agentleFS
fullymiddleagedfullymiddleaged/Clawness/skills/messaging/SKILL.md

messaging

Skill5 starsChanged 4 months agoMITView on GitHub

Write or rewrite the product's customer-facing copy — landing page, hero section, CTAs, onboarding, empty states, pricing, app-store and marketing pages — with the customer as the hero and the product as their guide. Scans the existing UI copy, drafts a one-page message brief (who the customer is, what they want, the problem in their words, the plan, the call to action, what's at stake, what success looks like), and stops for approval before changing any copy. Use when asked to improve marketing or UI copy, write a landing page, sharpen a value proposition, or when copy talks about the product instead of the customer.

16 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use tov-guidelines, icp-research and 6 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.
  • matteotittaSkill

    tov-guidelines

    Analyzes existing client content (website, blog, social, docs) to extract voice patterns, vocabulary preferences,

    Also in 4 projects that use this

  • growthack88Skill

    icp-research

    Scrapes case studies, testimonials, and solutions pages from a target website to build structured ICP documentation. Produces TAM analysis, firmographic segments, champion and economic buyer personas, use case mapping, customer proof points, and voice-of-customer synthesis with normalized attributes. Requires website URL as primary input. Upstream: recommended company-context. Downstream: feeds positioning, product-messaging, landing-page-copy, content-strategy, and outreach-emails.

    Also in 4 projects that use this

  • dachi-jp3Skill

    level

    表示レベル(auto / low / medium / high)を切り替える。

    Also in 3 projects that use this

  • YepAPISkill

    competitor-research

    Competitive analysis between domains using YepAPI.

    Also in 4 projects that use this

  • MicrosoftSkill

    authentication

    Wire this in whenever the app uses or connects to data — records, a database, entities, per-user data, row-level security — or when the user wants sign-in, accounts, login, or protected pages. Rayfin data is always accessed as an authenticated user, so **data implies auth**; only a static page over public data skips it. The starter ships as a no-auth "hello world" that previews with no backend, and the full Fabric auth scaffolding is already in the project — this skill wires it in: AuthProvider + bootstrapAuth in main.tsx, the route guard in App.tsx, the sign-in page, sign-out, and the env/deploy requirement. Triggers: auth, authentication, sign in, sign-in, login, log in, sign out, logout, account, user, identity, protect route, require login, gated page, data, database, records, per-user, row-level security, who is the current user, Fabric auth, Entra.

    Also in 3 projects that use this

  • JohnJBorenSkill

    ci-cd

    CI/CD pipeline design, GitHub Actions, testing automation, and deployment strategies

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 7

    Distinctive

    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
  1. Distinctive:

    Not the product name, not a pun.

    line 72
  2. Distinctive:

    Keep the existing design system, components, and i18n keys.

    line 81
  3. Distinctive:

    Don't make the product the hero ("We're the leading…").

    line 94
  4. Distinctive:

    Don't invent testimonials, stats, logos or customer counts.

    line 95
  5. Distinctive:

    Don't stack primary CTAs, or use clever wording where clear wording works.

    line 97
  6. Distinctive:

    Don't change copy before the brief is approved, even when auto-invoked.

    line 98
  7. Distinctive:

    Don't restructure layouts or swap components to fit a template.

    line 99

“Common” is measured: kept by at least 6 in 10 of the 12 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

Customer-as-hero messaging

Most product copy describes the product: its features, its stack, its history. People skim past that, because they're looking for their own problem. This skill rewrites copy as a short story where the customer is the hero, the product is the guide that helps them win, and every screen answers "what's in it for me?" within a few seconds.

Say this before you start. Copy changes are visible to every user. Whether the user typed /clawness:messaging or you reached for this skill yourself: scan, draft the brief, and stop for approval before editing any copy.

Argument

/clawness:messaging [surface]. The surface is what to work on: landing, onboarding, pricing, empty-states, a route, or a file. With no argument, find the highest-traffic surface (usually the landing page or first-run screen) and propose starting there.

The brief (seven parts, one line each)

PartQuestion it answersBad sign
HeroWho is the customer, and the ONE thing they want here?"Everyone"; several wants
ProblemWhat's in their way: the external obstacle, how it makes them feel, why it's unfairOnly the external problem; nobody buys a fix for a feeling they weren't shown
GuideWhy trust us: empathy ("we get it") plus proof (numbers, logos, reviews)Bragging with no empathy, or empathy with no proof
PlanThree or fewer steps from where they are to using itA feature list instead of steps
Call to actionOne direct CTA ("Start free") plus one low-commitment one (a guide, a demo)Several competing primary buttons; "Learn more" as the only CTA
StakesWhat it costs them to do nothingFear-mongering, or nothing at all
SuccessTheir life after: concrete, visual, specific"Unlock your potential"

The brief is the deliverable that matters. Copy is just the brief applied to a screen.

Steps

1. Scan the existing copy

Find where copy lives: route files and components for hero sections and CTAs, i18n message catalogs (the best source: every user-facing string in one place), CMS or Markdown content, <title>/meta descriptions, app-store listings. Read the README and any docs for who the product is for. Collect the current headline, subhead, primary CTA, and section headings for the surface.

2. Draft the brief, then stop

Fill the seven-part table from what the code and docs actually say. Where they don't say, don't invent customers or proof: ask. A testimonial, a stat, or a customer count you can't find in the source isn't proof, it's fabrication. Present:

  • the brief,
  • a before/after for the headline, subhead and primary CTA,
  • the files you'd change.

Edit nothing until the user approves.

3. Apply it to the surface

  • Headline: what the customer gets, in their words. Readable in five seconds. Not the product name, not a pun.
  • Subhead: the problem it solves, or the plan in one line.
  • Primary CTA: one, repeated at the top and the end of the page and in the header. A verb plus the outcome ("Start my free trial"), never "Submit" or "Learn more".
  • Sections: problem → guide (empathy + proof) → plan (≤3 steps) → success → stakes, then the CTA again. Trim anything that serves none of these.
  • UI copy: empty states name the next step and its payoff ("No projects yet: create one to see your first report in a minute"). Onboarding is the plan. Error messages say what to do next, not what went wrong internally.
  • Keep the existing design system, components, and i18n keys. Change strings, not structure, unless the user approved a structural change.

4. Verify

  • Grep each changed string back to confirm it landed where intended and that every locale's catalog is updated (or flagged for translation).
  • Five-second test: read only the headline, subhead and CTA. Can you say what's offered, why it matters, and what to do next? If not, rewrite.
  • Report what changed, with before/after for the headline and CTA.

Don't

  • Don't make the product the hero ("We're the leading…"). The customer is.
  • Don't invent testimonials, stats, logos or customer counts. Proof comes from source or from the user.
  • Don't stack primary CTAs, or use clever wording where clear wording works.
  • Don't change copy before the brief is approved, even when auto-invoked.
  • Don't restructure layouts or swap components to fit a template. Fit what's there.

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.