TypingMindTypingMindThe best frontend for AI
Stakeholder Brief logo

Stakeholder Brief

Community
leeandev
stakeholder-brief

Use when turning dev/project material (design doc, analysis, plan, status, root-cause report, tool/skill docs) into a document for a specific audience such as executives, customer PMs, internal staff or other teams, or customer engineers. Leads document requests that name an audience, and stop-slop-ko runs last as the tone pass. Triggers include /stakeholder-brief, "고객PM/경영진용으로 정리해줘", "직원 공유용 md 만들어줘", "이해관계자 공유용 문서/브리프/소개 자료 만들어줘". Outputs HTML, DOCX, or MD.

Overview

Publisherleeandev
Repositorystop-slop-ko
Skill namestakeholder-brief
Stars
77
Forks
4
Bundled files
5
LicenseMIT
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by leeandev on GitHub. Read the source before you install it.

Installation

Install the Stakeholder Brief AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/leeandev/stop-slop-ko/tree/main/plugins/stakeholder-brief/skills/stakeholder-brief
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/leeandev/stop-slop-ko.git /tmp/stop-slop-ko
mkdir -p .claude/skills
cp -r /tmp/stop-slop-ko/plugins/stakeholder-brief/skills/stakeholder-brief .claude/skills/stakeholder-brief
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Stakeholder Brief in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Stakeholder Brief on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Stakeholder Brief is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

stakeholder-brief

개발 자료(.md 산출물, 설계·분석 문서, 도구·스킬 파일)를 정해진 청중 눈높이의 공유 문서(HTML/DOCX/MD)로 바꾸는 하네스. 어려운 건 렌더링이 아니라 청중 눈높이 재구성 + 문서 유형에 맞는 재구조화다.

스킬 순서: 청중이 정해진 문서 요청이면 이 스킬이 먼저 청중과 구조를 잡고, stop-slop-ko는 마지막 문체 패스로만 쓴다. 문장을 먼저 다듬고 구조를 나중에 잡으면 재구성 과정에서 다듬은 문장이 다시 흐트러진다.

핵심 원칙 (어기면 문서가 망함)

  • 사실·숫자·결정은 원문에서만. 원문에 없는 진척률·일정·수치·결정을 지어내지 않는다. 없으면 "미정 / 확인 필요"로 표기.
  • 기술을 추상화하되 왜곡하지 않는다. 깊은 기술은 삭제가 아니라 부록/접기로.
  • 한 번에 한 청중. 청중이 바뀌면 다시 돌린다(한 문서에 여러 청중 욱여넣기 금지).

워크플로

  1. 입력·청중 확정 — 원본(단일 .md 또는 관련 파일 묶음) + 대상 청중 지정. 청중 미지정이면 먼저 물어본다.
  2. 문서 유형 결정 — 진행·합의를 공유하는 문서면 합의형(references/consensus-spine.md), 도구·절차·기능을 알려 주는 문서면 가이드형(references/guide-spine.md).
  3. 청중 렌즈 — references/audience-personas.md로 {관심사·전문용어 예산·깊이·원하는 액션} 적용
  4. 재구조화 — 고른 스파인에 원문 재배치 + 전문용어 번역 + so-what 추출 + 근거 추적(원문 위치)
  5. 렌더 — HTML → references/render-html.md / DOCX → references/render-docx.md / MD → 아래 "MD 출력"
  6. 톤 패스 — stop-slop-ko 스킬로 어조 정리 후 slop_scan.py로 스캔(한국어 개조식/서술체는 청중에 맞춤)
  7. 검증 — 숫자·결정 원문 대조, 청중 눈높이 확인, "지어낸 현황 없음" 자기점검

합의 문서 스파인 (기본)

  1. 1p 요약 (경영진 3줄: 지금 어디·무엇 결정됨·리스크)
  2. 배경·목적
  3. 진행 현황 (마일스톤·%·상태색)
  4. 합의된 결정
  5. 미결 / 리스크
  6. 다음 단계·일정
  7. 부록 (기술 상세·용어집)

가이드형(도구·절차 소개)은 references/guide-spine.md: 한눈에 보기 → 왜 필요한가 → 무엇을 하나 → 설치·적용 → 사용 예시 → 주의·한계 → 문제 해결 → 부록.

청중 (한 번에 하나)

경영진/스폰서 · 고객 PM/이해관계자 · 저년차/타팀 개발자 · 고객 개발자 — 프로필·번역 강도는 audience-personas.md.

출력

  • HTML 아티팩트 — 자기완결 파일(상태색·진행률 바·부록 <details> 접기). 빠른 공유용.
  • DOCX — python-docx. 공식 산출물·납품용.
  • MD — 사내 리포·위키·메신저 공유용. 아래 "MD 출력".
  • (PPTX가 필요하면 그때 추가. 현재 스코프 아님)

MD 출력

  • GFM 기준: 제목 번호(## 1.), 앞쪽 목차(앵커 링크), 섹션 사이 ---, 표·코드블록. 같은 폴더에 기존 가이드가 있으면 그 구성을 따른다.
  • 상태색은 이모지 대신 텍스트(완료, 진행, 지연, 미정). 장식 이모지·★ 금지.
  • 부록은 HTML의 <details> 대신 문서 끝 ## 부록 절로.
  • 명령어·경로·설정은 반드시 코드블록. 실제로 돌려 본 명령만 싣고, 못 돌린 건 "미검증"으로 표시.
  • 저장 위치·파일명은 사용자 문서 규칙을 따른다(주제로 시작, 날짜·버전은 파일명에 넣지 않음).

Common Mistakes

  • stop-slop-ko로 문장부터 다듬고 구조를 나중에 잡음 → 순서: 이 스킬로 재구성 먼저, stop-slop-ko는 마지막
  • 가이드형 문서에 합의형 스파인(현황·합의 결정)을 억지로 끼움 → 문서 유형부터 정한다
  • 원문에 없는 진척률·일정·결정을 그럴듯하게 지어냄 → 금지, "미정"으로
  • 기술을 과도하게 쳐내 부정확해짐 → 부록으로 내리되 사실 보존
  • 여러 청중을 한 문서에 → 초점 흐림. 한 번에 한 청중
  • 어조가 기계적 → 마지막에 stop-slop-ko
  • "완료"를 원문 근거 없이 단정 → 원문에 근거 있는 것만 완료로

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Stakeholder Brief AI skill do?

Use when turning dev/project material (design doc, analysis, plan, status, root-cause report, tool/skill docs) into a document for a specific audience such as executives, customer PMs, internal staff or other teams, or customer engineers. Leads document requests that name an audience, and stop-slop-ko runs last as the tone pass. Triggers include /stakeholder-brief, "고객PM/경영진용으로 정리해줘", "직원 공유용 md 만들어줘", "이해관계자 공유용 문서/브리프/소개 자료 만들어줘". Outputs HTML, DOCX, or MD.

Why use Stakeholder Brief on TypingMind?

Because you install it once and use it with any model. Stakeholder Brief is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Stakeholder Brief in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/leeandev/stop-slop-ko/tree/main/plugins/stakeholder-brief/skills/stakeholder-brief. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Stakeholder Brief?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Stakeholder Brief?

As many as you like. As long as a model supports skills, you can use Stakeholder Brief with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Stakeholder Brief AI skill free?

Yes. It is published on GitHub by leeandev under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
NousResearch logo

Adversarial Ux Test

NousResearch
OrganizationPopular

Roleplay a hostile user to find and triage UX pain points.

53.5K
250.4K
Instructions
View
NousResearch logo

3 Statement Model

NousResearch
OrganizationPopular

Build integrated IS/BS/CF financial workbooks in Excel.

53.5K
250.4K
3 files
View
NousResearch logo

Comps Analysis

NousResearch
OrganizationPopular

Build comparable-company valuation workbooks in Excel.

53.5K
250.4K
Instructions
View
NousResearch logo

Lbo Model

NousResearch
OrganizationPopular

Build leveraged buyout workbooks with IRR/MOIC in Excel.

53.5K
250.4K
Instructions
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇