conversion-storytelling
Skill1 starsChanged 42 days agoMITView on GitHub
Shapes truthful product narratives, message maps, proof, and CTAs for websites, landing pages, pricing, checkout, onboarding, and app flows, and adapts approved stories to video, thumbnail, and social briefs. Use when a surface must move a qualified audience to a credible next action without losing SEO, accessibility, or truth.
In this repository6 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 22
Framework, only if useful: read framework-selection.md.
≈ “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
Conversion Storytelling
Build a clear path from the audience's current state to a credible next action. Frameworks are hypotheses, not guarantees.
Precedence: user instructions and confirmed product truth → safety, privacy, legal truth, accessibility, platform rules → existing evidence, search intent, analytics, healthy conventions → this skill. Never silently replace the user's chosen framework; raise a risk only when it affects truth, safety, scope, or the outcome.
SEO is a release gate for public indexable surfaces: no change may remove crawlable meaning, distinct intent, evidence, metadata, internal links, or URL continuity. Offer an SEO-safe alternative instead of a waiver, unless the user makes the surface private or non-indexable.
Context gate
Extract what the prompt, files, links, assets, and repo already give. Ask one to three grouped questions only for blocking gaps (audience, product truth, strategy, format, safety, outcome). For a fast or authorized draft, state reversible assumptions and proceed. Never assume claims, customer evidence, legal status, results, or private facts.
Workflow
- Brief: audience, awareness, pain or desired progress; offer, mechanism, next action, user and business outcome; approved proof, objections, tone, prohibited claims; surface, entry context, format, constraints; current content, URLs, queries, baseline. Websites add primary task, friction, screens, device, accessibility, SEO; media adds placement, duration or size, viewer state, assets, CTA. Collect only what decides the work.
- Audit an existing surface first: hierarchy, semantic content, URLs, metadata, internal links, proof, CTA paths, funnel data. Keep what performs until evidence says otherwise.
- Framework, only if useful: read framework-selection.md. One primary spine per surface, at most one behavior diagnostic (behavior-and-decision-design.md for activation, onboarding, checkout friction, high-consideration decisions) and one execution audit. Never default to StoryBrand or force marketing prose into functional UI.
- Message map: present state, desired progress, problem, stakes, mechanism, proof, objections, plan, success, primary and secondary CTA, disqualifiers—each marked
approved,supported,needs evidence, orprohibited. - Surface: websites, apps, pricing, checkout, onboarding → page-execution.md. Video, thumbnails, social → content-adaptation.md.
- Truth and measurement: proof-and-measurement.md. Never fabricate testimonials, metrics, customers, scarcity, urgency, guarantees, or case studies; never promise uplift from a framework.
Output
- Brief, assumptions, open decisions. 2. Framework or strategy basis (plus material rejected options when a framework was chosen). 3. Message map and proof ledger. 4. Surface plan with hierarchy and CTA roles. 5. Quality, accessibility, and truth checks. 6. Measurement plan and implementation boundary.
Websites add flow outline, interaction states, responsive direction, and SEO preservation map. Video adds concept, hook, beats or script, scene/audio/caption direction, CTA timing. Thumbnails and static creative add composition, text hierarchy, small-size readability, export constraints. Social adds platform adaptation, copy structure, visual direction, CTA.
Companions (optional; suggest when missing)
product-architecture-and-development for implementation, ai-assisted-product-development for AI exploration and review loops, content-marketing-and-brand-growth for campaigns and publishing, global-discovery-browsing-extraction for audience, competitor, and search evidence, and the relevant UI, image, animation, or video skill for production.
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.

