messaging
Skill3 starsChanged 31 days agoMITView on GitHub
Builds a product messaging library from your positioning, your website and customer evidence: a description, the status quo and alternatives, pain points with their knock-on consequences, capabilities, functional, emotional and social benefits, branded features, the cost of doing nothing, common objections with responses, and core messaging blocks (tagline, elevator pitch, value props, proof, per-audience lines). Every claim sourced. Triggers: "product messaging", "messaging library", "messaging framework", "value props", "capabilities and benefits", "what are our differentiators in words". Run after /positioning. Not for choosing the position itself (use /positioning).
16 other projects use a version of this, 2 of them edited.
Adopted by
Most recently taken up by
- codewithmukesh/dotnet-claude-kittheir own version, first seen Nov 8, 2026
- matteotitta/repo-structure-agencyword for word, first seen Nov 8, 2026
- matteotitta/claude-code-marketing-quickstartedited, first seen Nov 1, 2026
- vercel-labs/marketing-team-eve-templatetheir own version, first seen Oct 23, 2026
- matteotitta/repo-structure-in-houseedited, first seen Oct 15, 2026
- akachandan1/proofstacktheir own version, first seen Oct 11, 2026
Used with
Projects with it also use level, authentication and 3 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.
dachi-jp3Skilllevel
表示レベル(auto / low / medium / high)を切り替える。
Also in 3 projects that use this
MicrosoftSkillauthentication
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
JohnJBorenSkillci-cd
CI/CD pipeline design, GitHub Actions, testing automation, and deployment strategies
Also in 3 projects that use this
wrsmith108Skilldocker
Container-based development for isolated, reproducible environments. Use when running npm commands, installing packages, executing code, or managing project dependencies. Trigger phrases include "npm install", "run the build", "start the server", "install package", or any code execution request.
Also in 3 projects that use this
NVIDIASkilltesting
Run Python and Rust tests for physicsnemo-curator using uv + pytest with coverage reporting via pytest-cov, and cargo-nextest for Rust tests. Includes benchmark workflows with pytest-benchmark and criterion.
Also in 4 projects that use this
Other versions16 projects use a version of this.
Word for word · 1
- matteotitta/repo-structure-agency★ 1100% same
Edited · 2
- matteotitta/claude-code-marketing-quickstart★ 7095% same
- matteotitta/repo-structure-in-house★ 7095% same
Wrote their own version · 13
- codewithmukesh/dotnet-claude-kit★ 808same name
- vercel-labs/marketing-team-eve-template★ 459same name
- Resgrid/Core★ 238same name
- joelhooks/joelclaw★ 65same name
- crisandrews/ClawCode★ 64same name
- GTMify/aigtm★ 25same name
- epode-studio/crosstalk★ 8same name
- fullymiddleaged/Clawness★ 5same name
- pluginagentmarketplace/custom-plugin-backend★ 4same name
- buildingwithai/skills★ 1same name
3 more not listed
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 repository10 other files it gives its agents.
- brand-kitSkill
- company-contextSkill
- competitor-researchSkill
- expert-povSkill
- funnel-strategySkill
- goalsSkill
- icp-researchSkill
- positioningSkill
- tov-guidelinesSkill
- win-lossSkill
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 6 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
6
Distinctive
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
- Distinctive: line 22
Before rewriting the website, a sales deck or a launch.
- Distinctive: line 23
When sales, marketing and product describe the product three different ways.
- Very specific: line 25
Don't use it to choose the position (/positioning), or for a single-feature question you can answer directly.
- Distinctive: line 31
Recommended: read these first if they exist:
- Very specific: line 40
Paths: Write to context/messaging/MMYY-messaging.md.
- Distinctive: line 59
Link it up: Every pain points to a capability, every capability to a feature and a benefit.
- Very specific: line 60
Verify: Check each claim against its source.
- Distinctive: line 70
All ten components present, or marked "not available" with a reason.
- Distinctive: line 71
No pain point stops at the first-order problem.
“Common” is measured: kept by at least 6 in 10 of the 11 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.
Files
Messaging
Turn the position into the words people will actually use: on the website, in sales calls, in emails and ads. The library links each pain to a capability, each capability to a benefit, and each benefit to proof, so any writer can pull a line and know it holds up.
When to use it
- Right after
/positioningis agreed. - Before rewriting the website, a sales deck or a launch.
- When sales, marketing and product describe the product three different ways.
Don't use it to choose the position (/positioning), or for a single-feature question you can answer directly.
Inputs
Required: the website URL and the exact product name. Confirm the name if it's ambiguous.
Recommended: read these first if they exist:
context/positioning/, the primary input, which frames everythingcontext/icp/for pains and voice of customercontext/competitors/for the status quo and contrastscontext/win-loss/for real objectionscontext/brand/for tone of voice
Also useful: internal docs and customer quotes. If positioning is missing, say so and offer /positioning first.
Paths. Write to context/messaging/MMYY-messaging.md. Agency or consultant? Swap context/ for clients/<client>/context/ throughout.
Tools. Page fetching for the site; web search for reviews, testimonials and comparison pages. Exa or Firecrawl if you have them.
Steps
- Validate inputs and load the upstream context.
- Research. Fetch at least five core pages (home, features, pricing, customers, about) with URLs and dates. Search reviews and testimonials. Record branded feature names exactly as the company writes them.
- Extract the ten components, in order:
- Description. What it is, in one or two sentences, using the positioning.
- Status quo and alternatives. Doing it by hand, plus at least one named alternative.
- Pain points. Each with a consequence chain: the first-order problem, what it causes, what that costs the business.
- Capabilities. What the product does about each pain.
- Functional benefits. The outcome, each backed by a verbatim customer quote or marked "not available".
- Emotional and social benefits. Two of each: how the buyer feels, and how they look to their boss and team.
- Features. The branded names that deliver each capability.
- Cost of inaction. What not acting costs per week or month, in numbers where you can.
- Objections. 3 to 5, each with its root cause and a response that acknowledges, reframes and gives evidence.
- Core messaging blocks. A tagline of 7 words or fewer, a one-sentence elevator pitch, a 3-bullet value prop, a lead proof point, and one line per audience segment.
- Link it up. Every pain points to a capability, every capability to a feature and a benefit.
- Verify. Check each claim against its source. Quotes are verbatim. Tag confidence
[VERIFIED],[INFERRED],[ESTIMATED]or[UNAVAILABLE]. For a client-facing library, aim for at least 60% verified and no more than 10% estimated. - Write the data gaps and how to fill each one.
- Hand off to
/funnel-strategy, and to any copy work.
Output shape
Title it # Product messaging library: [Product]. Open with a TLDR and one block of open questions. Then the ten components in order, a data gaps section, and a source list with URLs and access dates.
What good looks like
- All ten components present, or marked "not available" with a reason.
- No pain point stops at the first-order problem.
- The cost of inaction has a number, not an adjective.
- The tagline and pitch match the agreed position. If they don't, flag it rather than drifting.
- A seller could answer the top three objections using only this file.
Mistakes to avoid
- Feature lists dressed up as benefits.
- Invented customer quotes or made-up metrics.
- Messaging that contradicts the positioning because a line sounded better.
- Buzzwords where a plain verb would do.
- Repeating the same caveat in every component. Say it once.
Chain
Step 9 of the suggested chain: /company-context → /icp-research → /competitor-research → /win-loss → /expert-pov → /tov-guidelines → /brand-kit → /positioning → messaging → /funnel-strategy → /goals.
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.

