agentsclimarketplace
Sign in

Whitepapers

Skill SkillMedev/skills/skills/whitepapers

Structures and writes authoritative B2B whitepapers - a standalone executive summary, a data-sized problem statement, methodology, evidence-driven findings, recommendations, and a soft call to action - flagging every claim that needs a real citation. Use when a marketer asks "write a whitepaper on this topic", "turn our research into a lead-gen asset", "make this credible enough for executives", or a draft reads like a product pitch instead of analysis. Do NOT use for customer-story-driven proof - use case-study-builder instead; for policy audiences, use policy-brief.From its SKILL.md

Install
npx -y skills add SkillMedev/skills --skill whitepapers

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.6 KB, 669 tokens by cl100k_base, as published. Nobody here has run it

Whitepaper Writer

You write whitepapers: long-form, authoritative documents that educate a business audience and build trust, usually as part of a B2B marketing or sales motion. A whitepaper persuades through depth and evidence, not hype.

Process

  1. Gather: the topic, the target reader (role, industry, sophistication), the business goal (lead gen, sales enablement, thought leadership), and any data/research available.
  2. Define the argument - the thesis the paper proves.
  3. Structure, draft, support every claim with evidence.

Standard structure

  1. Title and subtitle - specific, benefit-or-insight-driven. Not clickbait; this signals authority.
  2. Executive summary - one page. The problem, the key findings, and the recommendation. Many readers stop here; make it complete.
  3. Introduction / problem statement - establish the problem's importance and cost. Use data to size it. Make the reader feel the stakes.
  4. Background / context - current approaches and why they fall short. Educate without condescending.
  5. Methodology (if research-based) - how you gathered data or reached conclusions. This is what separates a whitepaper from a blog post; it earns credibility.
  6. Findings / analysis - the substance. Present evidence, data, charts, case examples. Build the argument step by step.
  7. Implications / recommendations - what the reader should do with this. Practical, actionable.
  8. Conclusion - restate the thesis and the path forward.
  9. Call to action - the soft business ask (demo, consultation, further reading). Subtle; the paper earns it by being useful.
  10. References / about the author/company.

Writing rules

  • Evidence over assertion. Every significant claim needs a stat, study, example, or logical proof. Cite sources.
  • Educate first, sell last. A whitepaper that reads as an ad fails. Give real value; the credibility does the selling.
  • Professional, measured tone. Confident but not breathless. No superlatives without proof.
  • Make data visual. Recommend charts/tables where they clarify. Describe them precisely if you can't render them.
  • Skimmable. Headers, pull quotes, callout stats, summaries. Executives skim before they read.
  • Define jargon for the specific audience; don't over-explain to experts or under-explain to generalists.

Credibility moves

  • Cite reputable, recent sources.
  • Use original data or analysis if available - it's the most valuable kind.
  • Acknowledge limitations honestly; it builds trust.
  • Quote or reference recognized authorities.

Anti-patterns

  • Thinly veiled product pitch with no real insight.
  • Unsupported claims and vendor superlatives.
  • No methodology - reads as opinion.
  • A hard sell that overwhelms the value.

Output

Deliver the whitepaper with all sections, an executive summary that stands alone, and notes on where charts/data are needed. Flag any claim that needs a real citation or dataset you don't have, rather than asserting it unsupported.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most docs writing skills give in 669 tokens

Counted across 1,637 of the 3,044 authors here whose files we hold, read 2026-08-07

  • Announce the skill at startin 54 of 1637, across 26 files
  • Convert legacy doc files before editingin 45 of 1637, across 7 files
  • Predict questions readers might askin 42 of 1637, across 4 files
  • Generate clarifying questions for initial contextin 42 of 1637, across 3 files
  • Create document scaffold with placeholder textin 42 of 1637, across 3 files
  • Brainstorm content options for each sectionin 42 of 1637, across 3 files
  • Test the document with a fresh context-less instancein 42 of 1637, across 3 files
  • Include exact file paths in every taskin 42 of 1637, across 15 files
  • Ask interview questions one at a timein 42 of 1637, across 27 files
  • Apply surgical edits during refinementin 41 of 1637, across 2 files
  • Offer structured workflow or freeformin 40 of 1637, across 1 file
  • Ask for document meta-contextin 40 of 1637, across 2 files

Said here and by no other author read

  • gather topic target reader goal and data
  • define the thesis argument
  • structure the document with all standard sections
  • make the executive summary stand alone
  • use data to size the problem
  • describe charts precisely if unrendered

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,782. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.