Three-Statement Model Builder
ginlix-ai/LangAlpha
Builds or repairs an integrated income statement, balance sheet and cash flow model in Excel with live formulas, supporting schedules, scenarios and a Checks sheet.
Cross-checks a client's own registry data against its customers' and suppliers' to surface undisclosed related-party relationships for an audit.
SKILL.md written in Chinese; this summary is our English description.
Install Hidden Related-Party Audit Check
$ npx skills add nigo81/nigo-skills --skill related-party-identification -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install nigo81/nigo-skills related-party-identification --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/nigo81/nigo-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/related-party-identification .claude/skills/related-party-identification && rm -rf skills-srcUse ~/.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/
Install the "related-party-identification" agent skill from https://github.com/nigo81/nigo-skills/tree/main/related-party-identification into .claude/skills/related-party-identification/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "related-party-identification", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/nigo81/nigo-skills/tree/main/related-party-identificationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add nigo81/nigo-skills --skill related-party-identification -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install nigo81/nigo-skills related-party-identification --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nigo81/nigo-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/related-party-identification .agents/skills/related-party-identification && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "related-party-identification" agent skill from https://github.com/nigo81/nigo-skills/tree/main/related-party-identification into .agents/skills/related-party-identification/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "related-party-identification", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nigo81/nigo-skills --skill related-party-identification -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install nigo81/nigo-skills related-party-identification --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nigo81/nigo-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/related-party-identification .cursor/skills/related-party-identification && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "related-party-identification" agent skill from https://github.com/nigo81/nigo-skills/tree/main/related-party-identification into .cursor/skills/related-party-identification/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "related-party-identification", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/nigo81/nigo-skills.git --path related-party-identification--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add nigo81/nigo-skills --skill related-party-identification -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install nigo81/nigo-skills related-party-identification --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nigo81/nigo-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/related-party-identification .gemini/skills/related-party-identification && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "related-party-identification" agent skill from https://github.com/nigo81/nigo-skills/tree/main/related-party-identification into .gemini/skills/related-party-identification/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "related-party-identification", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install nigo81/nigo-skills related-party-identificationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add nigo81/nigo-skills --skill related-party-identification -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/nigo81/nigo-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/related-party-identification .github/skills/related-party-identification && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "related-party-identification" agent skill from https://github.com/nigo81/nigo-skills/tree/main/related-party-identification into .github/skills/related-party-identification/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "related-party-identification", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nigo81/nigo-skills --skill related-party-identification -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install nigo81/nigo-skills related-party-identification --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nigo81/nigo-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/related-party-identification .opencode/skills/related-party-identification && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "related-party-identification" agent skill from https://github.com/nigo81/nigo-skills/tree/main/related-party-identification into .opencode/skills/related-party-identification/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "related-party-identification", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
related-party-identification- GitHub stars
- 133
- Token cost
- ~1.7k tokens
- SKILL.md length
- 301 words
- Files
- 6 (incl. scripts, references)
- Skills in repo
- 13
- Repo updated
- First seen
- Licence
- MIT
At a glance
Cross-checks a client's own registry data against its customers' and suppliers' to surface undisclosed related-party relationships for an audit.
- Checking whether a client's customers or suppliers are undisclosed related parties
- SKILL.md covers 为什么做这个, 核心概念, 工作流（四步） and 输出格式（多 sheet Excel）, plus 5 more sections
- Runs Python scripts from its folder; calls python3
- Screening a batch of counterparties for shared addresses, phones or emails
What it does
Built from regulatory penalty cases where auditors missed obvious signals, such as matching phone number ranges, nearby addresses, a shared email domain, or a counterparty that is both customer and supplier in the same building, the skill turns those signals into a rule engine spanning eight dimensions: registry fingerprints, overlapping key personnel, equity look-through, counterparty profile anomalies, shared intangible assets, guarantee chains and historical relationship traces.
The workflow first runs an equity look-through to find subsidiaries at a 20% stake or above, downloads full registry data for the combined list of the audited unit, its subsidiaries, customers and suppliers, then runs the check engine pairwise across every company, not only against the audited unit, which can surface a hidden group among the counterparties themselves. Results come back as a multi-sheet Excel report split into hard matches and softer suspicious flags; the tool only surfaces evidence, leaving the actual related-party judgment and further procedures to the auditor.
When your agent uses it
- Checking whether a client's customers or suppliers are undisclosed related parties
- Screening a batch of counterparties for shared addresses, phones or emails
- Looking for a hidden corporate group behind a client's trading partners
Example prompts
- “Check these suppliers for hidden related-party ties to our client.”
- “Run the equity look-through on this parent company before the related-party check.”
- “Does this customer share a phone number or address with any supplier on our list?”
Requirements
- Python to run the discovery and check scripts
- Company registry data exports from the cicpa-company-query skill
What it can do on your machine
Read from SKILL.md and the folder at commit 6468211. 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:
python3
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
Hidden Related-Party Audit Check loads about 1.7k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 115 tokens; SKILL.md has 301 words of instructions outside code blocks.
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 nigo81/nigo-skills at commit 6468211, republished under its MIT licence (© nigo81). 301 words, ~1,719 tokens.
Download SKILL.mdSave it as
.claude/skills/related-party-identification/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- related-party-identification
- description
- 基于工商数据自动识别"隐形关联方"的审计核查工具。读取被审计单位及其客户、供应商的工商完整维度（52个Excel）， 自动比对地址/电话/邮箱/网址/法定代表人/董监高/股权穿透/客商异常画像/无形资产共用/担保链/历史关联痕迹等八大维度， 输出多sheet Excel核查报告（汇总判断sheet + 各维度证据sheet），揪出未披露的关联方关系。 当用户提到 关联方、关联方核查、关联方识别、隐形关联方、隐性关联方、未披露关联方、关联交易非关联化、 关联关系、客户供应商关联关系、客户是不是关联方、供应商有没有猫腻、股权穿透、实际控制人核查、 关联方尽调、审计关联方、related party、关联方核查底稿 时使用。 即使用户只说"查一下这几家公司之间有没有关联""帮我看下这批客户供应商的工商数据""这公司是不是空壳" "审计要核查关联方"也应触发。配合 cicpa-company-query skill 取数，规则集对齐证监会/财政部近年处罚案例。
- slug
- nigo-related-party-identification
- displayName
- 关联方识别核查工具
- version
- 1.0.0
- summary
- 基于工商数据自动识别"隐形关联方"的审计核查工具，比对地址/电话/股权穿透/担保链等八大维度，输出多 sheet Excel 核查报告。
- license
- MIT
关联方核查 / 隐形关联方识别
一句话：把被审计单位 + 客户 + 供应商的工商数据丢进来，自动揪出"应该披露但没披露"的关联方关系。
为什么做这个
证监会/财政部近年处罚了一大批会计师事务所，处罚决定书里反复出现同一类过错：
"审计底稿中已存在电话号段相邻、地址相近等明显异常，但未关注"（蓝山科技案） "对方邮箱域名与公司相同、既是客户又是供应商、同楼同座办公…未实施进一步程序"（天沃科技案） "相关客户时任监事及法定代表人为本公司员工…未识别为关联方"（卓朗科技案）
这些异常全部能用工商数据自动判定。这个 skill 就是把这些"监管认定的最低核查动作"固化成规则引擎，让审计人员不会再漏。规则集与处罚案例的对齐关系见 references/cases.md。
核心概念
两档输出（避免误报，又抓住实质）
关联方认定本质是"实质重于形式"，工具不替审计师下结论，而是分两档呈现证据：
| 档位 | 含义 | 典型命中 | 报告呈现 |
|---|---|---|---|
| 🔴 硬关联（high） | 工商数据直接证明关联，监管认定的强证据 | 同电话/同邮箱/同地址/同法人/股权穿透命中/客户表已标注关联方 | 必须查清 |
| 🟡 可疑红旗（medium/low） | 异常特征暗示关联，需进一步程序 | 成立时间短即大额交易、0参保、规模不匹配、人员同名、既客又供、历史关联痕迹 | 建议关注 |
八大核查维度
P0（监管反复处罚 + 工商数据现成，必做）：
1️⃣ 工商指纹重合 地址/电话/邮箱/网址/经纬度完全或高度相近
2️⃣ 关键人员重合 法定代表人/董监高/核心团队/最终受益人姓名跨公司撞名
3️⃣ 客商异常画像 成立即大客户、注册资本VS交易额不匹配、0参保、居民楼地址、经营范围不符
4️⃣ 已知关联方差集 客户/供应商表自带的"关联方名称"字段，与企业自报清单做差集
P1（监管点名，需穿透）：
5️⃣ 股权/控制穿透 多层股权、代持、实控人/最终受益人一致（默认穿透5层）
6️⃣ 历史关联痕迹 曾用名、曾任法人/股东、变更记录中的关联痕迹、非关联化
P2（实务有效，部分需配合银行/函证数据）：
7️⃣ 担保/资金链 互保、股权质押给对方、动产抵押关系
8️⃣ 无形资产/资源共用 商标/著作权/专利/微信公众号共有人、招聘办公地点重合每个维度的【识别原理 + 具体规则 + 红旗信号 + 监管出处】详见 references/rules.md。
工作流（四步）
第 1 步：取数（先股权穿透发现子公司，再批量下载）
⚠️ 必须先做股权穿透：造假常发生在子公司层面（如卓朗科技案，造假客户供应商挂在子公司"卓朗发展"名下，只查母公司看不出关联）。先把被审计单位的子公司纳入核查范围，才能准确识别。
1a. 股权穿透发现子公司（默认5层，持股>=20%）
SCOPE=~/.claude/skills/related-party-identification/scripts/discover_scope.py
python3 $SCOPE --target "被审计单位全称" --depth 5 --threshold 20 -o 核查名单.txt
# 输出 核查名单.txt：被审计单位 + 所有子公司/参控股企业（按股权链5层递归穿透）1b. 合并名单：把 核查名单.txt（穿透发现的子公司）+ 审计人员提供的客户/供应商，合并去重到同一文件。
1c. 批量下载工商数据
SCRIPT=~/.claude/skills/cicpa-company-query/scripts/cicpa_query.py
python3 $SCRIPT -n $(cat 核查名单.txt | tr '\n' ' ') --browser-export
# 输出 ZIP，解压后得到 完整维度导出_files/ 目录（含52个xlsx）threshold 用 20%（重大影响线） 而非 50%——监管按"实质重于形式"认定关联方，20% 以上参股公司也可能构成关联方，不能漏。企业名必须用工商注册全称。
子公司数量可能较多（一家集团几十上百家），若超出下载上限，优先保留：①target 直接控股的 ②持股比例高的 ③与客户/供应商有工商重合嫌疑的。
第 2 步：核查（调本 skill 引擎）
ENGINE=~/.claude/skills/related-party-identification/scripts/related_party_check.py
python3 $ENGINE \
--data-dir "完整维度导出_files/" \
--target "被审计单位全称" \
-o "关联方核查报告.xlsx"--data-dir：cicpa 完整导出解压后的_files目录--target：被审计单位全称（用于报告聚焦，标记主审计对象）--depth：股权穿透深度，默认 5--counterparties-file：可选，指定哪些是客户/哪些是供应商（否则引擎把 target 以外的都当交易对手）
引擎会读取 data-dir 里所有公司，做全图比对（不只 target vs 每个对手方，还包括对手方之间的互查——能发现"隐形集团"），跑八层规则，输出 Excel。
第 3 步：解读报告
报告是多 sheet Excel，结构见下方"输出格式"。重点看：
- 汇总 sheet：是否为关联方的判断 + 命中维度 + 风险等级
- 各维度证据 sheet：每条命中的具体字段值（地址、电话原文等）
第 4 步：审计师跟进
工具只负责"识别嫌疑"，不替审计师下结论。对每个 🔴 硬关联，审计师应：
- 实施进一步程序（函证、实地走访、资金流水核对）
- 询问管理层，要求披露
- 评估对审计意见的影响
输出格式（多 sheet Excel）
关联方核查报告.xlsx
├── 📋 汇总判断 ← 主表，每对公司一行：是否关联方/命中维度/风险等级/建议程序
├── 🔴 01_工商指纹重合 ← 同地址/同电话/同邮箱/同网址的具体记录
├── 🔴 02_关键人员重合 ← 法人/董监高/最终受益人撞名记录
├── 🟡 03_客商异常画像 ← 每个客户/供应商的异常特征清单（成立时间/规模/参保/经营范围）
├── 🔴 04_已知关联方差集 ← 客户/供应商表已标注关联方 vs 企业自报清单的差集
├── 🟡 05_股权控制穿透 ← 股权穿透路径、实控人/最终受益人重合
├── 🟡 06_历史关联痕迹 ← 曾用名、曾任法人/股东、变更记录痕迹
├── 🟡 07_担保资金链 ← 互保、股权质押、动产抵押关系
├── 🟡 08_无形资产共用 ← 商标/著作权/专利/公众号共有人
└── 📊 输入数据概览 ← 本次核查的公司清单 + 数据完整性汇总判断 sheet 的列结构：
| 公司A | 公司B | 关系类型 | 是否关联方 | 风险等级 | 命中维度 | 关键证据 | 建议审计程序 | 监管出处 |
|---|---|---|---|---|---|---|---|---|
| XX公司 | YY公司 | 客户 | 🔴是 | high | 工商指纹|人员重合 | 同电话138xxxx | 同法人张三 | 函证+实地走访 | 卓朗科技案 |
| XX公司 | ZZ公司 | 供应商 | 🟡可疑 | medium | 客商画像 | 成立6月即大额|0参保 | 资金流水核对 | 专网通信案 |
与 cicpa-company-query 的协作
本 skill 不直接调工商 API，而是消费 cicpa-company-query 导出的 _files 目录：
| 本 skill 需要 | cicpa 提供的文件 | 用途 |
|---|---|---|
| 地址/电话/邮箱/网址/法人/成立日期/参保/曾用名/经营范围 | 基础工商信息.xlsx | 指纹重合 + 客商画像（一站式） |
| 股东、出资比例 | 股东信息.xlsx / 最新公示股东.xlsx | 股权穿透 |
| 实控人、最终受益人 | 实际控制人.xlsx / 最终受益人.xlsx | 控制关系重合 |
| 董监高、核心团队 | 核心团队.xlsx / 主要人员（高管）.xlsx | 人员重合 |
| 客户/供应商 + 自带关联方标注 | 客户.xlsx / 供应商.xlsx | 客商画像 + 已知关联方差集 |
| 对外投资、参控股、分支机构 | 对外投资（新）.xlsx / 参控股企业.xlsx / 分支机构.xlsx | 投资关系网络 |
| 担保、质押、抵押 | 股权质押.xlsx / 动产抵押.xlsx / 对外担保.xlsx | 担保链 |
| 商标、著作权、专利、公众号 | 商标.xlsx / 软件著作权.xlsx / 专利信息.xlsx / 微信公众号.xlsx | 无形资产共用 |
| 变更历史 | 变更记录.xlsx / 法定代表人变更.xlsx | 历史关联痕迹 |
| 补充地址/电话/税号 | 发票信息.xlsx | 交叉验证指纹 |
完整字段映射见 references/dimensions.md。
八层规则速览（详见 references/rules.md）
维度1：工商指纹重合（最强信号）
- 注册地址完全相同 / 高度相似（去掉省市邮编后比对）
- 联系电话相同（手机去前缀，座机去区号）
- 邮箱相同或同域名（@后的部分）
- 官网网址相同或同域名
- 监管出处：蓝山科技、天沃科技、卓朗科技、爱康科技案
维度2：关键人员重合
- 法定代表人姓名相同（自然人，排除"同名高频姓"误报）
- 董监高/核心团队姓名跨公司重合
- 最终受益人/实际控制人姓名相同
- 监管出处：卓朗科技（对方监事为本公司员工）、爱康科技（法人同一人）
维度3：客商异常画像
- 客户/供应商成立日期距今过短即发生大额交易（<12个月）
- 注册资本远小于披露交易额（如注册资本10万，年交易1000万）
- 参保人数为 0 或 <5（空壳特征）
- 注册地址为居民楼/集中注册地
- 经营范围与交易品类不符
- 既是客户又是供应商（双向交易）
- 监管出处：爱康科技、专网通信系列案、天沃科技
维度4：已知关联方差集 ⭐
客户.xlsx/供应商.xlsx自带关联方名称/关联方ID/关联理由字段- 把数据库已标注的关联方，与企业自报披露的关联方清单做差集 → 直接揪出未披露关联方
- 监管出处：洛娃集团案（公开客户中5家是关联方却未识别）
维度5：股权/控制穿透
- 向上穿透股权（默认5层），看对手方是否在 target 的股权链上，或 target 在对手方股权链上
- 实际控制人 / 最终受益人姓名跨公司一致
- 共同股东（A和B有同一个股东）
- 代持痕迹（变更记录里股权频繁变动、法人变更）
- 监管出处：华道生物（法代曾代实控人持股）、多案共性
维度6：历史关联痕迹
- 曾用名命中（
基础工商信息.曾用名） - 曾任法定代表人/股东（变更记录、法人变更记录里出现过同一人）
- 曾用地址（变更记录里的历史地址撞对手方现地址）
- 非关联化嫌疑（曾是关联方，后通过股权转让"洗白"）
- 监管出处：ST新亿、扬子新材案
维度7：担保/资金链
- 互保关系（A质押给B，B也质押给A）
- 股权质押的质权人/出质人是对手方
- 动产抵押的抵押权人/债务人对手方
- 监管出处：康得新、延安必康案
维度8：无形资产/资源共用
- 商标/软件著作权/专利的共有人或代理机构相同
- 微信公众号主体关联
- 招聘信息的办公地点与对手方重合
- 监管出处：实务有效，工商可部分挖
边界与注意事项
- 工具只识别"嫌疑"，不下"是关联方"的最终结论：最终认定需审计师结合准则（CAS 36 / CSA 1323）判断。报告里"是否关联方"列是基于规则的初判，供审计师参考。
- 企业名称必须用工商全称：否则 cicpa 导出会匹配 0 家。
- 数据时效：工商数据有滞后（变更、注销可能未及时更新），核查结果需结合函证、走访等程序验证。
- 已注销公司查不到：部分造假空壳公司事后注销，cicpa 可能无数据。这种情况报告里会标注"数据缺失"。
- 亲属关系（第9维度）受限于公开数据：工商数据不直接提供亲属关系，只能通过"同名+同姓+同地址"间接推断，需谨慎。
何时不用
- 只需要函证地址核查（用 address-verification skill）
- 只需要查单家公司工商信息（用 cicpa-company-query 的 --detail）
- 需要会计准则层面的关联方认定咨询（用 chen-yiwei-perspective skill）
参考
references/rules.md—— 八层规则详解（识别原理、具体规则、阈值、红旗信号、监管出处）references/cases.md—— 处罚案例库（监管认定的过错 → 对应核查规则）references/dimensions.md—— cicpa 52维度字段与本 skill 规则的完整映射scripts/related_party_check.py—— 核查引擎主脚本
作者：nigo 微信公众号：逆行的狗
© nigo81, MIT. 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 5 other files (scripts, references) in related-party-identification of nigo81/nigo-skills.
- SKILL.md
- references/cases.md
- references/dimensions.md
- references/rules.md
- scripts/discover_scope.py
- scripts/related_party_check.py
Open the folder on GitHubat commit 6468211
Compare with similar skills
Hidden Related-Party Audit Check 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Hidden Related-Party Audit Check this skillnigo81/nigo-skills | 133 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Three-Statement Model Builderginlix-ai/LangAlpha | 1.8k | — | ~5.4k | Automated safety check: Pass | Apache-2.0 | |
| Anti Gambling Tradermars-tw/anti-gambling-trader-tw | 907 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Dcf ModelWind-Alice/AliceMarket | 134 | 2 repos | ~12k | Automated safety check: Pass | None | |
| Dcf ModelLuciole-Studio/Misaka-Agent | 171 | 2 repos | ~12k | Automated safety check: Pass | Apache-2.0 | |
| PipesHub Excel Spreadsheet Builderpipeshub-ai/pipeshub-ai | 3.8k | — | ~1.8k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Anti Gambling Trader
mars-tw/anti-gambling-trader-tw
分析台股 / 台股ETF / 台指期選擇權 / 美股 / 加密貨幣 / 外匯的交易紀錄 (CSV / JSON / Excel),用統計學判斷使用者的獲利是「可重複的優勢」還是 「運氣 + 倖存者偏差(賭博)」,不適合長期投資會明確勸退。內建反詐工具: 掃描群組對話的詐騙話術(scan-text)、檢驗老師宣稱的績效(guru-check)、…
Dcf Model
Wind-Alice/AliceMarket
Real DCF (Discounted Cash Flow) model creation for equity valuation.
Dcf Model
Luciole-Studio/Misaka-Agent
Build discounted cash flow valuation workbooks in Excel. An agent skill from Luciole-Studio/Misaka-Agent.
PipesHub Excel Spreadsheet Builder
pipeshub-ai/pipeshub-ai
Creates and edits .xlsx workbooks with real Excel formulas rather than hardcoded computed values, defaulting to exceljs in TypeScript with a static formula-safety check.
- Official
Instrument Data To Allotrope
aws-samples/amazon-bedrock-agents-healthcare-lifesciences
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV.
More from nigo81/nigo-skills
All 13 skills in this repoCICPA Company Registration Query
nigo81/nigo-skills
Looks up Chinese company registration data in the CICPA industry knowledge base, from a quick search to a full 61-dimension export, subsidiary discovery and Excel output.
Audit Report Checker
nigo81/nigo-skills
Checks audit reports (financial statements and notes) for cross-reference, summation and text errors, with arithmetic done by script and results exported to Excel and Markdown.
Bank Statement Merge and Reconciliation
nigo81/nigo-skills
Merges bank statements from several banks and formats into one standard Excel layout, then reconciles them against the general ledger with a layered matching engine.
Accounting Standards Advisor (Chen Yiwei)
nigo81/nigo-skills
A Chinese-language persona that answers accounting-standards and audit questions in the style of forum moderator Chen Yiwei, checking standards text before it replies.
Audit Swimlane Flowchart Generator
nigo81/nigo-skills
Chinese-language tool that turns a business process description into a swimlane flowchart for internal control and audit work, exported as .drawio, PNG, SVG or VSDX.
OpenCode Session Visualizer
nigo81/nigo-skills
Exports an OpenCode session from its local database into a single self-contained HTML page styled like the official share view, with folding and editing controls.
Related
Works with
Categories
Questions about Hidden Related-Party Audit Check
What does Hidden Related-Party Audit Check do?
Cross-checks a client's own registry data against its customers' and suppliers' to surface undisclosed related-party relationships for an audit. Built from regulatory penalty cases where auditors missed obvious signals, such as matching phone number ranges, nearby addresses, a shared email domain, or a counterparty that is both customer and supplier in the same building, the skill turns those signals into a rule engine spanning eight dimensions: registry fingerprints, overlapping key personnel, equity look-through, counterparty profile anomalies, shared intangible assets, guarantee chains and historical relationship traces.
When should I use Hidden Related-Party Audit Check?
Hidden Related-Party Audit Check fits situations like: checking whether a client's customers or suppliers are undisclosed related parties; screening a batch of counterparties for shared addresses, phones or emails; looking for a hidden corporate group behind a client's trading partners.
How do I install Hidden Related-Party Audit Check in Claude Code?
Run `npx skills add nigo81/nigo-skills --skill related-party-identification -a claude-code`. Or copy the skill folder (related-party-identification in nigo81/nigo-skills) into .claude/skills/related-party-identification in your project. Claude Code loads it when a task matches its description.
How do I install Hidden Related-Party Audit Check in Codex?
Run `npx skills add nigo81/nigo-skills --skill related-party-identification -a codex`. Or copy the skill folder (related-party-identification in nigo81/nigo-skills) into .agents/skills/related-party-identification in your project. Codex loads it when a task matches its description.
Can I use Hidden Related-Party Audit Check 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 nigo81/nigo-skills --skill related-party-identification -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/related-party-identification, .gemini/skills/related-party-identification, .github/skills/related-party-identification and .opencode/skills/related-party-identification in your project.
What does Hidden Related-Party Audit Check need to run?
Going by SKILL.md and its folder, Hidden Related-Party Audit Check needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python to run the discovery and check scripts; Company registry data exports from the cicpa-company-query skill.
Does Hidden Related-Party Audit Check 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 Hidden Related-Party Audit Check 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 Hidden Related-Party Audit Check use?
Hidden Related-Party Audit Check is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Hidden Related-Party Audit Check use?
About 1.7k tokens (SKILL.md is roughly 6.9k 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 8.5k tokens, read only when the agent opens those files.
What are the alternatives to Hidden Related-Party Audit Check?
Skills that share tags, products or a category with Hidden Related-Party Audit Check: Three-Statement Model Builder (ginlix-ai/LangAlpha, 1.8k stars), Anti Gambling Trader (mars-tw/anti-gambling-trader-tw, 907 stars), Dcf Model (Wind-Alice/AliceMarket, 134 stars) and Dcf Model (Luciole-Studio/Misaka-Agent, 171 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Hidden Related-Party Audit Check?
nigo81 (a GitHub user) maintains it in nigo81/nigo-skills, which has 133 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on August 23, 2026.
Source: nigo81/nigo-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.