pyramid-principle

pyramid-principle is a skill for Claude Code from ironyjk/strategy-frameworks. It costs 43 tokens per session (3,259 once invoked), scanned A, original, MIT.

A way to organise thinking and communication from the main answer down to its supporting reasons. It groups related evidence under clear points.

In plain words
What is it for?
Use it to write recommendations, reports, presentations, and other messages where readers need the conclusion first.
Why use it?
It prevents the key conclusion from getting buried under background information and makes complex explanations easier to follow.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the strategy-frameworks plugin — 27 skills shipped together

Good fit Use it to write recommendations, reports, presentations, and other messages where readers need the conclusion first.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ironyjk/strategy-frameworks/pyramid-principle
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 ironyjk/strategy-frameworks --skill pyramid-principle
Clone the repo
git clone --depth 1 https://github.com/ironyjk/strategy-frameworks

Made for: Claude Code.

Or install strategy-frameworks, the plugin that ships this one along with the rest of its 27 skills.

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 pyramid-principle

README.md
[![agentmods](https://agentmods.dev/badge/skills/ironyjk/strategy-frameworks/pyramid-principle/github.svg)](https://agentmods.dev/skills/ironyjk/strategy-frameworks/pyramid-principle)
Your own site
<a href="https://agentmods.dev/skills/ironyjk/strategy-frameworks/pyramid-principle"><img src="https://agentmods.dev/badge/skills/ironyjk/strategy-frameworks/pyramid-principle/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 pyramid-principle

Your own site · 80×15
<a href="https://agentmods.dev/skills/ironyjk/strategy-frameworks/pyramid-principle"><img src="https://agentmods.dev/badge/skills/ironyjk/strategy-frameworks/pyramid-principle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,259 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 $0.00043 $0.03259
Opus 5 $0.00022 $0.01630
Sonnet 5 $0.00009 $0.00652
Haiku 4.5 $0.00004 $0.00326

Measured 9d ago against content hash 0f495cc47564, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pyramid-principle 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 9d 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.

pyramid-principle/SKILL.md · 301 lines

How it starts

The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pyramid Principle (피라미드 원칙)

Barbara Minto가 McKinsey에서 개발한 구조적 사고 및 커뮤니케이션 프레임워크. 핵심: 결론을 먼저, 근거는 그 아래에 (Top-Down).


1. Core Rule: Answer First (결론 선행)

절대 규칙: 항상 답(결론/권고)을 먼저 제시하고, 그 다음에 근거를 배치한다.

  • 독자/청중은 "So what?"을 먼저 알고 싶어 한다
  • 근거부터 나열하면 핵심이 묻힌다
  • 경영진은 결론을 먼저 듣고, 필요하면 근거를 파고든다
❌ 나쁜 예: "A 조사를 했고, B 분석을 했고, C 결과가 나왔고... 그래서 X를 해야 합니다"
✅ 좋은 예: "X를 해야 합니다. 이유는 세 가지입니다: ①... ②... ③..."

2. Pyramid Structure (피라미드 구조)

                    ┌─────────────────────┐
                    │   Governing Thought  │  ← 핵심 메시지 (결론/권고)
                    │   (지배적 사고)        │
                    └──────────┬──────────┘
                               │
              ┌────────────────┼────────────────┐
              │                │                │
        ┌─────┴─────┐   ┌─────┴─────┐   ┌─────┴─────┐
        │ Key Line 1 │   │ Key Line 2 │   │ Key Line 3 │  ← 핵심 근거 (3~5개)
        │ (핵심근거1) │   │ (핵심근거2) │   │ (핵심근거3) │
        └─────┬─────┘   └─────┬─────┘   └─────┬─────┘
              │                │                │
         ┌────┼────┐     ┌────┼────┐     ┌────┼────┐
         │    │    │     │    │    │     │    │    │
        [데이터/사실]   [데이터/사실]   [데이터/사실]     ← 뒷받침 데이터

규칙:

  • 각 레벨은 아래 레벨의 요약(summary) 이어야 한다
  • 같은 레벨의 항목은 동일한 종류의 아이디어여야 한다
  • 그룹 내 항목은 논리적 순서로 배열한다

3. MECE Principle (상호배제 완전포괄)

Mutually Exclusive, Collectively Exhaustive

원칙 의미 테스트
ME (상호배제) 항목 간 겹침 없음 "이 두 항목에 동시에 속하는 것이 있는가?" → No
CE (완전포괄) 빠짐 없이 전체를 커버 "이 항목들 외에 빠진 것이 있는가?" → No

MECE 그룹화 방법:

  • 프레임워크 활용: 3C, 4P, SWOT, 내부/외부, 단기/장기
  • 프로세스 단계: 조달→생산→출하→A/S
  • 세그먼트 분류: 지역별, 고객군별, 제품별
❌ Non-MECE: "영업 문제, 마케팅 문제, 고객 문제" (겹침 존재)
✅ MECE:     "수요 측 문제, 공급 측 문제, 구조적 문제" (겹침 없고 전체 커버)

4. Two Ways to Build a Pyramid (피라미드 구축 방법)

4a. Top-Down (하향식) — 결론을 아는 경우

  1. 질문 정의: 독자가 가진 핵심 질문은?
  2. 답변 작성: 그 질문에 대한 답(결론)을 한 문장으로
  3. 근거 도출: 답을 뒷받침하는 3~5개 핵심 근거
  4. 데이터 배치: 각 근거를 뒷받침하는 사실/수치

Read the full file on GitHub · 301 lines

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. 9d ago First seen · 301 lines · 43 tokens per session scan A 0f495cc47564

Subscribe to this mod's changes

pyramid-principle is a skill published in the GitHub repository ironyjk/strategy-frameworks (11 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 3,259 once invoked, about $0.0002 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 2026-08-30.