Agent skill

Bank T121 Corporate Finance Creditpre Screen Assistant

by aifinlab in aifinlab/FinClaw

当用户需要在银行对公金融场景下,对企业授信申请做贷前初筛、材料完整性检查、准入红旗识别、补件清单整理、访谈问题设计或初筛意见输出时使用本技能。适合输出结构化初筛结论、风险提示、待核验事项和下一步推进建议。

Apache-2.0Auto-check passed

Install Bank T121 Corporate Finance Creditpre Screen Assistant

skills CLI
$ npx skills add aifinlab/FinClaw --skill bank-t121-corporate-finance-creditpre-screen-assistant -a claude-code

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

GitHub CLI
$ gh skill install aifinlab/FinClaw bank-t121-corporate-finance-creditpre-screen-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/bank-t121-corporate-finance-creditpre-screen-assistant .claude/skills/bank-t121-corporate-finance-creditpre-screen-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
bank-t121-corporate-finance-creditpre-screen-assistant
GitHub stars
255
Token cost
~1.3k tokens
SKILL.md length
156 words
Files
11 (incl. scripts, references, assets)
Skills in repo
74
Repo updated
First seen
Licence
Apache-2.0

At a glance

当用户需要在银行对公金融场景下,对企业授信申请做贷前初筛、材料完整性检查、准入红旗识别、补件清单整理、访谈问题设计或初筛意见输出时使用本技能。适合输出结构化初筛结论、风险提示、待核验事项和下一步推进建议。

  • Works in 5 steps: 主体与治理 → 业务与行业逻辑 → 财务与现金流 → …
  • SKILL.md covers 适用范围, 何时使用, 何时不要使用 and 默认工作流, plus 9 more sections
  • Runs Python scripts from its folder; calls python

What it does

Bank T121 Corporate Finance Creditpre Screen Assistant is an agent skill from aifinlab/FinClaw. 当用户需要在银行对公金融场景下,对企业授信申请做贷前初筛、材料完整性检查、准入红旗识别、补件清单整理、访谈问题设计或初筛意见输出时使用本技能。适合输出结构化初筛结论、风险提示、待核验事项和下一步推进建议。

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files, including scripts, reference files and assets (for example `assets/example-input.json`, `assets/templates/pre-screen-report-template.md` and `assets/templates/supplement-request-template.md`).

The licence is Apache-2.0.

Example prompts

  • “/bank-t121-corporate-finance-creditpre-screen-assistant”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. 主体与治理
  2. 业务与行业逻辑
  3. 财务与现金流
  4. 授信用途与还款来源
  5. 外部风险与增信措施

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 2 files 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

Bank T121 Corporate Finance Creditpre Screen Assistant loads about 1.3k tokens when it runs, and up to ~4.3k if it reads all its reference files. Until then it costs about 39 tokens; SKILL.md has 156 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
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.3k

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). 156 words, ~1,278 tokens.

Download SKILL.mdSave it as .claude/skills/bank-t121-corporate-finance-creditpre-screen-assistant/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.
name
bank-t121-corporate-finance-creditpre-screen-assistant
description
当用户需要在银行对公金融场景下,对企业授信申请做贷前初筛、材料完整性检查、准入红旗识别、补件清单整理、访谈问题设计或初筛意见输出时使用本技能。适合输出结构化初筛结论、风险提示、待核验事项和下一步推进建议。

对公授信初筛助手

这个 skill 用于银行对公授信场景下的第一轮判断。重点不是替代正式尽调或审批,而是在信息还不完整、时间又比较紧的时候,先回答四个关键问题:

  1. 这笔业务现在能不能继续往下推进
  2. 哪些问题已经足以构成明显红旗
  3. 哪些地方还缺关键材料或关键解释
  4. 下一步应该补什么、问什么、查什么

它更适合服务对公客户经理、风险经理、授信审查支持岗和中后台预审人员。输出要能直接支持后续尽调、客户沟通和内部评审,而不是只写一堆泛泛的风险口号。

适用范围

  • 新增对公授信项目的贷前初筛
  • 存量客户续作、增额、展期前的快速复核
  • 客户经理报送前的材料和逻辑自检
  • 审查岗在正式尽调前的预审和问题清单整理
  • 需要生成补件清单、客户访谈问题、红旗提示、初筛结论时
  • 材料来源比较分散,需要先做结构化归集和初步判断时

何时使用

  • 用户说“先帮我看一下这家企业能不能做”“先做一轮授信初筛”“先看有没有明显风险”时
  • 用户提供了企业基本信息、财务摘要、授信申请、流水、合同、发票、司法舆情等零散材料,希望先形成第一轮判断时
  • 用户希望输出补件清单、客户访谈问题、风险提示、初筛结论或内部汇报摘要时
  • 用户暂时拿不到全部材料,但希望先判断哪里最值得优先补查时

何时不要使用

  • 用户要求直接输出最终授信审批结论、批复结论、放款意见时
  • 用户要求伪造授信材料、包装还款来源、淡化重大风险或规避审查时
  • 需要依赖法律意见、审计意见、评估报告、专项行业研究才能完成的判断时
  • 只有极少量片段信息,连主体、授信用途、金额期限都不清楚时

默认工作流

  1. 先统一授信对象、业务场景、时间范围和材料来源。
  2. 归集企业主体信息、授信申请信息、财务信息、经营佐证、外部风险和增信信息。
  3. 检查资料完整性,先识别“缺什么”,再讨论“怎么看”。
  4. 围绕主体真实性、经营逻辑、还款来源、现金流、外部风险和担保措施做第一轮判断。
  5. 把发现的问题区分为硬性阻断项、重点核验项和一般关注项。
  6. 输出初筛结论分级、补件清单、访谈问题和下一步建议。
  7. 明确哪些判断已经具备证据支持,哪些仍需后续尽调或外部核验。

核心分析框架

1. 主体与治理
  • 企业是否真实、存续、经营范围清晰
  • 股权结构和实际控制人是否容易理解
  • 是否存在频繁工商变更、治理失衡或异常授权
  • 是否有隐性关联方、空壳主体或代持嫌疑
2. 业务与行业逻辑
  • 主营业务是否清楚,收入来源是否能解释
  • 业务模式、回款方式、上游采购和下游销售是否闭环
  • 行业景气度、政策敏感度、周期性和替代风险如何
  • 是否存在客户或供应商过度集中
3. 财务与现金流
  • 收入、利润、经营现金流是否互相印证
  • 资产负债率、流动比率、利息保障能力是否明显偏弱
  • 应收、存货、预付款、其他应收等科目是否有异常占用
  • 利润质量是否偏弱,是否存在“有利润、没现金”的情况
4. 授信用途与还款来源
  • 申请用途是否明确、合理、可核验
  • 授信金额和期限是否与业务规模、周转节奏匹配
  • 第一还款来源是否真实、稳定、可穿透
  • 是否存在用途虚化、资金回流、自融或闭环不足的风险
5. 外部风险与增信措施
  • 是否存在重大涉诉、被执行、失信、行政处罚、负面舆情
  • 是否存在民间借贷、交叉担保、集团风险传染等隐患
  • 担保、保证、抵押措施是否形成有效缓释
  • 外部风险是存量已知问题,还是正在恶化的新增问题

初筛结论分级

建议统一用以下四级口径:

  • 可进入下一环节:当前未发现明显硬性阻断项,资料基本完整,可进入正式尽调或审查。
  • 有条件推进:总体可继续推进,但存在资料缺口、局部风险或需要管理层说明的事项。
  • 审慎推进:存在多项重要疑点,建议补件、补查、访谈或升级审查后再决定是否推进。
  • 不建议直接推进:当前已出现明显红旗、证据冲突或还款逻辑难以成立,不建议继续推进。

输入要求

建议尽量覆盖以下信息,缺失时必须显式写明:

  • 企业基础信息:企业名称、统一社会信用代码、成立日期、注册资本、行业、区域、股权结构、实控人
  • 授信申请信息:授信品种、申请金额、期限、用途、增信方式、资金需求背景
  • 财务摘要:收入、毛利、净利润、经营现金流、总资产、总负债、带息负债、应收、存货、资本开支
  • 经营信息:核心产品、主要客户、主要供应商、订单和回款模式、税票和流水摘要
  • 外部风险:涉诉、处罚、失信、舆情、重大异常工商变更、历史违约或逾期信息
  • 增信信息:保证人、抵押物、质押物、保险、保证金、集团支持等
  • 材料状态:已提供材料、缺失材料、需后续补充或解释的材料

详细字段见 input-schema.md。

输出要求

标准输出至少应包含以下部分:

  1. 授信对象与本次初筛任务概况
  2. 已掌握信息与关键缺口
  3. 资料完整性判断
  4. 初筛核心结论
  5. 红旗风险清单
  6. 重点关注事项
  7. 补件清单
  8. 建议访谈问题
  9. 下一步推进建议
  10. 结论边界说明

如果用户需要结构化结果,可直接输出 JSON 风格对象,结构定义见 output-schema.md。

配套脚本

本 skill 已补配套脚本:

  • corporate_credit_pre_screen.py:执行输入解析、资料完整性检查、风险识别、结论分级和 Markdown/JSON 输出
  • run_skill.py:脚本入口

示例调用:

bash
python scripts/run_skill.py --input assets/example-input.json --output result.md --format markdown

如果只想看 JSON 结果:

bash
python scripts/run_skill.py --input assets/example-input.json --format json

参考资料与模板

  • pre-screen-methodology.md
  • risk-red-flags.md
  • interview-question-bank.md
  • pre-screen-report-template.md
  • supplement-request-template.md
  • example-input.json

风险与边界

  • 本技能只做授信初筛,不替代正式尽调、法律审查、评级审批和最终批复。
  • 不得把“客户陈述”直接写成“已核实事实”。
  • 对外部风险、司法舆情、抵押物有效性等事项,若没有权威核验结果,必须标注“待核验”。
  • 不得帮助用户包装流水、伪造合同、虚构用途、规避风控或弱化重大风险。
  • 对信息缺失较多的项目,应优先输出“资料缺口 + 风险清单 + 下一步建议”,而不是强行给出乐观结论。

信息不足时的处理

  • 如果只拿到了基础工商和授信申请信息,先输出最低可行的初筛框架和补件清单。
  • 如果拿到了财务摘要但缺少经营佐证,要把重点放在“还款来源是否可验证”和“经营真实性需补证据”上。
  • 如果发现重大红旗但证据尚不完整,应使用“高度关注”“建议优先核验”“不建议直接推进”之类的审慎表达。
  • 如果材料之间明显冲突,要单独列出矛盾点,不要在正文里一笔带过。

交付标准

  • 读者能看懂当前项目为什么可以推进、为什么需要谨慎,或者为什么不建议推进。
  • 输出能清楚区分硬性阻断项、重点核验项和一般关注项。
  • 补件清单和访谈问题具备可执行性,而不是泛泛要求“补充更多材料”。
  • 若调用脚本,结果至少能产出资料完整性、风险清单、结论分级和下一步建议四类信息。

© 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 10 other files (scripts, references, assets) in skills/bank-t121-corporate-finance-creditpre-screen-assistant of aifinlab/FinClaw.

  • SKILL.md
  • assets/example-input.json
  • assets/templates/pre-screen-report-template.md
  • assets/templates/supplement-request-template.md
  • references/input-schema.md
  • references/interview-question-bank.md
  • references/output-schema.md
  • references/pre-screen-methodology.md
  • references/risk-red-flags.md
  • scripts/corporate_credit_pre_screen.py
  • scripts/run_skill.py

Open the folder on GitHubat commit 9e62862

Compare with similar skills

Bank T121 Corporate Finance Creditpre Screen 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.

Bank T121 Corporate Finance Creditpre Screen Assistant compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Bank T121 Corporate Finance Creditpre Screen Assistant this skillaifinlab/FinClaw255—~1.3kAutomated safety check: PassApache-2.0
Bio Crispr Screens Screen QcFreedomIntelligence/OpenClaw-Medical-Skills3.1k—~2.1kAutomated safety check: PassNone
Open Banking Iodavila7/claude-code-templates33k—~472Automated safety check: PassMIT
Screen Recordinggithub/awesome-copilot40k—~2kAutomated safety check: PassMIT
macOS Screen Recordersickn33/agentic-awesome-skills47k1 repos~727Automated safety check: PassMIT
Generic Assistantmastra-ai/mastra29k—~1.1kAutomated safety check: PassCustom licence

Similar skills

  • Bio Crispr Screens Screen Qc

    FreedomIntelligence/OpenClaw-Medical-Skills

    Quality control for pooled CRISPR screens. An agent skill from FreedomIntelligence/OpenClaw-Medical-Skills.

    3.1k GitHub stars~2.1k tokensUpdated 2 mo ago
    Research & ScienceAuto-check passed
  • Open Banking Io

    davila7/claude-code-templates

    Read bank account balances and transactions from EU/UK banks via the open-banking.io PSD2 API.

    33k GitHub stars~472 tokensUpdated yesterday
    Auto-check passed
  • Screen Recording

    github/awesome-copilot

    Official

    Create annotated animated GIF demos and screen recordings for pull requests and documentation.

    40k GitHub stars~2k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • macOS Screen Recorder

    sickn33/agentic-awesome-skills

    macOS screen recorder that captures the main display PLUS system audio via ScreenCaptureKit — no BlackHole/loopback driver, no sudo, just the standard Screen Recording permission.

    47k GitHub starsUsed in 1 repo~727 tokens
    Auto-check passed
  • 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
  • Model Bank Metadata

    lobehub/lobehub

    Fills and maintains the knowledgeCutoff, family and generation fields on model cards in LobeHub's model bank, from a single new model up to repo-wide backfills.

    83k GitHub stars~2k 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…

    255 GitHub stars~952 tokensUpdated 5 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).

    255 GitHub stars~751 tokensUpdated 5 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).

    255 GitHub stars~605 tokensUpdated 5 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).

    255 GitHub stars~544 tokensUpdated 5 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).

    255 GitHub stars~487 tokensUpdated 5 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).

    255 GitHub stars~549 tokensUpdated 5 mo ago
    Auto-check passed

Questions about Bank T121 Corporate Finance Creditpre Screen Assistant

What does Bank T121 Corporate Finance Creditpre Screen Assistant do?

当用户需要在银行对公金融场景下,对企业授信申请做贷前初筛、材料完整性检查、准入红旗识别、补件清单整理、访谈问题设计或初筛意见输出时使用本技能。适合输出结构化初筛结论、风险提示、待核验事项和下一步推进建议。. Bank T121 Corporate Finance Creditpre Screen Assistant is an agent skill from aifinlab/FinClaw.

How do I install Bank T121 Corporate Finance Creditpre Screen Assistant in Claude Code?

Run `npx skills add aifinlab/FinClaw --skill bank-t121-corporate-finance-creditpre-screen-assistant -a claude-code`. Or copy the skill folder (skills/bank-t121-corporate-finance-creditpre-screen-assistant in aifinlab/FinClaw) into .claude/skills/bank-t121-corporate-finance-creditpre-screen-assistant in your project. Claude Code loads it when a task matches its description.

How do I install Bank T121 Corporate Finance Creditpre Screen Assistant in Codex?

Run `npx skills add aifinlab/FinClaw --skill bank-t121-corporate-finance-creditpre-screen-assistant -a codex`. Or copy the skill folder (skills/bank-t121-corporate-finance-creditpre-screen-assistant in aifinlab/FinClaw) into .agents/skills/bank-t121-corporate-finance-creditpre-screen-assistant in your project. Codex loads it when a task matches its description.

Can I use Bank T121 Corporate Finance Creditpre Screen 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 bank-t121-corporate-finance-creditpre-screen-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/bank-t121-corporate-finance-creditpre-screen-assistant, .gemini/skills/bank-t121-corporate-finance-creditpre-screen-assistant, .github/skills/bank-t121-corporate-finance-creditpre-screen-assistant and .opencode/skills/bank-t121-corporate-finance-creditpre-screen-assistant in your project.

What does Bank T121 Corporate Finance Creditpre Screen Assistant need to run?

Going by SKILL.md and its folder, Bank T121 Corporate Finance Creditpre Screen Assistant needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Bank T121 Corporate Finance Creditpre Screen 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 Bank T121 Corporate Finance Creditpre Screen 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 Bank T121 Corporate Finance Creditpre Screen Assistant use?

Bank T121 Corporate Finance Creditpre Screen 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 Bank T121 Corporate Finance Creditpre Screen Assistant use?

About 1.3k tokens (SKILL.md is roughly 5.1k 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 3k tokens, read only when the agent opens those files.

What are the alternatives to Bank T121 Corporate Finance Creditpre Screen Assistant?

Skills that share tags, products or a category with Bank T121 Corporate Finance Creditpre Screen Assistant: Bio Crispr Screens Screen Qc (FreedomIntelligence/OpenClaw-Medical-Skills, 3.1k stars), Open Banking Io (davila7/claude-code-templates, 33k stars), Screen Recording (github/awesome-copilot, 40k stars) and macOS Screen Recorder (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Bank T121 Corporate Finance Creditpre Screen Assistant?

aifinlab (a GitHub user) maintains it in aifinlab/FinClaw, which has 255 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.