Systems Lab

Agent skill

marketing-content-case-study

Write a B2B case study (500-1500 words, PASTOR framework) from a content idea.

activeSelf-containedInstructions only459 words

Filed under Content and SEO.

From b2bforce/b2bforce · 29 skills · 2 · pushed 2026-08-21

What it does when it runs

Write a B2B case study (500-1500 words, PASTOR framework) from a content idea. Use when content_type is case_study and buying_stage is decision or vendor. Uses Exa reference articles. Output to workspace/marketing/content/drafts/case-studies/.

Read from the skill and the 1 file bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply
None found.
Hosts it reaches
No third-party host appears in the skill or its bundled files.
Tool permissions it declares
No allowed-tools in the frontmatter. It only issues instructions, so there is nothing to bound.
Actions present in the files
None. Instructions only.

Ask about marketing-content-case-study

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah
git clone --depth 1 --filter=blob:none --sparse https://github.com/b2bforce/b2bforce.git /tmp/b2bforce
git -C /tmp/b2bforce sparse-checkout set ".agents/skills/marketing-content-case-study"
mkdir -p ~/.claude/skills/marketing-content-case-study
cp -R "/tmp/b2bforce/.agents/skills/marketing-content-case-study/." ~/.claude/skills/marketing-content-case-study/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

Reproduced in full from b2bforce/b2bforce/blob/7682ed90c62190a0f3c09eb135596d08bd6890bc/.agents/skills/marketing-content-case-study/SKILL.md, which is licensed MIT (skill frontmatter). 459 words, 9 headings.

Case Study Generation

Draft pipeline for a content idea of type case_study.

When to Use

  • Idea with content_type: case_study
  • Buying stage must be decision or vendor only

Prerequisites

  • Valid content idea (stage check)
  • Firm/service/ICP/persona context
  • Current agent/LLM session
  • Optional: Exa reference notes via tool-exa for quality benchmarks
  • A record in workspace/firm/proof/ with usable_publicly: true when the idea uses placeholder proof

Prompt layering

  1. Base writer
  2. Quality layer
  3. Case study format layerreferences/format-requirements.md

Follow the shared draft gate and writing quality rules in docs/content-generation.md.

Proof gate

If proof_source says needs real client proof before draft, or the title contains [Client], do not ask the user to retype the facts yet — read workspace/firm/proof/ first. See the Proof Gate in AGENTS.md.

  1. Look for a record matching this service and ICP.
  2. A case study is public material, so it requires usable_publicly: true. A record with usable_publicly: false may not be drafted into a case study even though a private proposal could cite it.
  3. Name the client only with client_public: true; otherwise use the record's approved anonymized label.
  4. Quote the client only with quote_approved: true.
  5. Use only metrics with verified: true.

If no usable record exists, stop and ask for the client facts, then have sales-outcome-log write them to workspace/firm/proof/ before drafting. Recording them once is what stops this gate from blocking every future case study.

Facts needed for a record: client name or approved label, starting situation, service delivered, timeline, 2–3 real metrics, and an approved quote or a note that none is available.

Do not invent metrics, quote, client name, industry, timeline, or result.

PASTOR structure (required)

  • P Problem — client challenge with context
  • A Amplify — consequences (revenue, team, risk)
  • S Solution — your process/approach
  • T Transformation — results with metrics (%, $, time)
  • O Offer — how reader gets similar results
  • R Response — clear CTA

Must include

  • 2–3 quantifiable metrics when real metrics are available; otherwise use verified qualitative outcomes and state proof limits plainly
  • At least 1 client quote only when supplied or approved
  • Before vs after comparison
  • Timeline of engagement

Research

Optional Exa: 5 reference case studies/articles on topic for quality benchmark (do not copy).

Output

Brand scope. In a multi-brand workspace the draft inherits the idea file's brand: write to workspace/marketing/content/{brand}/drafts/… — same brand segment as the idea. See the Brand Scope Gate in AGENTS.md.

workspace/marketing/content/drafts/case-studies/{slug}.md — Markdown

Headline pattern: "[Client Result] in [Timeframe]" or "How [Client] Achieved [Result]"

Frontmatter: idea, content_type, buying_stage, service, icp, persona, generated_at. Run scripts/validate-content-draft.sh {output} and update the idea to status: generated after the draft validates.

Files bundled with it

These load only when the skill asks for them, so they cost nothing until it runs.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

Need help setting it up?

This page tells you what marketing-content-case-study does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.