Purpose
Turn scattered inputs — metrics, background, competing options, and a decision that needs to be made — into a tight, decision-ready briefing that senior stakeholders can absorb in five minutes and act on with confidence. Solves the problem of executives walking into decisions under-briefed or over-buried in raw material.
When to Use
Invoke this skill when the user asks to:
- Prepare a pre-read or briefing doc before a board or steering committee meeting
- Write a decision memo asking leadership to approve, fund, or choose between options
- Summarize a complex situation into an executive-ready context document
- Build a briefing for a stakeholder who wasn't in the room for the working sessions
- Frame a recommendation with the tradeoffs and risks a senior audience will scrutinize
- Consolidate research, data, and discussion into a single page before a key decision
Inputs Required
Before starting, collect:
- The decision: The specific question stakeholders need to resolve or approve
- Audience: Who reads this (roles/seniority), and what they already know vs. don't
- Background context: The situation, how it arose, and why it matters now
- Supporting data: Metrics, financials, research, or evidence available
- Options on the table: The 2–4 paths being considered (if a choice is involved)
- The recommendation: The user's current view, if they have one
- Timeline / stakes: Deadline for the decision and what's at risk if it slips or goes wrong
If no recommendation is provided, derive one from the data and options, and flag it as a proposed recommendation for the user's review.
Instructions
Step 1: Frame the Decision
Open with the single question the briefing exists to answer. State it as a decision, not a topic — "Should we enter the enterprise segment in Q3?" not "Enterprise segment overview." Then in one line, state why this decision is on the table now (the trigger or deadline). This becomes the top of the document — the stakeholder should know within 10 seconds what they're being asked to weigh in on.
Step 2: Write the Bottom Line Up Front (BLUF)
In 2–3 sentences, state the recommendation and the single most important reason for it. Senior readers decide whether to trust the analysis in the first paragraph — lead with the answer, then justify. If the recommendation is conditional, state the condition ("Recommend proceeding, contingent on securing the second supplier").
Step 3: Establish Context
Give only the background the audience needs to evaluate the recommendation — not a full history. Calibrate to what the audience already knows (from Step 1's intake). Cover: how the situation arose, what's changed recently, and what happens if no decision is made. Keep this to 3–5 sentences or 3–4 bullets.
Step 4: Present the Evidence
Surface the data that drives the recommendation, framed for interpretation — not raw numbers. For each key metric, state the number and what it means ("Churn rose to 8% — above the 5% threshold where CAC payback breaks even"). Prioritize 3–5 pieces of evidence that most influence the decision. Use a compact table if comparing figures across time or options.
Step 5: Lay Out the Options
If a choice is involved, present each option with a consistent structure:
- Option name and one-line description
- Upside: The primary benefit or opportunity
- Cost/tradeoff: What it requires or sacrifices
- Key risk: The main thing that could go wrong
Present options neutrally enough that the reader trusts the analysis, then make the recommendation clear. Include the "do nothing" option when it's a real alternative.
Step 6: Name the Risks and Mitigations
List the 3–5 risks a skeptical senior stakeholder will raise — and address them before they're asked. For each: the risk, its likelihood/impact in a phrase, and how it's mitigated or monitored. This is what separates a briefing from a pitch; naming the downside builds credibility.
Step 7: State the Ask
Close with exactly what's needed from the reader and by when: a decision, an approval, a resource, or input on a specific open question. Be concrete — "Requesting approval to allocate $400K and a go/no-go decision by March 15." If there are open questions requiring the stakeholder's judgment, list them separately.
Output Format
- Structure: Single briefing document, top-loaded with the decision and recommendation, supporting detail below
- Length: 500–800 words (one to two pages)
- Format: Structured document — short prose paragraphs with bulleted evidence, options, and risks; compact table only where comparing figures
- Sections: Decision Question → Bottom Line (BLUF) → Context → Evidence → Options → Risks & Mitigations → The Ask
- Tone: Chief-of-staff voice — precise, neutral, senior-reader-calibrated; no hedging, no filler, no persuasion theater
Quality Checklist
Before delivering output, verify:
- [ ] The decision question appears in the first two lines and is phrased as a decision, not a topic
- [ ] The recommendation is stated up front, before the supporting analysis
- [ ] Every metric is paired with its interpretation — no raw numbers left unexplained
- [ ] Each option (when present) uses the same structure: upside, cost, key risk
- [ ] At least 3 risks are named with mitigations — the briefing addresses objections, not just benefits
- [ ] The Ask specifies both what is needed and the deadline
- [ ] Total length stays within one to two pages (500–800 words)
Notes
- If the audience is deeply familiar with the situation, compress or drop the Context section — repeating known background erodes trust with senior readers
- When the user has no recommendation, still commit to a proposed one; a briefing that presents options without a point of view forces the executive to do the analysis themselves
- The "do nothing" baseline is often the strongest reframe — quantifying the cost of inaction sharpens every other option
- Match evidence density to the decision's reversibility: high-stakes, one-way-door decisions warrant more risk detail; reversible calls should stay lean
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:
- Drag this file into a new chat, or copy and paste its contents
- 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