StyleSeed UI Component Generator

VerifiedCaution

Generates a new UI component following StyleSeed design conventions, resolving the registry and reading the React/Tailwind v4 implementation context.

Sby Skills Guide Bot
DevelopmentIntermediate
9/13/2026
Claude CodeCodex
#react#design-system#tailwind#component-generator#ui-components

Recommended for

Automated summary

Generates a new React UI component that follows StyleSeed design conventions, after resolving and checking the project's artifact registry.

Strengths

  • Enforces a specific structure: `function` declarations, `data-slot` attributes, the `cn()` utility, `React.ComponentProps<>` typing, and CVA for variants
  • Checks the registry or legacy lock first and explicitly refuses to fall back to the global bundle or recreate `STYLESEED.md`
  • Reads a nearby existing primitive to reuse the project's real API, tokens, and import paths
  • Bans inline hex colors in favor of semantic tokens like `bg-card` and `text-foreground`

Limitations

  • Assumes an already-configured React/Tailwind v4 component system with StyleSeed; not usable otherwise
  • Depends on an external `resolve-context.mjs` script whose failure or invalid configuration blocks generation
  • The instructions cut off mid-sentence on the spacing scale, so the exact spacing rules are not fully spelled out
When to use it

Use it when adding a single new component to a React project that already follows StyleSeed conventions.

When not to use it

Avoid it for full-page scaffolding, composed multi-component patterns, or small tweaks to an existing component.

Security analysis

Caution
Quality score88/100

The skill uses powerful tools (Bash, Write, Edit) for legitimate scaffolding work: it runs a read-only context-resolution script, may regenerate compiled bundles, and writes UI component files within the project. There is no destructive command, no network exfiltration, no base64 payloads, and no safety-disabling instruction. The only residual concern is that it invokes a Node script located in a separately installed skill directory, which is normal but worth noting; overall this warrants 'caution' rather than 'safe' due to write/exec capability.

Findings
  • •Declares Bash and Write/Edit, allowing execution of a Node script and filesystem modification within the project
  • •Executes `node "<ss-resolve>/scripts/resolve-context.mjs"` from an externally-resolved skill directory, so the script path is trusted from the installed skill rather than the project
  • •Writes and edits component source files, but scoped to the project's component directory
How this analysis is made

Examples

New badge component
/ss-component status-badge A small pill badge that shows one of: active, pending, failed, using semantic color tokens and CVA variants.
Card with variants
/ss-component info-card Generate a card component with a default and a compact variant, supporting className overrides and a data-slot attribute, reusing the project's existing card primitive if it fits.
Component in a shared artifact
/ss-component avatar-circle Create an avatar component for the dashboard artifact; resolve and check the registry context first and report any missing tokens before writing files.

name: ss-component description: Generate a new UI component following the StyleSeed design conventions argument-hint: "[component-name] [description]" allowed-tools: Read, Write, Edit, Grep, Glob, Bash

UI Component Generator

Registry-first artifact boundary

If either .styleseed/project.json or .styleseed/artifacts/index.json exists, require a complete, valid registry. Resolve the requested artifact ID before writing a component; ask for scope if it is ambiguous. Never fall back to the global legacy bundle, create STYLESEED.md, or restart setup because a registry is incomplete, invalid, or has no compiled output.

Locate the installed ss-resolve skill directory (shown as <ss-resolve> below), then run this read-only check from the target project root with the active agent (codex, claude, etc.):

node "<ss-resolve>/scripts/resolve-context.mjs" --project-root . --artifact <artifact-id> --agent <agent> --check

For a valid registry with missing or stale compiled output, run the same command without --check, then check again. Stop on invalid configuration or installation errors; do not change approved selections to make the check pass. After success, read only the selected .styleseed/bundles/<artifact-id>.md and .styleseed/manifests/<artifact-id>.json as the compiled method and provenance. A shared component affecting multiple artifacts requires resolving and checking each affected artifact separately, not merging their bundles.

Legacy projects use the following path only when neither registry file exists. Preserve STYLESEED.md; if it is missing, use setup before component code.

node "<ss-resolve>/scripts/resolve-context.mjs" --project-root . --from-lock STYLESEED.md --agent <agent> --check

For missing or stale legacy output, run the same command without --check, then check again. Read .styleseed/effective-rules.md and .styleseed/manifest.json only after success.

When NOT to use

  • For full-page scaffolding → use /ss-page
  • For composed multi-component patterns → use /ss-pattern
  • For tweaking an existing component — just edit the file directly
  • For projects without a configured StyleSeed React/Tailwind v4 component system

Generate a new component: $0 Description: $ARGUMENTS

Instructions

  1. Apply the registry/legacy boundary above, then read the actual implementation context:

    • For a registry artifact, start from its implementation.sourceRoots and implementation.tokenFiles. For legacy projects, discover the existing component and stylesheet entry points from the project source.
    • Follow the active stylesheet imports to the token definitions and recipe helpers used by this artifact. css/theme.css and css/recipes.css are examples, not required locations.
    • Read an existing nearby primitive (such as the project's button) and its real imports, props, variants, and states. Reuse an existing component when it already fits the request.
    • Preserve the project's approved tokens and component API. If required context is missing or unsupported, report the gap before inventing files, aliases, tokens, or replacements.
  2. Follow these conventions strictly:

    • Use function declaration (not const)
    • Add data-slot="component-name" attribute
    • Use the project's existing cn() utility and verified import path for className merging
    • Use React.ComponentProps<> for prop typing
    • Always support className prop for overrides
    • Use CVA (class-variance-authority) if the component has variants
    • Use semantic color tokens (bg-card, text-foreground) — never inline hex
  3. Design token usage:

    • Colors: text-foreground, bg-card, text-brand, text-muted-foreground, border-border
    • Pattern surfaces: ss-pattern-surface; insets/controls/icons use the matching ss-* class
    • Primitives use the project token scale; do not hardcode one radius or shadow personality
    • Spacing follows one repeatable selected-recipe rhythm
    • Motion: duration-[var(--duration-fast)], ease-[var(--ease-default)]
  4. Typography rules:

    • Display (36-48px): leading-none tracking-[-0.02em]
    • Heading (18-24px): leading-snug tracking-[-0.01em]
    • Body (14-17px): leading-normal (default tracking)
    • Caption uppercase (10-13px): tracking-[0.05em]
    • Use size-* shorthand instead of w-* h-*
    • Use ms-*/me-* instead of ml-*/mr-* (logical properties)
  5. Accessibility requirements:

    • Minimum touch target: 44x44px (min-h-11 min-w-11)
    • Support aria-* attributes passthrough
    • Use focus-visible:ring-2 focus-visible:ring-ring for keyboard focus
    • Respect prefers-reduced-motion for animations
  6. Export the component as a named export (not default)

  7. Place the file in the existing component directory established in step 1, inside the affected artifact's implementation scope. src/components/ui/ is a common layout, not a path to create in every project. Route composed patterns to /ss-pattern.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/styleseed-ui-component-generator-mtz9jr5h/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/styleseed-ui-component-generator-mtz9jr5h' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/styleseed-ui-component-generator-mtz9jr5h/download' --output '.skill-downloads/styleseed-ui-component-generator-mtz9jr5h/SKILL.md.part' && mv '.skill-downloads/styleseed-ui-component-generator-mtz9jr5h/SKILL.md.part' '.skill-downloads/styleseed-ui-component-generator-mtz9jr5h/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): Read, Write, Edit, Grep, Glob, Bash

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/styleseed-ui-component-generator-mtz9jr5h/SKILL.md' && test -s '.skill-downloads/styleseed-ui-component-generator-mtz9jr5h/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/ss-component' && cp -R '.skill-downloads/styleseed-ui-component-generator-mtz9jr5h' '.claude/skills/ss-component'

Codex
test -f '.skill-downloads/styleseed-ui-component-generator-mtz9jr5h/SKILL.md' && test -s '.skill-downloads/styleseed-ui-component-generator-mtz9jr5h/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/ss-component' && cp -R '.skill-downloads/styleseed-ui-component-generator-mtz9jr5h' '.agents/skills/ss-component'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/styleseed-ui-component-generator-mtz9jr5h'

openskills read 'styleseed-ui-component-generator-mtz9jr5h'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/styleseed-ui-component-generator-mtz9jr5h/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills