agentleFS
Pesty-MarketingPesty-Marketing/agent-skills/storytelling/SKILL.md

storytelling

Skill0 starsChanged 27 days agoMITView on GitHub

Apply Will Storr's Science of Storytelling framework (Sacred Flaw, theory of control, dramatic question, change-driven openings) to long-form narrative copy where engagement matters more than direct-response structure. Two modes — Write (founder narrative, brand story, About page, case study, blog hook, long-form sales) and Audit (review existing narrative for character flaw, change, curiosity gap, transformation arc). Invoke when user says "use Storr," "Science of Storytelling," "sacred flaw," "make this more compelling," or requests help with founder stories, About pages, case studies, brand origin, or any narrative where character + transformation is the point. Not for homepages, ad headlines, or scan-first marketing surfaces — use the storybrand skill for those.

22 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ant, artistic and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • bergsideSkill

    ant

    Structured, enterprise-focused design system emphasizing clarity, consistency, and efficiency for data-dense web applications.

    Also in 3 projects that use this

  • bergsideSkill

    artistic

    High-contrast, expressive style with creative typography and bold color choices for visually striking interfaces.

    Also in 3 projects that use this

  • +10 more from bergside

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 14 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the user is asking for a homepage, ad, one-liner, or scan-first marketing surface, stop and recommend the storybrand skill instead.

    line 15
  2. Very specific:

    Read references/sacred-flaw.md for the full 8-step worksheet with sentence stems and examples.

    line 23
  3. Distinctive:

    If character/brand context is already known in this session, fill in the worksheet from context and only ask when an answer cannot be …

    line 25
  4. Very specific:

    Read references/surfaces.md for the full applications and templates (it also has a per-surface effort-budget table — worksheet + drafting …

    line 47
  5. Very specific:

    Read references/craft-rules.md for the line-level rules:

    line 58
  6. Very specific:

    Read references/audit-checklist.md for the full checklist.

    line 70
  7. Very specific:

    If the user wants a numeric score, read references/scoring.md.

    line 74
  8. Distinctive:

    User skips the worksheet and wants narrative directly: Do not skip it. Say: "I need 5 minutes of Sacred Flaw answers first — otherwise the …

    line 82

“Common” is measured: kept by at least 6 in 10 of the 14 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Science of Storytelling Skill (Will Storr)

Mode Detection

Determine mode before doing anything else:

  • Write mode: User wants to CREATE narrative copy (founder story, About page, brand origin, case study, long-form hook, character-driven blog opener).
  • Audit mode: User wants to EVALUATE existing narrative against Storr's framework.

If the user is asking for a homepage, ad, one-liner, or scan-first marketing surface, stop and recommend the storybrand skill instead. This skill is for narrative engagement, not direct-response structure.


WRITE MODE

Step 1: Build the Sacred Flaw worksheet (REQUIRED — never skip)

Read references/sacred-flaw.md for the full 8-step worksheet with sentence stems and examples.

If character/brand context is already known in this session, fill in the worksheet from context and only ask when an answer cannot be confidently determined. Otherwise, ask each question. Record all answers before writing any copy.

Who is the "character"? In business storytelling the character is usually:

  • Founder narrative / About page → the founder
  • Case study → the customer
  • Brand origin → the founder OR the brand's first customer
  • Blog hook / long-form sales → either a named protagonist or the reader themselves

The Sacred Flaw approach applies the same way regardless. Pin down ONE character before drafting.

Worksheet steps to complete:

  1. STARTING POINT — milieu, what-if, argument, or character
  2. SACRED FLAW — the flawed theory of control they have made identity-defining
  3. ORIGIN DAMAGE — the specific childhood/early-career scene that built the flaw
  4. PERSONALITY — Big Five lens; what version of the self emerges
  5. HERO-MAKER MOMENT — when the flaw worked; the "superpower" scene
  6. CHARACTERISTIC WORLD — what the flaw gives them; what they fear losing
  7. STORY EVENT — the real-world happening that overwhelms the flaw
  8. PLOT (5 acts) — This is me, it's not working → Is there another way? → I have transformed → Can I handle the pain? → Who am I going to be?

Step 2: Apply to the Output Surface

Read references/surfaces.md for the full applications and templates (it also has a per-surface effort-budget table — worksheet + drafting time by surface).

Available surfaces:

  • Founder narrative / About page — flaw → ignition → transformation arc
  • Case study — customer as flawed hero; product as agent of change
  • Brand origin story — the founder's sacred flaw that produced the company
  • Blog hook / long-form opener — change in the first sentence, curiosity gap, dramatic question
  • Long-form sales page — reader-as-hero, theory of control breaking, "God moment" close

Step 3: Engineer for the brain

Read references/craft-rules.md for the line-level rules:

  • Open with change (or its threat) inside the first sentence
  • Curiosity gap — pose puzzle, plant evidence someone knows
  • Filmic word order (subject → verb → object), active voice
  • Three specific sensory qualities per object (show, don't tell)
  • "Because" between scenes, never "and then"
  • Describe environment to describe character

AUDIT MODE

Read references/audit-checklist.md for the full checklist.

For each failed item: state what specifically is broken, quote the offending copy, and suggest the exact fix.

If the user wants a numeric score, read references/scoring.md.


Troubleshooting

User can't identify the sacred flaw. Walk them through the sentence stems in references/sacred-flaw.md (e.g. "The thing people most admire about me is…", "I'm only safe when I…"). The flaw is whichever answer immediately suggests a suite of behaviours.

User skips the worksheet and wants narrative directly. Do not skip it. Say: "I need 5 minutes of Sacred Flaw answers first — otherwise the story has no engine. Let's go fast." Then ask only what can't be inferred from context.

Character feels flat after drafting. They have no flaw, or the flaw is too generic. Storr: "You'll know when you have it because you'll feel your character lurch alive in your imagination." If you don't feel that, the flaw is wrong.

The arc feels rushed. Probably skipped Act IV (the pain of change). Without it the transformation reads as unearned.

Customer copy: should the brand be the hero? No. In every business application the customer (or founder-as-customer-of-their-own-vision) is the hero. The product is the agent that breaks or rebuilds their theory of control. Storr and StoryBrand agree on this. Brand-as-hero kills the story.

Conflict with the storybrand skill. They don't conflict — they layer. StoryBrand structures the marketing surface. Storytelling deepens character and arc inside that structure. If asked to choose, use StoryBrand for scan-first surfaces (homepage, ad, one-liner) and Storytelling for read-first surfaces (founder story, About, case study, long-form).


Pairing with other skills

  • the storybrand skill for marketing structure (homepage, one-liner, email, CTA, plan). Run first if both apply.
  • the ann-handley skill for voice and quality polish on the draft Storytelling produces.

Typical pipeline for long-form: the storytelling skill (character + arc) → the ann-handley skill (voice + line-edits) → the storybrand skill only if the piece also has to convert.


Examples

Write mode — founder narrative: User: "Use Science of Storytelling to write our founder's About page." Skill: Fills Sacred Flaw worksheet from context → identifies flaw ("I'm only safe when I out-work everyone"), origin damage scene, hero-maker moment, the story event that broke the flaw → drafts About page with change in the first sentence, theory of control front and center, transformation arc that ends in the "God moment" of the company's founding.

Write mode — case study: User: "Write a case study about how our pest control service helped a Phoenix homeowner." Skill: Customer = hero with sacred flaw ("A good host has a perfect house"). Ignition point = pest sighting at a dinner party. Acts I-V map to the engagement timeline. Product appears as the agent that lets the customer rebuild their theory of control on healthier terms.

Audit mode: User: "Audit this About page against Storr." Skill: Loads audit-checklist.md → runs each check → "Opening FAIL — 'Founded in 2014' has no change. Rewrite to open with the moment something broke. Flaw check FAIL — founder is described only by virtues. Storr: a character's value is in their imperfections. Add the flaw that made the company necessary."


Maintained by Pesty Marketing · Browse the full skill catalog.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.