How this skill is triggered — by the user, by Claude, or both
Slash command
/bantou:tax-classifierThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Classify Japanese business transactions into standard accounting categories
Classify Japanese business transactions into standard accounting categories (kanjou-kamoku / 勘定科目) using a 3-stage pipeline that minimizes API costs and maximizes accuracy.
Invoke this skill whenever the user provides a transaction description (e.g. "スタバ 渋谷店 ¥580") and needs:
Before any classification attempt, run check_exclusion to filter out
non-classifiable items. The standard rules exclude:
If an item is excluded, return the exclusion reason without proceeding.
Query recall_memory first. If the exact vendor or pattern has been
corrected before, use the memorized classification immediately.
If no memory hit, match against the 14-category keyword dictionary:
| Category | Examples |
|---|---|
| 会議費 | cafe, meeting room |
| 交際費 | dinner with client, gift |
| 旅費交通費 | train, taxi, hotel |
| 通信費 | phone, internet, postage |
| 消耗品費 | office supplies, toner |
| 地代家賃 | rent, parking |
| 水道光熱費 | electricity, gas, water |
| 支払手数料 | bank fee, service charge |
| 広告宣伝費 | ads, marketing |
| 外注費 | subcontractor, freelancer |
| 福利厚生費 | employee meal, health check |
| 保険料 | insurance premium |
| 租税公課 | stamp duty, property tax |
| 雑費 | miscellaneous (last resort) |
When keyword matching fails or confidence is below threshold, call
classify_transaction which uses Claude to analyze the description
with full context from the firm's CLAUDE.md configuration.
Always assign a tax treatment. Be careful with the rates:
When uncertain between 10% and 8%, flag as "confirmation needed" rather than guessing. A wrong tax rate causes real compliance risk.
classify_transaction — full AI classificationcheck_exclusion — Stage 0 exclusion filterrecall_memory — check correction historynpx claudepluginhub michielinksee/bantou --plugin bantouGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.