homepage-messaging
From a positioning doc to a homepage: value propositions on the Messaging House, section outline, hero choice, element counts; hands finished lines to…
Skill by renzobianchi
Chalk Labs
Need help deploying homepage-messaging?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code. Read the repository before you give any tool access to your data.
npx agentmarket install skill/renzobianchi-homepage-messaging
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 2, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/homepage-messaging
Tools it pre-approves 6
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Read,Write,WebFetch,AskUserQuestion,Bash(curl*)
What's inside
- Skill name
homepage-messaging- Description
- From a positioning doc to a homepage: value propositions on the Messaging House, section outline, hero choice, element counts; hands finished lines to language-market-fit for voice. Also audits an existing homepage by element.
- License
- MIT
- Allowed tools
- Read,, Write,, WebFetch,, AskUserQuestion,, Bash(curl, *)
- Instructions
- 75 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves some shell commands
Files (6)
- README.md
- SKILL.md
- elements.md · references/
- frameworks.md · references/
- rules.md · references/
- sources.md · references/
SKILL.md (first lines)
# Homepage messaging You turn positioning into what the homepage says, in what order. Most copywriting problems are messaging problems, and most messaging problems are positioning problems, so this skill refuses to write a hero for a product with no positioning doc: `build` needs the doc from `startup-positioning`; `audit` reads a live page and reports which layer is broken. Vocabulary: the messaging elements in [references/elements.md](references/elements.md). Every headline you write or grade is tagged with one. Output of `build` is a **messaging doc**: the Messaging House, the section outline with the element each section leads with, the hero, and a hand-off to `language-market-fit`, which owns the words. This skill decides which element goes where. That skill decides whether the words are the prospect's. ## Mode `build <path>`: read the positioning doc, run phases 1 to 5. `audit <url>`: run the audit at the end of this file. No argument: ask which. ## 1. Purpose and reader Two questions before any structure, in one call to the ask-user tool: - What is the homepage for: explore (marketing-led, convert one persona on a CTA), try (PLG, get a trial), or book a demo (sales-led, establish credibility)? The growth model decides what the hero leads with (marketing-led: maximal clarity on what the product does; PLG: the most compelling capability and the feature behind it; sales-led: credibility beside the capability). - Who reads it: the **ignorant champion**, a senior manager to VP who has the problem and has never heard of you. The executive never reads the homepage; the powerless end user cannot buy (PLG excepted). Closed when both are recorded at the top of the messaging doc. ## 2. Value propositions Three arguments for why the target customer should use the product, each tied to a sub-use case, built on the **Value Proposition Canvas** in [references/frameworks.md](references/frameworks.md): for one persona, answer the seven questions in order (who, what capability, when needed, how done today, what limits that way, what problem results, what outcome). Two checks per value prop: the limitation contrasts sharply with the capability (that contrast is the differentiation), and the benefit directly opposes the problem. Every capability names the feature that powers it. When the product has more than three candidate arguments, score features: biggest problem solved (1 to 5) plus biggest wow factor (1 to 5); the three highest go on the page. Closed when the Messaging House has its top (the positioning doc's one sentence, with one market element and one product element) and three value props, each with all seven answers. ## 3. Section outline Start from the **World's Clearest Homepage Template** and adapt by category maturity and growth model, per the section table in the frameworks reference: hero → problem → solution intro → three value-prop sections at the feature-set level → proof → CTA. Then decide the post-hero section type: How It Works for a new category (capability plus feature), Use Cases for a horizontal product, Features only in a very mature category, Results last and only if forced. Multi-audience or multi-product: pick one persona for the first one to three scrolls and prioritize one product; the others get their own pages. Itemizing every product in the hero or summarizing them into an abstraction are the two ways the hero stops saying anything. Vision and roadmap go on their own page. Closed when every section has the element it leads with, the value prop it carries, and a one-line purpose; and the element counts on the page are within range (personas 1 to 2, problems 1 to 3, category exactly 1, capabilities 1 to 3, features 1 to 5, benefits 1 to 3). ## 4. Hero The hero is the only line guaranteed to be read. It answers what is it, who is it for, what does it let me do; or, in the two-question test, "which of my tools does this replace" or "which task in my job does this help with." Choose the template from the frameworks reference (X for Y, category differentiator, how-to, networker) by market maturity and by which element the positioning doc leads with; then write headline, subhead, and the product visual that goes beside it (real UI, never an illustration). Run the hero and every section headline through [references/rules.md](references/rules.md). Rewrite any line that fails a rule. A line that keeps failing has an abstract claim underneath it; fix the claim in the messaging doc and the wording follows. Closed when a stranger reading only the hero can say what the product does and who it is for. ## 5. Deliver and hand off Write `messaging-<slug>.md`: purpose and reader, the Messaging House, the section outline table, the hero with its template and element tags, the counts check, and what was left off the page and why. Then hand the outline to `language-market-fit compose` with the positioning doc attached: it rewrites each line in the prospect's words and runs the voice gate. Copy is not final until it has passed there. Closed when the messaging doc exists and the hand-off names the exact lines the copy pass must keep as element anchors. ## Audit mode Fetch the page. **Headline audit**: list every headline in order, tag each with its element, note the growth model the CTAs imply. Then grade: 1. Do the headlines alone answer what is it, who is it for, what does it replace, why is it better? Quote the blanks. 2. Which layer is broken: copy (right elements, wrong words → send to `language-market-fit audit`), messaging (wrong element leads, wrong order, counts out of range → this skill's phases 3 and 4), or positioning (no target customer, no alternative, an outcome lead in a mature category → send to `startup-positioning`)? 3. The rules broken, by number, each with the failing line quoted and the rewrite direction. Lead with the biggest problem. End with the one change that would move the most, and which skill does it. ## Guardrails - **Place elements here and send every line to `language-market-fit` for the words.** A hero written in this skill skips the voice gate. - **Lead with the capability and close with the benefit.** The reader sees what it does before believing what it changes; a benefit lead sounds bigger and reads as any vendor's promise. - **Stack elements until the two hero questions are answered, then stop.** A three-word tagline obscures the product; a paragraph makes the reader bounce. - **Keep results and ROI below the fold, and keep benefits first-order.** A fourth-order outcome is a promise every competitor also makes. - **Name features in plain words.** A branded feature is a word the reader has to learn before it means anything. - **Give a multi-persona product one persona for the first scrolls and a page per persona after.** A channel-changer hero speaks to nobody. ## Credits Method distilled from Fletch PMM (Anthony Pierri, Robert Kaminski): the messaging elements, the Value Proposition Canvas, the Messaging House, the World's Clearest Homepage Template, the hero templates and the homepage evaluation counts. Names kept on purpose; [references/sources.md](references/sources.md) maps each part to its post.
From renzobianchi/skills, MIT.
More from renzobianchi/skills
- 0.600score
arena-design
renzobianchi
Design-exploration arena: N parallel candidates with assigned directions attack the same UX+UI problem in Paper, Figma, or code; visual cross-judge, base +…
SkillAFreshness: A★ 2Claude Code +9 - 0.559score
startup-positioning
renzobianchi
Guided positioning interview for a B2B product you do not own: readiness gate, reconnaissance, four interview rounds, candidate strategies with thesis and…
SkillBFreshness: B★ 2Claude Code - 0.559score
gtm-readiness
renzobianchi
Go-to-market audit for a B2B startup: which fit it has (find, sell, serve, retain), which GTM phase it is in, whether the segment is real, and the mistakes in…
SkillBFreshness: B★ 2Claude Code - 0.557score
html
renzobianchi
Build standalone interactive HTML artifacts as the medium for agent↔designer conversation — review docs with approve/deny/discuss, N-way prototype variants…
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
ds-rules
renzobianchi
Rules for building components in a shadcn-based design system with a Figma or Paper kit.
SkillBFreshness: B★ 2Claude Code +9 - 0.554score
ds-patterns
renzobianchi
Post-migration phase: inventory reused layouts, name them in the kit, write rules beside them, run the drift test, set up the product knowledge base and…
SkillBFreshness: B★ 2Claude Code +9 - 0.554score
ds-migrate
renzobianchi
Run one phase of a design-system migration to shadcn (AI-ready): triage, foundations, kit, parity, component <key>, cleanup, steward.
SkillBFreshness: B★ 2Claude Code +9 - 0.547score
ds-help
renzobianchi
Where the migration stands, what blocks it, and the next command.
SkillBFreshness: B★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 2
- Open issues
- 0
- Last commit (this folder)
- Sep 2, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/renzobianchi/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from renzobianchi
- 0.600score
arena-design
renzobianchi
Design-exploration arena: N parallel candidates with assigned directions attack the same UX+UI problem in Paper, Figma, or code; visual cross-judge, base +…
SkillAFreshness: A★ 2Claude Code +9 - 0.559score
startup-positioning
renzobianchi
Guided positioning interview for a B2B product you do not own: readiness gate, reconnaissance, four interview rounds, candidate strategies with thesis and…
SkillBFreshness: B★ 2Claude Code - 0.559score
gtm-readiness
renzobianchi
Go-to-market audit for a B2B startup: which fit it has (find, sell, serve, retain), which GTM phase it is in, whether the segment is real, and the mistakes in…
SkillBFreshness: B★ 2Claude Code - 0.557score
html
renzobianchi
Build standalone interactive HTML artifacts as the medium for agent↔designer conversation — review docs with approve/deny/discuss, N-way prototype variants…
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
ds-rules
renzobianchi
Rules for building components in a shadcn-based design system with a Figma or Paper kit.
SkillBFreshness: B★ 2Claude Code +9 - 0.554score
ds-patterns
renzobianchi
Post-migration phase: inventory reused layouts, name them in the kit, write rules beside them, run the drift test, set up the product knowledge base and…
SkillBFreshness: B★ 2Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get homepage-messaging running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
homepage-messaging skill. Agent Mart. https://agentmart.dev/skills/renzobianchi-homepage-messaging (last updated 2026-10-24)