Agent skill

Tsh Implementing Frontend

by TheSoftwareHouse in TheSoftwareHouse/copilot-collections

Frontend component patterns, composition, design token integration, barrel file organization, error handling, and Figma-to-code workflow.

MITAuto-check passedFrontend & Design

Install Tsh Implementing Frontend

skills CLI
$ npx skills add TheSoftwareHouse/copilot-collections --skill tsh-implementing-frontend -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install TheSoftwareHouse/copilot-collections tsh-implementing-frontend --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/TheSoftwareHouse/copilot-collections.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/tsh-implementing-frontend .claude/skills/tsh-implementing-frontend && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
tsh-implementing-frontend
GitHub stars
284
Token cost
~2.6k tokens
SKILL.md length
1,091 words
Files
2 (incl. references)
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

Frontend component patterns, composition, design token integration, barrel file organization, error handling, and Figma-to-code workflow.

  • Works in 5 steps: Extract the raw value from Figma (e.g.,… → Search the codebase for a matching token. → If a token exists — use it. → …
  • Implementing UI components
  • SKILL.md covers Implementation Process, State Decision Framework, Barrel File Guidelines and Component Checklist, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Tsh Implementing Frontend is an agent skill from TheSoftwareHouse/copilot-collections. Frontend component patterns, composition, design token integration, barrel file organization, error handling, and Figma-to-code workflow. Use when implementing UI components, translating Figma designs into code, managing component state, or integrating with a design system.

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/react-patterns.md`).

It sits in Frontend & Design, covering Design systems, Design tokens and Design to code. It works with Figma. The repository describes itself as: Opinionated AI-enabled workflows for product engineering. The licence is MIT.

When your agent uses it

  • Implementing UI components
  • Translating Figma designs into code
  • Managing component state
  • Integrating with a design system

Example prompts

  • “/tsh-implementing-frontend”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Extract the raw value from Figma (e.g., #3B82F6, 16px).
  2. Search the codebase for a matching token.
  3. If a token exists — use it.
  4. If no exact match — find the closest existing token and document the deviation.
  5. If truly new — flag it and ask the user before creating.

What it can do on your machine

Read from SKILL.md and the folder at commit 2fbe51e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Tsh Implementing Frontend loads about 2.6k tokens when it runs, and up to ~3.7k if it reads all its reference files. Until then it costs about 75 tokens; SKILL.md has 1,091 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~75
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from TheSoftwareHouse/copilot-collections at commit 2fbe51e, republished under its MIT licence (© TheSoftwareHouse). 1,091 words, ~2,633 tokens.

Download SKILL.mdSave it as .claude/skills/tsh-implementing-frontend/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
tsh-implementing-frontend
description
Frontend component patterns, composition, design token integration, barrel file organization, error handling, and Figma-to-code workflow. Use when implementing UI components, translating Figma designs into code, managing component state, or integrating with a design system.
user-invocable
false

Implementing Frontend

Provides patterns for building reusable, composable frontend components with design system integration and a structured Figma-to-code workflow.

<principles>
<declarative-over-imperative>
Define what the UI should look like based on state, not how to manipulate the DOM. Describe the desired outcome through components and state declarations. Let the framework handle reconciliation and updates. Compose complex UIs from simple, predictable building blocks rather than writing step-by-step mutation sequences.
</declarative-over-imperative>
<composition-over-complexity>
Build complex UIs by composing small, focused components rather than creating monolithic ones. Each component should have a single clear responsibility. Prefer children, slots, and compound component patterns over deep prop trees.
</composition-over-complexity>
<design-system-first>
Always use design tokens (colors, spacing, typography) from the project's design system. Never hardcode visual values. Map Figma specs to existing tokens. If no exact token match exists, find the closest and document the deviation — do not invent tokens without approval.
</design-system-first>
<never-guess>
If design context, tokens, or specifications are missing or unclear, stop and ask the user. Do not proceed with assumptions about visual implementation. Missing information produces wrong UI — asking produces correct UI.
</never-guess>
</principles>

Implementation Process

Use the checklist below and track progress:

Progress:
- [ ] Step 0: Fetch and review Figma design (Figma-backed tasks only)
- [ ] Step 1: Gather design context
- [ ] Step 2: Plan component structure
- [ ] Step 3: Implement components
- [ ] Step 4: Organize modules
- [ ] Step 5: Verify implementation

Step 0: Fetch and review Figma design (Figma-backed tasks only)

  • This is a hard gate for any Figma-backed task. Before planning component structure or writing code, resolve the Figma node, export the node image via the figma MCP, and extract the relevant specs: layout, spacing, typography, colors, dimensions, variants, and states.
  • If the task is Figma-backed but the Figma reference is missing, the node cannot be resolved, or the figma MCP cannot export the design, stop and ask the user through the calling agent's vscode/askQuestions. Do not implement from assumptions.
  • Treat this pre-implementation design review as distinct from the later UI verification loop. Looking at the design before coding is mandatory; verifying after coding is mandatory too.

Step 1: Gather design context

  • For Figma-backed tasks, Step 1 begins only after Step 0 is complete. Use the design already fetched through the figma MCP to identify components, spacing, typography, colors, and interaction states.
  • If the task is not Figma-backed, gather design context from the user-provided source of truth before proceeding.
  • Map every Figma value to an existing design token in the codebase:
    1. Extract the raw value from Figma (e.g., #3B82F6, 16px).
    2. Search the codebase for a matching token.
    3. If a token exists — use it.
    4. If no exact match — find the closest existing token and document the deviation.
    5. If truly new — flag it and ask the user before creating.
  • Identify all states the design implies: default, hover, focus, active, disabled, loading, error, empty.
  • Identify responsive breakpoints from the design. Check how the component should adapt across screen sizes — layout shifts, hidden/shown elements, typography scaling. Map breakpoints to the project's existing responsive tokens or media queries.

Step 2: Plan component structure

  • Decide component boundaries: what is a reusable component vs. page-specific layout.
  • Identify the props interface for each component — typed, with sensible defaults.
  • Determine state needs using the State Decision Framework table below.
  • Search the codebase for existing similar components. Extend or compose existing components rather than duplicating.
  • Sketch the component tree: parent → children relationships, data flow direction, and where state lives.

Step 3: Implement components

Follow these patterns for every component:

  • Composition: Use composition patterns — content projection (children/slots), render delegation, compound components — to keep components flexible. Avoid prop sprawl — if a component accepts more than ~7 props, it likely needs decomposition.
  • Typed props: Define explicit TypeScript types for all props. Never use any. Co-locate types in ComponentName.types.ts.
  • Named exports only: Use export { ComponentName } — no default exports. This ensures consistent imports and simplifies refactoring.
  • Error handling wrappers: Wrap data-dependent sections with the framework's error boundary mechanism for graceful failure. See the framework reference for the specific API.
  • Three UI states: Every data-dependent component must handle loading (progress indicator), error (meaningful message + recovery action), and empty (helpful message when no data).
  • Design tokens: All visual values (colors, spacing, typography, shadows, radii) must come from the design system. Zero hardcoded values.

Step 4: Organize modules

Apply barrel file rules from the Barrel File Guidelines table below:

  • Create index.ts barrel files at public API boundaries — folders whose exports are consumed by other modules.
  • Use named re-exports only: export { Button } from './Button'.
  • Skip barrels for internal utility folders that serve a single parent component.
  • Verify the barrel doesn't re-export unused internals that bloat the bundle.

Step 5: Verify implementation

  • If a calling workflow provides a verification loop (e.g., the Engineering Manager runs tsh-ui-reviewer automatically during /tsh-implement), defer to that workflow — do not duplicate verification here.
  • If no verification workflow is active, use the ui-verifying skill directly to compare the implementation against the Figma design.
  • Walk through each interaction state (hover, focus, disabled, error, loading, empty) and verify correctness.
  • Iterate on differences until the implementation matches the design within acceptable tolerances.
Show full SKILL.md (284 more words)Show less

State Decision Framework

State typeWhen to useExample
Local stateUI-only, single componentModal open/close, input value
Lifted stateShared between 2-3 siblingsFilter applied to a sibling list
Context / DIDeeply nested consumptionTheme, locale, auth status
Global storeComplex cross-cutting stateMulti-step form wizard, shopping cart
Server cacheRemote data with cachingAPI responses, paginated lists

Barrel File Guidelines

RuleDescription
Create barrel whenFolder exports are consumed by OTHER modules (public API boundary)
Avoid barrel whenInternal utils serving a single parent component — import directly
Re-export styleNamed re-exports only: export { Button } from './Button'
Never wildcardAvoid export * from — breaks tree shaking, hides API surface
Keep flatOne level deep — no barrel importing another barrel
Test with buildVerify barrel doesn't pull unused code into bundle

Component Checklist

Component:
- [ ] Single responsibility — one clear purpose
- [ ] Typed props — explicit types, sensible defaults
- [ ] Named export — no default exports
- [ ] Design tokens — no hardcoded visual values
- [ ] Error state — handles failure gracefully
- [ ] Loading state — shows progress indicator
- [ ] Empty state — meaningful message when no data
- [ ] Composition — uses children/slots, not prop sprawl

Anti-Patterns

Anti-PatternInstead Do
Hardcoded colors/spacing (#3B82F6, 16px)Use design tokens (var(--color-primary-500), theme.spacing(2))
Monolithic component (300+ lines)Split into composed sub-components
Props drilling through 4+ levelsUse context or composition pattern
Duplicating existing componentExtend existing with variants
Inline styles for themingUse design system's styling approach
export defaultNamed exports for consistency and refactoring
any type for propsExplicit type definitions
Barrel file for internal utilsDirect imports for single-consumer folders

Framework-Specific Patterns

The patterns above are framework-agnostic. For framework-specific implementation guidance, load the appropriate reference:

  • React: See ./references/react-patterns.md — hooks, JSX composition, error boundaries, memoization patterns.

Connected Skills

  • tsh-ui-verifying - for verifying implementation against Figma designs
  • tsh-technical-context-discovering - for understanding project conventions before implementing
  • tsh-ensuring-accessibility — to ensure components meet WCAG 2.1 AA standards
  • tsh-optimizing-frontend — for performance considerations during component implementation
  • tsh-implementing-forms — for form-specific component patterns and validation
  • tsh-writing-hooks — for custom hook patterns used within components
  • tsh-reviewing-frontend — for frontend-specific code review of implemented components

© TheSoftwareHouse, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in .github/skills/tsh-implementing-frontend of TheSoftwareHouse/copilot-collections.

  • SKILL.md
  • references/react-patterns.md

Open the folder on GitHubat commit 2fbe51e

Compare with similar skills

Tsh Implementing Frontend next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Tsh Implementing Frontend compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tsh Implementing Frontend this skillTheSoftwareHouse/copilot-collections284—~2.6kAutomated safety check: PassMIT
Figma use_figma Plugin API Ruleswarpdotdev/warp65k4 repos~4.4kAutomated safety check: PassAGPL-3.0
Figma Screen Generatorwarpdotdev/warp65k2 repos~5kAutomated safety check: PassAGPL-3.0
AnyDesignuxKero/anydesign216—~1.5kAutomated safety check: PassMIT
AnyDesign Design Analyzeravelikiy/great_cto1031 repos~3.2kAutomated safety check: PassMIT
Figma Design Inspectorasgeirtj/system_prompts_leaks69k—~936Automated safety check: PassCC0-1.0

Similar skills

  • Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.

    65k GitHub starsUsed in 4 repos~4.4k tokens
    Frontend & DesignAuto-check passed
  • Figma Screen Generator

    warpdotdev/warp

    Builds or updates full Figma screens from code or a description by reusing the file's published design system components, variables and styles.

    65k GitHub starsUsed in 2 repos~5k tokens
    Frontend & DesignAuto-check passed
  • AnyDesign

    uxKero/anydesign

    Extracts the design of a screenshot, website URL or Figma file into a design.md of tokens, components, layout and brand rules, or copies one element into element.md.

    216 GitHub stars~1.5k tokensUpdated 24 days ago
    Frontend & DesignAuto-check passed
  • AnyDesign Design Analyzer

    avelikiy/great_cto

    Analyzes a screenshot, website or Figma file and writes a `design.md` with its token system, component inventory and reconstruction notes, or an `element.md` for one element.

    103 GitHub starsUsed in 1 repo~3.2k tokens
    Frontend & DesignAuto-check passed
  • Figma Design Inspector

    asgeirtj/system_prompts_leaks

    Inspects Figma designs through the figma CLI and Figma's MCP server to read variants, spacing, tokens and layouts and to extract assets for implementation.

    69k GitHub stars~936 tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Figma Core Workflow A

    jeremylongshore/tons-of-skills-marketplace

    Extract design tokens, colors, typography, and spacing from Figma files via REST API.

    2.8k GitHub stars~1.8k tokensUpdated today
    Frontend & DesignAuto-check passed

More from TheSoftwareHouse/copilot-collections

All 21 skills in this repo
  • Tsh Creating Skills

    TheSoftwareHouse/copilot-collections

    Create new skills (SKILL.md) for GitHub Copilot. An agent skill from TheSoftwareHouse/copilot-collections.

    284 GitHub stars~4.1k tokensUpdated 3 days ago
    Auto-check passed
  • Tsh Implementing Terraform Modules

    TheSoftwareHouse/copilot-collections

    Build reusable Terraform modules for AWS, Azure, and GCP infrastructure following infrastructure-as-code best practices.

    284 GitHub stars~1.6k tokensUpdated 3 days ago
    Auto-check passed
  • Tsh Optimizing Frontend

    TheSoftwareHouse/copilot-collections

    Frontend rendering optimization, code splitting, memoization strategies, bundle size control, asset optimization, and memory management.

    284 GitHub stars~4.1k tokensUpdated 3 days ago
    Auto-check passed
  • Tsh Reviewing Frontend

    TheSoftwareHouse/copilot-collections

    Frontend-specific code review criteria, component anti-patterns, hooks quality, rendering correctness, accessibility and performance spot-checks, and module organization issues.

    284 GitHub stars~4.4k tokensUpdated 3 days ago
    Auto-check passed
  • Tsh Writing Hooks

    TheSoftwareHouse/copilot-collections

    Custom hook and composable patterns — naming, composition, stable return shapes, lifecycle cleanup, and testing strategies.

    284 GitHub stars~3k tokensUpdated 3 days ago
    Auto-check passed
  • Tsh Creating Instructions

    TheSoftwareHouse/copilot-collections

    Creates custom instruction files (.instructions.md) for GitHub Copilot in VS Code.

    284 GitHub stars~2.9k tokensUpdated 3 days ago
    Auto-check passed

Works with

Questions about Tsh Implementing Frontend

What does Tsh Implementing Frontend do?

Frontend component patterns, composition, design token integration, barrel file organization, error handling, and Figma-to-code workflow. Tsh Implementing Frontend is an agent skill from TheSoftwareHouse/copilot-collections. Frontend component patterns, composition, design token integration, barrel file organization, error handling, and Figma-to-code workflow.

When should I use Tsh Implementing Frontend?

Tsh Implementing Frontend fits situations like: implementing UI components; translating Figma designs into code; managing component state; integrating with a design system.

How do I install Tsh Implementing Frontend in Claude Code?

Run `npx skills add TheSoftwareHouse/copilot-collections --skill tsh-implementing-frontend -a claude-code`. Or copy the skill folder (.github/skills/tsh-implementing-frontend in TheSoftwareHouse/copilot-collections) into .claude/skills/tsh-implementing-frontend in your project. Claude Code loads it when a task matches its description.

How do I install Tsh Implementing Frontend in Codex?

Run `npx skills add TheSoftwareHouse/copilot-collections --skill tsh-implementing-frontend -a codex`. Or copy the skill folder (.github/skills/tsh-implementing-frontend in TheSoftwareHouse/copilot-collections) into .agents/skills/tsh-implementing-frontend in your project. Codex loads it when a task matches its description.

Can I use Tsh Implementing Frontend in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add TheSoftwareHouse/copilot-collections --skill tsh-implementing-frontend -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tsh-implementing-frontend, .gemini/skills/tsh-implementing-frontend, .github/skills/tsh-implementing-frontend and .opencode/skills/tsh-implementing-frontend in your project.

What does Tsh Implementing Frontend need to run?

SKILL.md names no scripts, command-line tools or credentials: Tsh Implementing Frontend is instructions for the agent only.

Does Tsh Implementing Frontend access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Tsh Implementing Frontend safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Tsh Implementing Frontend use?

Tsh Implementing Frontend is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Tsh Implementing Frontend use?

About 2.6k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.1k tokens, read only when the agent opens those files.

What are the alternatives to Tsh Implementing Frontend?

Skills that share tags, products or a category with Tsh Implementing Frontend: Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars), Figma Screen Generator (warpdotdev/warp, 65k stars), AnyDesign (uxKero/anydesign, 216 stars) and AnyDesign Design Analyzer (avelikiy/great_cto, 103 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tsh Implementing Frontend?

TheSoftwareHouse (a GitHub organization) maintains it in TheSoftwareHouse/copilot-collections, which has 284 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 5, 2026.

Source: TheSoftwareHouse/copilot-collections on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.