Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/Coowoolf/insighthunt-skills --skill flashtag-communication-protocol명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
Use when designing AI agent products, defining roadmaps for agentic workflows, or evaluating how to evolve AI from passive tool to proactive partner in software development
Shift from rigid roles (PM, Designer, Engineer) towards a model where individuals use AI to bridge skill gaps, enabling smaller and flatter teams. Use in early-stage startups or innovation units where speed is critical.
Use when designing AI agents or chatbots, when raw model outputs feel like a black box, or when building natural language interfaces that need structure and trust
SOC 직업 분류 기준
SKILL.md 표시 중
| name | Flashtag Communication Protocol |
| description | Use explicit tags (#fyi, |
"The challenge is people will take [an opinion] and over-index on what was an opinion... Flashtags are an escalating set of the 'dying on the hill' spectrum." — Dharmesh Shah
A system of explicit tags used in written communication (email, Slack) that clearly defines the expected weight of the feedback and the required response level.
┌──────────────────────────────────────────────────────┐
│ #fyi │
│ "I found this interesting." │
│ → No response expected. Go on with your life. │
├──────────────────────────────────────────────────────┤
│ #suggestion │
│ "A thought I had." │
│ → You don't have to do it. Consider it. No reply. │
├──────────────────────────────────────────────────────┤
│ #recommendation │
│ "I have researched this. I would do this." │
│ → If you don't do it, explain why (learning loop). │
├──────────────────────────────────────────────────────┤
│ #plea │
│ "I beg of you. High conviction. Please do this." │
│ → Use EXTREMELY rarely (count on one hand). │
└──────────────────────────────────────────────────────┘
STEP 1: Before Sending Feedback
└── Ask: "How strongly do I feel about this?"
└── Choose the appropriate tag
STEP 2: Add Tag to Message
└── "#suggestion: Have you considered..."
└── "#recommendation: Based on X, I'd do Y..."
STEP 3: Respect the System
└── Don't follow up on #fyi or #suggestion
└── Only expect response for #recommendation+
STEP 4: Track #plea Usage
└── Should be extremely rare (1-2x per year)
└── If overused, loses meaning
❌ Overusing #plea (turns into micromanagement)
❌ Following up aggressively on #suggestion (defeats purpose)
❌ Not using any tags (defaults to "founder megaphone")
Dharmesh uses these daily at HubSpot to give product feedback without disempowering the specific product owners (DRIs).
Source: Dharmesh Shah, Lenny's Podcast