# One-Pager Designer > Writes a decision-driving one-pager - problem, evidence, impact, and a specific ask compressed into a single page readable in under three minutes. Use when someone asks "turn this into a one-pager", "write a brief for leadership", "I need a one-page pitch for this decision", or is preparing a document a busy reader must act on from one page. Do NOT use for a client-facing sales proposal with pricing and scope - use sales-proposal-writer instead; for condensing an existing long document use executive-summary; for multi-slide narratives use slide-deck-builder. - Skill: `skillmedev/one-pager-designer` (Agent Skill) - Install (CLI): `npx skillmds@latest add skillmedev/one-pager-designer` - Raw SKILL.md: https://api.skillmd.com/api/skills/skillmedev/one-pager-designer/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Docs & Writing - Author: SkillMedev (https://skillmd.com/u/skillmedev) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/skillmedev/one-pager-designer --- # One-Pager Designer A one-pager is a commitment device: confining the argument to one page forces the author to know what matters and discard what does not. It is not a short document; it is a complete argument at compression. The costly failure it prevents is the vague ask - a page that makes the reader feel informed but gives them nothing to say yes or no to, which means the meeting happens anyway and the page changed nothing. A one-pager is not an executive summary. An executive summary condenses a longer document; a one-pager is the whole argument - it stands alone, requires no parent document, and is designed to be forwarded, printed, or shared independently. ## Inputs to collect 1. **The exact decision or action sought** - if the requester cannot state it in one sentence, extract it before writing anything else; the ask determines everything upstream of it. 2. **The reader** - who decides, what they already know, what they care about. Default to "knows the domain, not the details." 3. **The strongest fact or number** grounding the problem. If none exists, say so and label any estimate as an estimate. 4. **Three to five pieces of evidence** - facts or precedents, not assertions. 5. **The deadline or decision window**, if any. ## Operating procedure Write in this order - ask first, header last - even though the page presents in the reverse. The ask is the load-bearing element; everything else exists to earn it. 1. **Write the ask first.** It must be **specific** (name the exact decision, resource, or approval), **actionable** (something the reader can say yes or no to right now), and **time-bounded** (a deadline or decision window when relevant). "Approve $80K and 1 backend engineer for Q3; decision needed by June 14 to hit the July window" is an ask. "Support this initiative" is a request to feel good about something. 2. **State the problem or opportunity** in two to four sentences, grounded in a specific fact or number - what is broken or what is at stake. 3. **State the recommendation** in two to four sentences - concrete, not aspirational. 4. **List the evidence**: three to five bullets, each one fact or precedent, not assertion. One idea per bullet, no nesting. 5. **Quantify the impact** - what success looks like, in numbers where possible. "Reduces processing time by 40%" beats "significantly faster." 6. **Write the header last**: title, author, date, and a single-sentence purpose statement. 7. **Run the density pass.** Read every line and ask: does removing this change anything? If not, cut it. Delete introductory sentences that restate the title ("This one-pager addresses..."). Delete hedges unless the hedge changes the ask ("This assumes budget approval" stays; "this may or may not work" goes). Six sections. One page. No exceptions - if it spills to page two, the argument is not yet understood well enough to write. ## Worked skeleton (copy and fill) ``` [TITLE - THE RECOMMENDATION, NOT THE TOPIC] [AUTHOR] · [DATE] · Purpose: [ONE SENTENCE - what decision this page seeks] PROBLEM [2-4 sentences. Anchor fact: FILL - e.g. "Support ticket backlog grew from 210 to 640 in two quarters; median first response is now 31 hours."] RECOMMENDATION [2-4 sentences. Concrete: FILL - e.g. "Stand up a 3-person triage rotation and deploy macro templates for the top 12 ticket types."] EVIDENCE • [FILL - fact or precedent, one idea] • [FILL] • [FILL] (3-5 bullets total; no nesting) IMPACT [Quantified: FILL - e.g. "First response under 8 hours within 6 weeks; projected 15% reduction in churn-flagged accounts, worth ~$220K ARR."] ASK [Specific + actionable + time-bounded: FILL - e.g. "Approve 2 internal transfers and $18K tooling budget. Decision needed by May 30."] ``` ## Formatting rules - Single column beats two columns for most uses - it reads faster and prints cleanly. - One level of hierarchy: a bold label per section. No nested bullets. - Whitespace is not waste; a page that fills every pixel is harder to read than one with breathing room. - Numbers beat adjectives, everywhere. ## Deliverable Produce a single page containing exactly six sections - header with purpose statement, problem grounded in a fact, concrete recommendation, 3-5 evidence bullets, quantified impact, and a specific, actionable, time-bounded ask - readable in under three minutes and able to stand alone when forwarded. ## Do NOT - **Do NOT write a vague ask.** "Support this initiative" produces a nod, not a decision, and the page fails its only job. - **Do NOT open with throat-clearing** that restates the title - the reader's first three seconds go to the problem or they go nowhere. - **Do NOT let it depend on a parent document** - a one-pager that needs context is an executive summary wearing the wrong name. - **Do NOT use adjectives where numbers exist.** - **Do NOT nest bullets or add a second hierarchy level** - compression, not outline. - **Do NOT spill to a second page.** Cutting is the work. ## Quality bar The page ships only if: a stranger with domain context could act on it without the author present; the ask names a decision, an owner-of-the-decision, and a date; the problem contains at least one number or verifiable fact; every evidence bullet is a fact, not an opinion; a three-minute read covers everything; and removing any remaining sentence would change the argument.