Agent skill

Reading Deduction Cert

by kazukinagata in kazukinagata/shinkoku

控除証明書(生命保険料・地震保険料等)の画像を読み取り構造化データを返す. An agent skill from kazukinagata/shinkoku.

MITAuto-check passedDocuments & Office

Install Reading Deduction Cert

skills CLI
$ npx skills add kazukinagata/shinkoku --skill reading-deduction-cert -a claude-code

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

GitHub CLI
$ gh skill install kazukinagata/shinkoku reading-deduction-cert --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/kazukinagata/shinkoku.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/reading-deduction-cert .claude/skills/reading-deduction-cert && 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
reading-deduction-cert
GitHub stars
365
Token cost
~608 tokens
SKILL.md length
104 words
Files
2
Skills in repo
24
Repo updated
First seen
Licence
MIT

At a glance

控除証明書(生命保険料・地震保険料等)の画像を読み取り構造化データを返す. An agent skill from kazukinagata/shinkoku.

  • Works in 3 steps: shinkoku pdf extract-text --file-path… → 抽出テキストに必要な情報(保険料額・証明額等)が含まれていれば、テキストから構造化… → テキストが不十分(スキャン PDF 等)の場合は shinkoku pdf…
  • Documents & Office work in your project
  • SKILL.md covers PDF ファイルの場合, 画像読み取り方法, 基本ルール and 対象書類, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Reading Deduction Cert is an agent skill from kazukinagata/shinkoku. 控除証明書(生命保険料・地震保険料等)の画像を読み取り構造化データを返す。 他のスキルから呼び出されるほか、直接ユーザーが呼び出すことも可能。

Its SKILL.md is about 610 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `README.md`).

It sits in Documents & Office. The repository describes itself as: 確定申告自動化 AI エージェントプラグイン — 帳簿管理から e-Tax 入力代行まで. The licence is MIT.

When your agent uses it

  • Documents & Office work in your project

Example prompts

  • “/reading-deduction-cert”

Workflow steps

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

  1. shinkoku pdf extract-text --file-path を実行する
  2. 抽出テキストに必要な情報(保険料額・証明額等)が含まれていれば、テキストから構造化データを生成する
  3. テキストが不十分(スキャン PDF 等)の場合は shinkoku pdf to-image --file-path --output-dir で PNG に変換し、以下の画像読み取りフローに進む

What it can do on your machine

Read from SKILL.md and the folder at commit 607574d. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

    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

Reading Deduction Cert loads about 608 tokens when it runs. Until then it costs about 24 tokens; SKILL.md has 104 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~24
When it runs · the whole SKILL.md, loaded when a task matches
~608

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from kazukinagata/shinkoku at commit 607574d, republished under its MIT licence (© kazukinagata). 104 words, ~608 tokens.

Download SKILL.mdSave it as .claude/skills/reading-deduction-cert/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
reading-deduction-cert
description
控除証明書(生命保険料・地震保険料等)の画像を読み取り構造化データを返す。 他のスキルから呼び出されるほか、直接ユーザーが呼び出すことも可能。

控除証明書 画像読み取り

控除証明書(生命保険料控除証明書、地震保険料控除証明書、社会保険料控除証明書等)の画像を読み取り、構造化データとして返すスキル。

PDF ファイルの場合

ファイルが PDF(.pdf)の場合、画像 OCR の前にテキスト抽出を試みる。

  1. shinkoku pdf extract-text --file-path <path> を実行する
  2. 抽出テキストに必要な情報(保険料額・証明額等)が含まれていれば、テキストから構造化データを生成する
  3. テキストが不十分(スキャン PDF 等)の場合は shinkoku pdf to-image --file-path <path> --output-dir <dir> で PNG に変換し、以下の画像読み取りフローに進む

画像読み取り方法

推奨: デュアル検証(並列2コンテキスト)

精度を高めるため、同じ画像を2つの独立したコンテキストで並列に読み取り、結果を照合する。

  1. 2つの独立した読み取りを実行する: サブエージェントが使える環境では、2つのサブエージェントを並列で起動し、それぞれ独立に画像を読み取る。 各サブエージェントには以下の「基本ルール」と「出力フォーマット」をプロンプトとして渡し、画像ファイルパスを指定する。

  2. 結果照合: 両方の読み取り結果から主要フィールド(金額等)を比較する。

  3. 一致の場合: そのまま採用。「2つの独立した読み取りで結果が一致しました」と報告する。

  4. 不一致の場合: ユーザーに元画像パスと両方の結果を提示し、正しい方を選択してもらう:

    • 差異のあるフィールドを明示する
    • A を採用 / B を採用 / 手動入力 の3択を提示する
フォールバック(サブエージェント非対応の場合)

サブエージェントが利用できない環境では、以下の手順で読み取る:

  1. 画像ファイルを直接 Read ツールで読み取る
  2. 以下の「基本ルール」と「出力フォーマット」に従ってデータを抽出する
  3. 抽出結果をユーザーに提示し、必ず目視確認を依頼する

⚠ デュアル検証が利用できないため、必ずユーザーに目視確認を依頼してください。

基本ルール

  • 画像ファイルは Read ツールで読み取る(Claude Vision が自動的に画像を認識する)
  • 金額は必ず int(円単位の整数)で返す。カンマや「円」は除去する
  • 日付は YYYY-MM-DD 形式で返す
  • 和暦は西暦に変換する(令和7年 → 2025、令和6年 → 2024、平成31年 → 2019)
  • 読み取れないフィールドは UNKNOWN(文字列)または 0(金額)とする

対象書類

  • 生命保険料控除証明書
  • 地震保険料控除証明書
  • 社会保険料(国民年金保険料)控除証明書
  • 小規模企業共済等掛金払込証明書(iDeCo含む)

出力フォーマット

JSON オブジェクトとして返す。金額は必ず int(円単位の整数)とする。

生命保険料控除証明書
json
{
  "certificate_type": "life_insurance",
  "policy_type": "新制度 or 旧制度",
  "category": "一般 or 介護医療 or 個人年金",
  "company_name": "保険会社名",
  "policy_number": "証券番号",
  "annual_premium": 120000,
  "dividend": 0
}
地震保険料控除証明書
json
{
  "certificate_type": "earthquake_insurance",
  "company_name": "保険会社名",
  "policy_number": "証券番号",
  "annual_premium": 50000,
  "is_old_long_term": false
}
社会保険料控除証明書
json
{
  "certificate_type": "social_insurance",
  "insurance_type": "national_pension",
  "annual_premium": 200000,
  "period": "対象期間"
}
小規模企業共済等掛金払込証明書
json
{
  "certificate_type": "small_business_mutual_aid",
  "sub_type": "ideco or small_business or disability",
  "annual_contribution": 276000
}

抽出のポイント

  • 書類の種別(生命保険料/地震保険料/社会保険料/小規模企業共済等)を最初に判定する
  • 生命保険料控除は新旧制度の区別と、3区分(一般/介護医療/個人年金)の分類を確認する
  • 地震保険料控除は旧長期損害保険かどうかの区別を確認する
  • 金額は「証明額」「申告額」が異なる場合、「申告額」を使用する
  • 保険会社名・証券番号は確認用に抽出する

© kazukinagata, 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 1 other file in skills/reading-deduction-cert of kazukinagata/shinkoku.

  • SKILL.md
  • README.md

Open the folder on GitHubat commit 607574d

Compare with similar skills

Reading Deduction Cert 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.

Reading Deduction Cert compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Reading Deduction Cert this skillkazukinagata/shinkoku365—~608Automated safety check: PassMIT
Markdown Article FormatterJimLiu/baoyu-skills27k6 repos~3.5kAutomated safety check: PassMIT
MarkitdownImCa0/just-laws78114 repos~3.2kAutomated safety check: NotesMIT
Obsidian MarkdownAtmosphere/atmosphere3.8k20 repos~1.3kAutomated safety check: PassApache-2.0
DOCXrvdbreemen/OTGW-firmware20733 repos~4.3kAutomated safety check: PassProprietary
Word Document Reader and WriterHKUDS/DeepTutor41k—~2.5kAutomated safety check: PassApache-2.0

Similar skills

  • Markdown Article Formatter

    JimLiu/baoyu-skills

    Reformats plain text or Markdown articles with frontmatter, a title, a summary, headings, bold, lists and code blocks, and saves a separate formatted copy.

    27k GitHub starsUsed in 6 repos~3.5k tokens
    Documents & OfficeAuto-check passed
  • Markitdown

    ImCa0/just-laws

    Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.

    781 GitHub starsUsed in 14 repos~3.2k tokens
    Documents & OfficeAuto-check: notes
  • Obsidian Markdown

    Atmosphere/atmosphere

    Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax.

    3.8k GitHub starsUsed in 20 repos~1.3k tokens
    Documents & OfficeAuto-check passed
  • DOCX

    rvdbreemen/OTGW-firmware

    A skill your agent uses whenever the user wants to create, read, edit, or manipulate Word documents (.docx files).

    207 GitHub starsUsed in 33 repos~4.3k tokens
    Documents & OfficeAuto-check passed
  • Reads, creates and edits Word .docx files with python-docx, and drops to raw OOXML for tracked changes, comments and byte-exact edits.

    41k GitHub stars~2.5k tokensUpdated 2 days ago
    Documents & OfficeAuto-check passed
  • Crossposting

    wasp-lang/wasp

    Crosspost Wasp blog articles (MDX) to DEV.to and Medium. An agent skill from wasp-lang/wasp.

    19k GitHub stars~1.1k tokensUpdated yesterday
    Documents & OfficeAuto-check passed

More from kazukinagata/shinkoku

All 24 skills in this repo
  • Consumption Tax

    kazukinagata/shinkoku

    This skill should be used when the user needs to calculate consumption tax (消費税) or determine their tax method (2割特例, 簡易課税, or 本則課税).

    365 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Furusato

    kazukinagata/shinkoku

    This skill manages furusato nozei (hometown tax) donations. An agent skill from kazukinagata/shinkoku.

    365 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Incorporation

    kazukinagata/shinkoku

    法人成り(個人事業主から法人への移行)に関する相談。税額比較シミュレーション、 法人形態の選択、設立手続き、役員報酬戦略、社会保険の比較を支援する。

    365 GitHub stars~687 tokensUpdated 1 mo ago
    Auto-check passed
  • Invoice System

    kazukinagata/shinkoku

    This skill should be used when the user asks about the invoice system (インボイス制度), qualified invoices (適格請求書), registration numbers (登録番号), input tax credits (仕入税額控除), the 20% special measure (2割特例)…

    365 GitHub stars~778 tokensUpdated 1 mo ago
    Auto-check passed
  • Journal

    kazukinagata/shinkoku

    This skill should be used when the user wants to record bookkeeping entries (仕訳), import transaction data from CSV files, receipts, or invoices, or manage their general ledger.

    365 GitHub stars~2.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Settlement

    kazukinagata/shinkoku

    This skill should be used when the user needs to perform year-end closing adjustments (決算整理), review financial statements (決算書), compute depreciation, or review their trial balance.

    365 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Reading Deduction Cert

What does Reading Deduction Cert do?

控除証明書(生命保険料・地震保険料等)の画像を読み取り構造化データを返す. An agent skill from kazukinagata/shinkoku. Reading Deduction Cert is an agent skill from kazukinagata/shinkoku.

When should I use Reading Deduction Cert?

Reading Deduction Cert fits situations like: documents & Office work in your project.

How do I install Reading Deduction Cert in Claude Code?

Run `npx skills add kazukinagata/shinkoku --skill reading-deduction-cert -a claude-code`. Or copy the skill folder (skills/reading-deduction-cert in kazukinagata/shinkoku) into .claude/skills/reading-deduction-cert in your project. Claude Code loads it when a task matches its description.

How do I install Reading Deduction Cert in Codex?

Run `npx skills add kazukinagata/shinkoku --skill reading-deduction-cert -a codex`. Or copy the skill folder (skills/reading-deduction-cert in kazukinagata/shinkoku) into .agents/skills/reading-deduction-cert in your project. Codex loads it when a task matches its description.

Can I use Reading Deduction Cert 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 kazukinagata/shinkoku --skill reading-deduction-cert -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/reading-deduction-cert, .gemini/skills/reading-deduction-cert, .github/skills/reading-deduction-cert and .opencode/skills/reading-deduction-cert in your project.

What does Reading Deduction Cert need to run?

SKILL.md names no scripts, command-line tools or credentials: Reading Deduction Cert is instructions for the agent only.

Does Reading Deduction Cert 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 Reading Deduction Cert 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. Review the folder before installing.

What licence does Reading Deduction Cert use?

Reading Deduction Cert is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Reading Deduction Cert use?

About 608 tokens (SKILL.md is roughly 2.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Reading Deduction Cert?

Skills that share tags, products or a category with Reading Deduction Cert: Markdown Article Formatter (JimLiu/baoyu-skills, 27k stars), Markitdown (ImCa0/just-laws, 781 stars), Obsidian Markdown (Atmosphere/atmosphere, 3.8k stars) and DOCX (rvdbreemen/OTGW-firmware, 207 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Reading Deduction Cert?

kazukinagata (a GitHub user) maintains it in kazukinagata/shinkoku, which has 365 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on September 9, 2026.

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