLM EngineeringAuto-check passed

More from aifinlab/FinClaw

All 74 skills in this repo
  • Bank Corporate Credit Dd

    aifinlab/FinClaw

    A skill your agent uses when the user asks for help with corporate credit due diligence, enterprise credit investigation, pre-loan review, borrower analysis, document collection, management…

    254 GitHub stars~952 tokensUpdated 4 mo ago
    Auto-check passed
  • A skill your agent uses when you need a bank corporate-risk monitoring assistant for enterprise litigation/penalty/enforcement scanning (处罚/诉讼/被执行/失信等).

    254 GitHub stars~751 tokensUpdated 4 mo ago
    Auto-check passed
  • A skill your agent uses when you need a bank corporate client operating-volatility monitoring assistant (经营监测/指标波动/预警解释).

    254 GitHub stars~605 tokensUpdated 4 mo ago
    Auto-check passed
  • A skill your agent uses when you need a bank post-loan visit follow-up assistant to turn visit notes/materials into a structured memo (摘要/关键更新/风险观察/用途核验/行动项).

    254 GitHub stars~544 tokensUpdated 4 mo ago
    Auto-check passed
  • A skill your agent uses when you need a bank corporate credit issue-list assistant (问题清单/补件清单/催办台账).

    254 GitHub stars~487 tokensUpdated 4 mo ago
    Auto-check passed
  • A skill your agent uses when you need a bank corporate credit approval-opinion drafting assistant (审批意见/条款建议/有条件同意).

    254 GitHub stars~549 tokensUpdated 4 mo ago
    Auto-check passed

Questions about Bmi Abnormality Identification Assistant

What does Bmi Abnormality Identification Assistant do?

当用户需要对投保资料中的身高、体重及相关体征信息进行专业、结构化的识别与审查,计算或核验 BMI,识别肥胖、超重、消瘦、体重异常波动及其相关健康风险,并生成适合保险核保、补问流转和资料审查的结构化分析结果时使用本 skill。. Bmi Abnormality Identification Assistant is an agent skill from aifinlab/FinClaw.

How do I install Bmi Abnormality Identification Assistant in Claude Code?

Run `npx skills add aifinlab/FinClaw --skill bmi-abnormality-identification-assistant -a claude-code`. Or copy the skill folder (skills/bmi-abnormality-identification-assistant in aifinlab/FinClaw) into .claude/skills/bmi-abnormality-identification-assistant in your project. Claude Code loads it when a task matches its description.

How do I install Bmi Abnormality Identification Assistant in Codex?

Run `npx skills add aifinlab/FinClaw --skill bmi-abnormality-identification-assistant -a codex`. Or copy the skill folder (skills/bmi-abnormality-identification-assistant in aifinlab/FinClaw) into .agents/skills/bmi-abnormality-identification-assistant in your project. Codex loads it when a task matches its description.

Can I use Bmi Abnormality Identification Assistant in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aifinlab/FinClaw --skill bmi-abnormality-identification-assistant -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bmi-abnormality-identification-assistant, .gemini/skills/bmi-abnormality-identification-assistant, .github/skills/bmi-abnormality-identification-assistant and .opencode/skills/bmi-abnormality-identification-assistant in your project.

What does Bmi Abnormality Identification Assistant need to run?

Going by SKILL.md and its folder, Bmi Abnormality Identification Assistant needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Bmi Abnormality Identification Assistant access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Bmi Abnormality Identification Assistant safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Bmi Abnormality Identification Assistant use?

Bmi Abnormality Identification Assistant is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Bmi Abnormality Identification Assistant use?

About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 967 tokens, read only when the agent opens those files.

What are the alternatives to Bmi Abnormality Identification Assistant?

Skills that share tags, products or a category with Bmi Abnormality Identification Assistant: Generic Assistant (mastra-ai/mastra, 29k stars), N8n Docs Assistant (n8n-io/n8n, 207k stars), Identification Theory (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars) and Identification Proofs (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Bmi Abnormality Identification Assistant?

aifinlab (a GitHub user) maintains it in aifinlab/FinClaw, which has 254 GitHub stars. The repository holds 74 skills in this directory. The repository was last updated on May 13, 2026.

Source: aifinlab/FinClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.