AGENT SKILL

positioning

Use when working out what a product is, who it's for, and what it competes with: the market alternatives, the ideal customer, the differentiators worth claiming, and the positioning statement that follows.

License 许可
Apache-2.0
所属仓库
vercel/eve
最近更新
2026-11-15
Stars
★ 5.9k
Forks
656

01 前言 Front Matter

description
Use when working out what a product is, who it's for, and what it competes with: the market alternatives, the ideal customer, the differentiators worth claiming, and the positioning statement that follows.

02 资源文件 1

03 SKILL.md 正文

Positioning

Positioning is not a tagline. It's a decision about which market you're in and who you're beating, and the words come last. Work it in order, because each step constrains the next.

  1. What would this customer do if the product didn't exist? That's the real alternative, and it is often a spreadsheet, a contractor, an intern, or nothing at all rather than a competitor.
  2. What can you do that those alternatives can't? Only features that are actually hard to copy count here.
  3. What is the value that follows from those features, stated as something a customer gets rather than something the product has?
  4. Who cares most about that value? Not everyone who could use it: the segment that feels its absence most.
  5. What market does that put you in? The category the customer already searches, or a new one you have to teach.

Get 1, 2, and 4 right and the statement writes itself. Skip to the statement and you get something true of every product in the category.

Choosing the alternative you beat

The alternative determines everything downstream, and picking the wrong one is the most expensive error available. Positioning against a well-funded incumbent when your customers actually arrive from a spreadsheet means your messaging answers questions nobody is asking.

Ask the user directly what the last few customers used before, and take the most common answer over the most flattering one.

What counts as a differentiator

A differentiator survives three tests. It has to be true, provable, and hard to copy. Fail any one and it isn't yours to claim.

  • True: the product actually does it today, not on the roadmap.
  • Provable: you can point at a customer, a number, a demo, or a doc.
  • Hard to copy: a competitor can't ship it next quarter. Being cheaper is rarely defensible; being architecturally different usually is.

Things that feel like differentiators and aren't: being easy to use, caring about customers, being fast, having a modern interface, being AI-powered. Every competitor claims all of these, so claiming them positions you nowhere. If a competitor's site would say the same sentence, delete it.

Segments

A segment is useful when its members share a problem, a budget, and a way of finding you. "Mid-market" is a size, not a segment. "Series B companies whose finance team still closes the books in spreadsheets" is a segment, because it predicts the problem, the buyer, and the search.

Pick the narrowest segment that can still support the business. Broad positioning feels safer and converts worse, because a message addressed to everyone sounds addressed to no one.

The statement

One paragraph, internal, written to be checked rather than published:

For [segment] who [situation and problem], [product] is a [category] that [key benefit]. Unlike [the real alternative], it [the differentiator, with proof].

Then test it. Would a competitor's marketing team write the same sentence? Could a customer disagree with it? Does it name something you can prove? If any answer is wrong, the problem is upstream in the five questions, not in the wording.

references/frameworks.md has the fuller worked structure, a positioning-map format for handing back a competitive picture, and the failure patterns worth recognizing.

Leaving it unresolved

Sometimes the honest output is that the positioning isn't settled: the differentiator is unproven, or two segments are pulling in different directions. Say that. Write the options and what evidence would decide between them, rather than picking one and presenting it as concluded. The team can work with a stated question; it can't recover from confident guessing.

04 同仓库更多 Skills

vercel
vercel/eve

writing-quality

The review rubric: writing-quality rules and reference lists for judging a content draft, covering AI-sounding phrasing, bloated wording, structure, and web-content specs. Load at the start of every review.

★ 5.9k
vercel
vercel/eve

writing-quality

Writing-quality guardrails for any prose the agent drafts or edits: blog posts, page copy, Notion drafts, release notes, marketing text. Use this skill whenever writing or revising content meant for humans to read, to keep the prose natural, plain, and free of AI-sounding phrasing. Not needed for code, queries, or structural CMS work.

★ 5.9k
vercel
vercel/eve

seo-aeo-best-practices

SEO and AEO best practices for metadata, Open Graph, sitemaps, robots.txt, hreflang, JSON-LD structured data, EEAT, and content optimized for search engines and AI answer surfaces. Use this skill when implementing page SEO, technical SEO, schema markup, international SEO, AI-overview readiness, or improving content for Google, ChatGPT, Perplexity, and similar assistants.

★ 5.9k
vercel
vercel/eve

sanity-best-practices

Sanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, Sanity Functions, Blueprints, and framework integrations such as Next.js, Nuxt, Astro, Remix, SvelteKit, Angular, Hydrogen, and the App SDK. Use this skill whenever working with Sanity schemas, defineType or defineField, GROQ or defineQuery, content modeling, Presentation or preview setups, Sanity-powered frontend integrations, Sanity Functions, documentEventHandler, defineDocumentFunction, defineMediaLibraryAssetFunction, @sanity/functions, @sanity/blueprints, sanity.blueprint.ts, event-driven content automation, or when reviewing and fixing a Sanity codebase.

★ 5.9k
vercel
vercel/eve

portable-text-serialization

Render and serialize Portable Text to React, Svelte, Vue, Astro, HTML, Markdown, and plain text. Use when implementing Portable Text rendering in any frontend framework, building custom serializers for non-standard block types, converting Portable Text to HTML strings server-side, converting Portable Text to Markdown, extracting plain text from Portable Text, or troubleshooting rendering issues with marks, blocks, lists, or custom types.

★ 5.9k
vercel
vercel/eve

portable-text-conversion

Convert HTML and Markdown content into Portable Text blocks for Sanity. Use when migrating content from legacy CMSs, importing HTML or Markdown into Sanity, building content pipelines that ingest external content, converting rich text between formats, or programmatically creating Portable Text documents. Covers @portabletext/markdown (markdownToPortableText), @portabletext/block-tools (htmlToBlocks), custom deserializers, and the Portable Text specification for manual block construction.

★ 5.9k