storybrand
Skill0 starsChanged 27 days agoMITView on GitHub
Apply the StoryBrand SB7 framework to create or evaluate customer-facing copy. Two modes — Write (homepage, landing page, email, ad, one-liner) and Audit (review existing copy against SB7 checklist). Invoke when user says "use StoryBrand," "SB7," "apply the framework," or requests help with brand messaging, homepage copy, or marketing copy where narrative structure matters. Not for blog posts, SEO articles, or general writing.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- getagentseal/founder-playbooktheir own version, first seen Oct 13, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- getagentseal/founder-playbook★ 745same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository22 other files it gives its agents.
- ai-writing-tellsSkill
- animated-explainerSkill
- ann-handleySkill
- buyer-personasSkill
- desktop-mockupSkill
- linkedin-guest-kitSkill
- mobile-mockupSkill
- pesty-asana-tasksSkill
- pesty-designSkill
- pesty-explainerSkill
- pesty-frontendSkill
- presentation-structureSkill
- problem-solving-processSkill
- pyramid-principleSkill
- scrSkill
- storytellingSkill
- transcript-cleanupSkill
- ui-designSkill
- untangleSkill
- website-launch-impact-reportSkill
- youtube-thumbnailsSkill
- yt-structureSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 6 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 21
Read references/brandscript.md for the full 8-question BrandScript with examples and language patterns.
- Distinctive: line 23
If client/brand context is already known in this session, fill in the BrandScript from context and only ask when an answer cannot be …
- Distinctive: line 31
CALL TO ACTION — Direct CTA + Transitional CTA
- Very specific: line 37
Read references/surfaces.md for the full wireframe, one-liner formula, and email stage structure.
- Very specific: line 50
Read references/audit-checklist.md for the full checklist.
- Distinctive: line 58
User can't identify the villain: Ask: "What is the one thing that stands between your customer and what they want?" If still stuck, offer 3 …
- Distinctive: line 60
User skips BrandScript and wants copy directly: Do not skip it. Say: "I need 5 minutes of BrandScript answers first — otherwise the copy …
- Distinctive: line 62
Client context conflicts across session: If memory has prior BrandScript answers, confirm they still apply before using them.
- Distinctive: line 64
Audit on very short copy (tagline, ad): Not every SB7 element can fit in 10 words.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
StoryBrand SB7 Skill
Mode Detection
Determine mode before doing anything else:
- Write mode: User wants to CREATE copy (homepage, email, ad, one-liner, landing page).
- Audit mode: User wants to EVALUATE existing copy against SB7.
WRITE MODE
Step 1: Build the BrandScript (REQUIRED — never skip)
Read references/brandscript.md for the full 8-question BrandScript with examples and language patterns.
If client/brand context is already known in this session, fill in the BrandScript from context and only ask when an answer cannot be confidently determined. Otherwise, ask each question. Record all answers before writing any copy.
Questions to answer:
- HERO — What does the customer want? (one desire, not a list)
- VILLAIN — What root cause threatens that desire?
- PROBLEM — External / Internal / Philosophical
- GUIDE — Empathy statement + competency evidence
- PLAN — 3-step process plan or agreement plan
- CALL TO ACTION — Direct CTA + Transitional CTA
- FAILURE — What does the customer lose by not buying?
- SUCCESS — Before/After grid + success type
Step 2: Apply to the Output Surface
Read references/surfaces.md for the full wireframe, one-liner formula, and email stage structure.
Available surfaces:
- Homepage / Landing page — 8-section wireframe in prescribed order
- One-liner — 3-part formula (Problem → Product → Result)
- Email / Drip — Curiosity / Enlightenment / Commitment stage mapping
Deliverable: the finished copy for the requested surface, plus the BrandScript when one was built.
AUDIT MODE
Read references/audit-checklist.md for the full checklist. If a numeric score is wanted, also read references/scoring.md for the rubric.
For each failed item: state what specifically is broken, quote the offending copy, and suggest the exact fix.
Troubleshooting
User can't identify the villain. Ask: "What is the one thing that stands between your customer and what they want?" If still stuck, offer 3 archetypal villain options (external force, internal resistance, broken system) and let them pick the closest.
User skips BrandScript and wants copy directly. Do not skip it. Say: "I need 5 minutes of BrandScript answers first — otherwise the copy will sound generic. Let's go fast." Then ask only the questions you can't infer from context.
Client context conflicts across session. If memory has prior BrandScript answers, confirm they still apply before using them. Brand strategy shifts; stale BrandScript produces wrong copy.
Audit on very short copy (tagline, ad). Not every SB7 element can fit in 10 words. Scope the audit to: hero/guide framing, CTA clarity, and whether the internal problem is addressed.
Examples
Write mode — one-liner request: User: "Use StoryBrand to write a one-liner for our pest control company." Skill: Asks 8 BrandScript questions → hero = homeowner who wants peace of mind, villain = invasive pests, problem = embarrassment + health risk + feeling like a bad host, etc. → produces: "Many homeowners deal with the anxiety of seeing pests in their home. [Company] offers fast, guaranteed treatments so you can stop worrying and get back to enjoying your space."
Audit mode: User: "Audit this homepage copy against SB7." Skill: Loads audit-checklist.md → runs each check → outputs a flagged list: "CTA check FAIL — 'Learn More' is passive. Change to 'Get a Free Quote.' Guide check FAIL — empathy is implied but never stated. Add: 'We know how unsettling it is to find pests in your home.'"
Pairing
Once SB7 structure is right, run the ann-handley skill for line-level voice and style polish on the output.
Maintained by Pesty Marketing · Browse the full skill catalog.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.