用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/CleanExpo/ATO --skill audit-risk-benchmarking命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
基于 SOC 职业分类
| name | audit-risk-benchmarking |
| description | Compare entity financial ratios against ATO small business benchmarks to assess audit probability |
Compares a taxpayer's financial ratios (expense/income, labour costs, rent, motor vehicle) against ATO-published small business benchmarks for their ANZSIC industry code. Generates a risk profile without recommending behaviour change.
ATO benchmarks are DESCRIPTIVE, not NORMATIVE. Being outside a benchmark is NOT illegal. This skill assesses probability, never recommends adjusting legitimate figures to match benchmarks.
| Ratio | Calculation | Source |
|---|---|---|
| Cost of sales | Cost of sales / Total income | ATO Small Business Benchmarks |
| Total expenses | Total expenses / Total income | ATO Small Business Benchmarks |
| Labour costs | Wages + super / Total income | ATO Small Business Benchmarks |
| Rent | Rent expense / Total income | ATO Small Business Benchmarks |
| Motor vehicle | Motor vehicle / Total income | ATO Small Business Benchmarks |
lib/analysis/audit-risk-engine.tsassessAuditRisk(tenantId, financialYear, options)AuditRiskAssessment — includes risk factors, benchmark comparisons, and recommendationsaudit_risk_benchmarks table stores cached benchmark data per industry code and FYato.gov.au/Business/Small-business-benchmarksRoute complex requests to the right specialist agent or chain of agents. This skill acts as the central brain of an agent swarm — it analyses what the user needs, determines which specialist domain(s) are required, and coordinates parallel or sequential agent execution. Use this skill when a request spans multiple domains (e.g., "research competitors and create a pitch deck"), when you need to decide which specialist should handle an ambiguous request, or when a task requires a multi-step pipeline across different skills. Triggers on: multi-step requests, cross-domain tasks, "coordinate", "plan this out", "I need help with multiple things", or any complex request that touches more than one specialist area. Also triggers when the user seems unsure which tool or approach to use.
>-
>-