Skip to content This library is free, offered as dana. If it helps your work, donate here →

This is one of 3,622 free prompts in the penguin tree ai library. Sign up once and the whole library opens, with new prompts by email.

open the library →

Cross-audience communication adapter

Transforms a single piece of technical content into three audience-calibrated versions — technical practitioner, executive sponsor, and mixed-room — each with adjusted vocabulary, altitude, proof points, and calls to…

download .md

Purpose

Take one core message — a technical update, project status, incident recap, or product recommendation — and produce distinct versions tuned for developers, executives, and mixed rooms, so the same truth lands correctly regardless of who's reading. Eliminates the two failure modes: burying executives in technical detail, or hollowing out a message until practitioners stop trusting it.

When to Use

Invoke this skill when the user asks to:

  • Rewrite a technical update for an executive or C-suite audience
  • Build a QBR section that works for both the practitioner team and their sponsor
  • Turn an engineering-heavy status into an exec briefing or board-ready summary
  • Adapt an incident postmortem for the customer's technical team vs. leadership
  • Send one email that needs to satisfy both an admin/developer and their VP
  • Create tiered talking points for a mixed-stakeholder meeting

Inputs Required

Before starting, collect:

  • Source content: The original message, notes, or draft — technical detail included
  • Target audiences: Which versions are needed (technical / executive / mixed — one or more)
  • Format: Email, deck slide, briefing doc, talking points, or Slack/chat message
  • Core outcome: The one decision, action, or takeaway the reader must walk away with
  • Relationship context: New account / stable / at-risk / renewal / escalation
  • Sensitivities: Anything to soften, avoid, or explicitly own (a miss, a delay, a bad metric)

If target audiences aren't specified, produce all three versions. If format is missing, default to email for executive and technical, talking points for mixed.

Instructions

Step 1: Extract the Invariant Core

Before adapting anything, isolate what stays true across every version:

  • The fact: What actually happened or is being recommended (never changes)
  • The outcome: The single decision or action required
  • The proof: The strongest supporting evidence available Write these three down internally. Every version must preserve all three — only the framing, altitude, and detail change.

Step 2: Build the Technical Practitioner Version

Audience: developers, admins, engineers, technical implementers.

  • Altitude: Ground level — the "how" and the "why it works"
  • Vocabulary: Precise technical terms; no dumbing down; assume domain fluency
  • Detail: Include specifics — versions, configs, error codes, metrics, root cause
  • Proof: Reproducible evidence, logs, benchmarks, methodology
  • Trust driver: Accuracy and specificity — vagueness reads as incompetence to this audience
  • Call to action: A concrete technical next step (implement X, test Y, review config Z)
  • Length: Longer is acceptable if every detail earns its place

Step 3: Build the Executive Sponsor Version

Audience: C-suite, VPs, budget owners, business decision-makers.

  • Altitude: 30,000 feet — the "so what" for the business
  • Vocabulary: Business outcomes — cost, risk, time-to-value, revenue, adoption, retention
  • Detail: Minimal technical detail; translate every technical fact into a business consequence
  • Proof: Quantified impact — dollars, hours saved, risk reduced, benchmark vs. goal
  • Trust driver: Clarity and confidence — one clear ask, no hedging, no jargon
  • Structure: Lead with the conclusion (BLUF — bottom line up front), then support
  • Call to action: A business decision (approve, prioritize, allocate, endorse)
  • Length: Tight — 3–5 sentences or bullets for email; one slide for a deck

Step 4: Build the Mixed-Room Version

Audience: both present at once (e.g., a QBR with the admin team and their VP).

  • Layered structure: Executive summary first (so leadership gets it in 15 seconds), technical appendix or expandable detail second (so practitioners can go deep)
  • Signposting: Explicitly label sections so each audience knows where their content lives
  • Bridge language: Connect the technical detail to the business outcome in one sentence so neither audience feels the other's section is wasted air
  • Call to action: Two-tiered — the business decision for leadership, the technical next step for the team
  • Avoid the trap of an averaged, blurry middle — layer, don't blend

Step 5: Apply Relationship and Sensitivity Calibration

Adjust tone based on context:

  • At-risk / escalation: Lead with ownership and the fix; quantify the path back to health
  • Renewal: Emphasize value delivered and forward roadmap in the executive version
  • Owning a miss: State the miss plainly in the technical version; frame it as controlled and resolving in the executive version — never spin it away
  • New account: Slightly more context-setting; assume less shared history

Step 6: Verify Consistency Across Versions

Read the fact, outcome, and proof in every version side by side. Confirm no version contradicts another — an executive who reads the technical version later must find the same truth, just described differently.

Output Format

  • Structure: One labeled section per requested audience version, each ready to send/paste as-is
  • Length: Technical version 150–300 words; executive version 60–120 words; mixed version 200–350 words with clear layer breaks
  • Format: Matches requested format per audience (email body, slide copy, briefing doc, or talking points); mixed version uses a layered summary-then-detail structure
  • Sections: Invariant Core (brief, labeled) → Technical Version → Executive Version → Mixed-Room Version → Consistency Note
  • Tone: Technical version — precise and peer-level; executive version — confident, business-fluent, BLUF; mixed version — signposted and bridging. Never condescending in either direction.

Quality Checklist

Before delivering output, verify:

  • [ ] The same fact, outcome, and proof appear in every version — no version contradicts another
  • [ ] The executive version leads with the conclusion and contains zero unexplained technical jargon
  • [ ] The technical version includes at least one specific detail (metric, config, version, root cause) the executive version omits
  • [ ] Each version ends with an audience-appropriate call to action — a technical step for practitioners, a decision for executives
  • [ ] The mixed-room version is layered (summary + detail), not an averaged blend
  • [ ] Any sensitivity flagged in the inputs is handled explicitly, not spun or omitted

Notes

  • The most common failure is the "blurry middle" — a mixed message that satisfies no one. Layering beats averaging every time.
  • Executives don't want less information; they want a different information — consequence over mechanism. Translate every technical fact into "what it means for the business."
  • When owning a miss, the technical version can be more candid than the executive version, but the two must never contradict — leadership will eventually read both.
  • For QBR decks specifically, put the executive version on the visible slide and the technical version in the appendix or speaker notes.

How to use this skill

This file is a Claude Code skill in Anthropic's standard format — markdown with YAML frontmatter at the top.

Installing in Claude Code:

  • ~/.claude/skills/<folder-name>/SKILL.md — auto-loads in every session anywhere on your machine (recommended for skills you'll use across multiple projects)
  • <your-project>/.claude/skills/<folder-name>/SKILL.md — auto-loads only when working in that project (recommended for project-specific skills)

Restart Claude Code or open a new session to register.

Using in Claude.ai, ChatGPT, Gemini, or other AI tools:

  1. Drag this file into a new chat, or copy and paste its contents
  2. Send your task or request as your next message — the AI will apply the skill where it fits

For Claude Code skill details: https://docs.anthropic.com/en/docs/claude-code/skills