> ## Documentation Index > Fetch the complete documentation index at: https://docs.tastelabs.com/llms.txt > Use this file to discover all available pages before exploring further. # Skills > Install the Taste Engine agent skills into your coding agent A **skill** is a package of instructions that teaches your AI agent how to use the Taste Engine well. Where the [MCP server](/ai-tools/mcp) gives your agent the tools, a skill gives it the judgment. Two skills ship today: `brand-search` finds real design references before the agent commits to a visual direction, and `brand-adherence` builds a page inside an existing brand's identity, then verifies the result instead of trusting its own eyes. Skills follow the open [`SKILL.md`](https://github.com/vercel-labs/skills) standard, so the same skill works across Claude Code, Codex, Cursor, OpenCode, Gemini CLI, and other agents that support it. ## Install Install with the `skills` CLI. No global install is needed: `npx` runs it on demand. ```bash theme={null} # Install both skills into every coding agent the CLI detects on your machine npx skills add Taste-AI/skills ``` A few variations: ```bash theme={null} # Preview the skills in the repo before installing npx skills add Taste-AI/skills --list # Install a single skill by path npx skills add github.com/Taste-AI/skills/tree/main/skills/brand-search npx skills add github.com/Taste-AI/skills/tree/main/skills/brand-adherence ``` You can also install manually by copying a skill folder into your agent's skills directory: ```bash theme={null} # Claude Code (project- or user-scoped) cp -r skills/brand-search ~/.claude/skills/ cp -r skills/brand-adherence ~/.claude/skills/ # Codex cp -r skills/brand-search ~/.agents/skills/ cp -r skills/brand-adherence ~/.agents/skills/ ``` ## Connect the MCP server first `npx skills add` installs the **instructions**, not the tools. The skills drive the Taste Engine MCP tools for search, extraction, and verification, so they only work once the [MCP server](/ai-tools/mcp) is connected. For example, with Claude Code: ```bash theme={null} claude mcp add --transport http taste-engine https://mcp.tastelabs.com/mcp ``` If your agent does not see the tools, the MCP server is not connected. See [MCP server](/ai-tools/mcp) for setup in Codex, Cursor, and other clients. ## What the skills do ### Find references with `brand-search` The `brand-search` skill triggers whenever your agent needs website design references: you describe a style or mood ("dreamy editorial skincare, calm and warm"), name reference sites ("layout of linear.app, colors of ramp.com"), ask for brands that look like an existing site ("competitors of acme.com"), or ask for a website with no visual direction at all ("build a website for my bakery"). Instead of inventing a look, the agent grounds its design decisions in real websites from the curated corpus, in four moves: * **Pick the right search tool.** A description becomes a `search_brands` query. A brand you already have becomes a `search_similar_brands` call on its extraction: the agent reuses an existing `submission_id`, or extracts the site first when it only has a URL. Sites you name are extracted directly, since they are already the reference. An unqualified site ("sites like patagonia.com") gets both lenses: its visual neighbours from `search_similar_brands`, and its cultural neighbourhood from a `search_brands` query anchored in what the site is about. * **Search what the prompt says, not what the agent assumes.** The query is built from the words you wrote: industry, page type, audience, named references, and any style, layout, or palette terms. Your style words travel verbatim ("vintage" stays "vintage", even where the corpus tags that register "retro"), and the agent adds no adjectives you never used. When the prompt names no style, the query names none either, and the results propose the directions. Empty adjectives ("completely custom and unique") are dropped, and the one real fact left is what gets searched. * **Inspect every result, in order.** Results come back ranked, and every card is mandatory evidence, including the [discovery results](/concepts/brand-search#the-corpus) that widen the set. For each one the agent reads the metadata and description and views the screenshot, in the returned order, before choosing references. It never re-ranks on a hunch: claims about motion or interaction get checked on the live site, and a result is set aside only with a stated mismatch against your prompt. * **Extract only when it needs to.** A card's metadata, description, and screenshot are usually enough to judge a reference, and often enough to design from. The agent runs `extract_brand` when it will build directly from a source and needs its real values, or when it needs a `submission_id` to feed `search_similar_brands`. It polls to completion, reads the result, and replaces any failed extraction with the next ranked result from the same query. The skill asks for six results per query by default and raises `top_k` (up to 12) when you want a broad moodboard. [Find inspiration](/use-cases/find-inspiration) walks the same search, pick, extract workflow over the HTTP API. ### Ship on-brand pages with `brand-adherence` The `brand-adherence` skill triggers when you name one reference site and ask for a page inside its identity: "a pricing page for stripe.com", "a careers page in linear.app's system", "as if their design team built it". It ships that page as if the brand's own team shipped it, in three moves: * **Pull the whole brand, exactly.** The agent pulls the extraction a few sections at a time, saves each answer to disk, and copies values out of those files when it writes code: exact hex, exact type specs, exact CSS, with no transcription from memory. It also downloads the captured CSS, HTML, and screenshot, which carry the real font-loading rules, the real logo, and the honest picture of the brand's density and mood. * **Compose inside hard rules.** Every color traces to a brand token, only the brand's typefaces load, and every component is built from the brand's own CSS. Layout, hierarchy, and copy are the agent's latitude; the tokens are not. * **Verify with the Verifier, twice.** Once the page is on a URL the engine can reach, the agent runs a [brand-adherence check](/use-cases/brand-adherence), applies the fixes and recommendations, re-verifies, and closes with both scores side by side. You decide whether another round is worth it. The Verifier extracts both sides from their URLs, so the finished page needs a URL the engine can reach. A page served only on localhost is invisible to it. ## Available skills | Skill | What it does | | ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `brand-search` | Find real design references before designing. Searches the brand corpus by described aesthetic, or finds brands visually similar to an extraction, and inspects every result before choosing. | | `brand-adherence` | Ship a new page for a brand that already exists, as if that brand's own team shipped it. Builds from the extraction's verbatim tokens, fonts, components, and assets, then grades the result with the adherence verifier. | The two chain naturally: `brand-search` finds and extracts the reference, and `brand-adherence` builds inside it. The catalog lives in the [`Taste-AI/skills`](https://github.com/Taste-AI/skills) repository and grows over time. Run `npx skills add Taste-AI/skills --list` to see the current set. ## Next steps Connect the tools the skills rely on. The search, pick, extract workflow the `brand-search` skill runs. The verify, fix, re-verify pattern the `brand-adherence` skill runs.