Purpose
Turn marketing performance data into a concise, decision-oriented briefing that leads with the takeaway, proves it with revenue-linked metrics, and ends with a clear ask — so a senior leader can grasp what happened, why it matters, and what they need to decide in under five minutes.
When to Use
Invoke this skill when the user asks to:
- Prepare a marketing performance update for an RVP or regional director
- Build the marketing section of a Quarterly Business Review (QBR)
- Summarize a campaign, program, or pipeline contribution for senior leadership
- Convert a metrics dashboard or spreadsheet into an executive narrative
- Request budget, headcount, or strategic backing from leadership
- Brief leadership ahead of a meeting where a decision needs to be made
Inputs Required
Before starting, collect:
- Performance data: The metrics, results, or dashboard the briefing covers (pipeline, leads, MQLs, spend, ROI, attainment, etc.)
- Reporting period: The timeframe — month, quarter, campaign window
- Audience: Who reads this — RVP, regional director, VP of Sales, CMO — and their primary concern (revenue, efficiency, coverage)
- Targets/benchmarks: The numbers being measured against — quota, plan, prior period, or goal
- The decision or ask: What the leader should approve, change, or act on (or "none — informational")
- Known risks or headwinds: Anything off-track, at-risk, or requiring intervention
- Context the leader may not have: Recent changes, market shifts, or dependencies
If targets or benchmarks are missing, request them — performance has no meaning without a comparison point. If no decision is required, frame the briefing as informational and lead with the trend that matters most.
Instructions
Step 1: Find the Single Headline Takeaway
Before writing anything, determine the one sentence a leader would repeat to their boss.
- Lead with outcome, not activity ("Pipeline sourced grew 34% QoQ to $4.2M" — not "We ran 6 campaigns")
- Tie it to a number the audience already cares about (revenue, pipeline, attainment, efficiency)
- If results are mixed, the headline names the net position honestly, then the body explains
- The headline must be true at a glance and survive being read alone
Step 2: Select 3–5 Proof Points, Ranked by Revenue Relevance
Choose only the metrics that support or qualify the headline. Discard vanity metrics.
- Rank by proximity to revenue: Closed/won and pipeline first, then conversion and velocity, then volume metrics last
- Each proof point states the number, the comparison, and the "so what" in one line
- Use the format: Metric → result vs. target/prior → implication
- Example: "Marketing-sourced pipeline: $4.2M, +34% QoQ, now 41% of regional pipeline coverage"
- Translate marketing-native terms into revenue language the audience uses
- Show direction (▲/▼) and magnitude — leaders scan for trend before detail
Step 3: Build the Risks & Asks Section
Senior leaders trust briefings that name problems before being asked.
- Risks: 1–3 items that are off-track or threatening the target — each with current status and the intervention underway
- Asks: The specific decision, resource, or backing needed — stated as a clear request with the expected return
- Format: "Ask: [decision]. Why: [impact]. Cost of inaction: [consequence]."
- If no ask exists, state "No decision required — informational" so leadership isn't hunting for the catch
- Keep asks concrete and bounded — "Approve $25K reallocation to ABM" beats "More budget for marketing"
Step 4: State the Recommendation
End with a recommended path, not a menu.
- One clear recommendation tied to the headline and the ask
- Frame it as the obvious next move given the data, with one sentence of rationale
- Be opinionated — a briefing that ends in "let me know your thoughts" wastes the leader's read
Step 5: Compress to One Page
Cut everything that doesn't change a decision.
- Remove process narration, internal team names, and tool references the leader won't recognize
- Replace jargon with plain business language
- Confirm the entire briefing is scannable top-to-bottom in under 5 minutes
- Every sentence must either state a fact, prove it, or recommend an action
Output Format
- Structure: One-page briefing — headline takeaway up top, proof points, risks & asks, recommendation
- Length: 350–500 words
- Format: Structured document — bolded headline, bulleted proof points with directional markers, short labeled sections (not prose-heavy paragraphs)
- Sections: Headline Takeaway → Performance Proof Points (3–5) → Risks & Asks → Recommendation
- Tone: Confident, plain-spoken, executive-ready — bottom-line-first, no hedging, no marketing jargon a sales leader wouldn't use
Quality Checklist
Before delivering output, verify:
- [ ] The headline takeaway is a single sentence and survives being read alone
- [ ] Every proof point includes a number, a comparison point, and a "so what" implication
- [ ] Proof points are ranked by proximity to revenue — not by what was easiest to measure
- [ ] The ask is specific and bounded, or the briefing explicitly states "informational"
- [ ] The briefing ends with one clear recommendation — not a list of options
- [ ] Total length is under 500 words and readable in under 5 minutes
Notes
- The fastest way to lose a senior leader is to bury the takeaway under activity — always lead with the outcome
- Mixed or negative results build more credibility when stated plainly up front, paired with the intervention already in motion
- Match the audience's metric vocabulary: an RVP cares about pipeline coverage and attainment; a CMO may care about CAC and efficiency — translate accordingly
- If the data doesn't support a clear headline, that's a signal the underlying program needs review, not a prettier briefing
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