jp-consulting-skills

jp-consulting-skills is a skill for Claude Code, Codex from Lilaaa-05/awesome-claude-skills. It costs 162 tokens per session (12,770 once invoked), scanned A, original, MIT.

A Japanese-only method for creating consulting reports and presentation materials. It structures business questions, tests hypotheses, analyzes evidence, supports several consulting-firm formats, and includes web-search integration.

In plain words
What is it for?
Use it for Japanese-language work on market entry, mergers and acquisitions, growth, pricing, technology or AI adoption, cloud migration, cybersecurity, ESG, and other listed case types.
Why use it?
It helps turn an unclear business challenge into a staged analysis and an organized Japanese deliverable. Information is gathered gradually, so the user does not need to provide everything at once.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for Japanese-language work on market entry, mergers and acquisitions, growth, pricing, technology or AI adoption, cloud migration, cybersecurity, ESG, and other listed case types.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lilaaa-05/awesome-claude-skills/jp-consulting
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Lilaaa-05/awesome-claude-skills --skill jp-consulting
Clone the repo
git clone --depth 1 https://github.com/Lilaaa-05/awesome-claude-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for jp-consulting-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/lilaaa-05/awesome-claude-skills/jp-consulting/github.svg)](https://agentmods.dev/skills/lilaaa-05/awesome-claude-skills/jp-consulting)
Your own site
<a href="https://agentmods.dev/skills/lilaaa-05/awesome-claude-skills/jp-consulting"><img src="https://agentmods.dev/badge/skills/lilaaa-05/awesome-claude-skills/jp-consulting/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for jp-consulting-skills

Your own site · 80×15
<a href="https://agentmods.dev/skills/lilaaa-05/awesome-claude-skills/jp-consulting"><img src="https://agentmods.dev/badge/skills/lilaaa-05/awesome-claude-skills/jp-consulting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 162 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 12,770 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00162 $0.12770
Opus 5 $0.00081 $0.06385
Sonnet 5 $0.00032 $0.02554
Haiku 4.5 $0.00016 $0.01277

Measured 11d ago against content hash 2d91a8fd3505, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

jp-consulting-skills scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

consulting-skills/jp-consulting/SKILL.md · 1,225 lines

How it starts

The opening of the file, as written. The whole thing — 1,225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

コンサルティングアウトプット生成スキル(さよならコンサル!)

設計思想: 段階的構築(Incremental Build) × スライド指向(Slide-First Approach) 基本理念: 戦略・総合・テクノロジーコンサルティングの品質基準を実現 主要機能:

  • イシュー駆動型の課題設定
  • 仮説検証型フレームワーク分析
  • データに基づくスライド構成
  • 複数企業フォーマット対応
  • 進捗可視化スライド構成
  • より豊富な分析コンテンツ

📌 スキルの基本方針

対話の進め方

本スキルでは、ユーザーとの対話を通じて段階的に情報を収集します。

初回の対応:

  • ユーザーが取り組みたい課題を簡潔に尋ねる
  • 企業フォーマットの希望を確認
  • 一度に多くの情報を求めない
  • 過度に詳細なヒアリングは避ける

作業開始のタイミング:

  • 課題の概要が把握できた時点
  • 企業フォーマットが確定した時点
  • または、ユーザーから作業開始の意思表示があった時点

情報が不足している場合:

  • 最も重要な1-2点のみ追加で確認
  • 詳細は作業を進めながら段階的に確認

🏢 企業フォーマット選択

本スキルは複数のコンサルティングフォーマットに対応しています:

利用可能なフォーマット

  1. McKinsey
  2. BCG
  3. Bain
  4. Deloitte
  5. EY
  6. PwC
  7. Accenture
  8. Abeam (アビームコンサルティング)
  9. NRI (野村総合研究所)
  10. 標準 (汎用フォーマット)

📖 各フォーマットの詳細: FIRM_FORMATS.md を参照

フォーマット確認

タイミング: フェーズ1開始前(ユーザーが指定しない場合)

確認方法:

ご希望の資料フォーマットはありますか?
(McKinsey/BCG/Bain/Deloitte/EY/PwC/Accenture/Abeam/NRI/標準/指定なし)

フォーマット適用:

  • スライド構成の設計
  • レイアウトスタイル
  • データ可視化の方法
  • メッセージの表現

: フォーマットを指定しない場合は標準フォーマットを使用します


🏗️ 設計思想の背景

特徴:

  • 全体構成を先に固めてから、各スライドの詳細に入る
  • 各スライドは独立して作成可能(モジュール設計)
  • 中断・再開が容易な設計
  • 進捗状況の可視化

コンテキスト効率化:

  • 必要な情報のみを順次読み込み
  • 作業完了後は不要な情報を保持しない
  • スライド単位での区切りにより、長尺資料でも対応可能

進捗管理:

  • ✅ 作成済みスライドの明示
  • 📝 作成中スライドの表示
  • ⬜ 未作成スライドの表示
  • 進捗率の自動計算

📋 作業フローの全体像

本スキルは4つのフェーズで資料を完成させます:

Phase 0: 企業フォーマット選択 (所要時間: 2-3分)

  • 利用可能なフォーマットの提示
  • ユーザーの選択確認
  • 選択フォーマットの特性理解

Phase 1: 問題設定 (所要時間: 20-30分)

  • イシューの明確化と構造化
  • 検証すべき仮説の設定
  • フレームワークの選定
  • より深い分析視点の追加(EYのNexus思考など参考)

Phase 2: 資料構成の設計 (所要時間: 15-20分)

  • ストーリーラインの構築
  • 作成流れファイルの作成(作成流れ.md形式)
  • 各スライドのデータ要件定義
  • 進捗ステータスの初期化(全て⬜未作成)

Phase 3: スライド作成 (所要時間: 40-80分)

  • 1枚ずつデータ収集とスライド生成
  • 完成したスライドに✅マーク付与
  • 各スライド完成後、品質確認
  • 進捗率の更新
  • ユーザー確認を得てから次へ進行

Phase 4: 品質確認 (所要時間: 10-15分)

  • 全体の整合性チェック
  • 品質基準との照合
  • 最終調整

Read the full file on GitHub · 1,225 lines

Files

What ships with it

10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 1,225 lines · 162 tokens per session scan A 2d91a8fd3505

Subscribe to this mod's changes

jp-consulting-skills is a skill published in the GitHub repository Lilaaa-05/awesome-claude-skills (1 stars, last pushed 7mo ago), licensed MIT. It adds 162 tokens to every session and 12,770 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

data-analysis

Answer data questions from quick metric lookups to full investigations and stakeholder-ready reports.

datagallery-ai/dataagent · 19 tokens

knowledge-absorber

A tool that deeply examines links, documents, code, or images and turns them into teaching notes and knowledge posters. It supports formats such as PDF, Word, Markdown, source code, and images, and can save the results to a knowledge base.

wwwzhouhui/skills_collection · 171 tokens

ascend-migration-analysis

A feasibility analysis for moving a PyTorch project from CUDA/GPU hardware to Ascend NPU hardware. It scans the code for hardware-specific dependencies and reviews device code, attention mechanisms, custom operations, distributed communication, precision, third-party packages, and compilation.

ascend-ai-coding/awesome-ascend-skills · 137 tokens

swot-analysis

A structured way to assess a decision by listing internal strengths and weaknesses, then external opportunities and threats. SWOT stands for Strengths, Weaknesses, Opportunities, and Threats.

konglong87/methodology-skills · 92 tokens

first-principles

Use when facing complex problems requiring innovative solutions, when conventional approaches fail, when breaking down assumptions, or when user asks to 'think from first principles', 'get to the root', 'fundamentally rethink', 'what's the essence', 'strip away assumptions'.

konglong87/methodology-skills · 58 tokens

ai-identity-platform

Structured identity management for AI agent fleets — define, govern, and audit agent personas at scale.

live-neon/persona-mcp · 23 tokens