agentleFS
kellen-millerkellen-miller/skills/frontend-design/SKILL.md

frontend-design

Skill2 starsChanged 4 days agoMITView on GitHub

Use when frontend UI, visual design, layout, CSS, responsive behavior, component composition, design-system fit, or frontend implementation quality materially affects the work.

187 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use instantly-campaign, albert-dm and 10 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.
  • yawningwhaleAISkill

    instantly-campaign

    Create a new Instantly cold-email campaign in the proven 5-email structure of the user's top-performing campaign (~16% reply rate). Use when the user wants to launch a new outbound campaign, write a cold email sequence, create an Instantly campaign, draft outreach for a new service or niche, or set up a sales sequence.

    Also in 6 projects that use this

  • yawningwhaleAISkill

    albert-dm

    Reply to DMs and messages the way Albert would. Use when the user asks "how would Albert reply to this", pastes a conversation and wants an Albert-style response, or asks you to draft/write a DM in Albert's voice. Albert sells AI voice agents / automations to local service businesses (Go High Level, lead follow-up, bookings).

    Also in 5 projects that use this

  • naman10parikhSkill

    ecosystem-reference

    Quick-access directory of Claude Code ecosystem repos, skills, plugins, MCPs, and patterns. Use when improving the harness.

    Also in 5 projects that use this

  • naman10parikhSkill

    fractal-delegation

    Also in 5 projects that use this

  • julianoczkowskiSkill

    brief-to-tasks

    Break a design brief into an ordered checklist of independently buildable tasks using vertical slices. Saves as a markdown checklist. Use when user wants to break down work, create tasks from a brief, plan implementation order, or mentions "tasks" or "breakdown".

    Also in 7 projects that use this

  • SeifBenayedSkill

    file-reading

    Use this skill when a file has been uploaded but its content is NOT in your context — only its path at /mnt/user-data/uploads/ is listed in an uploaded_files block. This skill is a router: it tells you which tool to use for each file type (pdf, docx, xlsx, csv, json, images, archives, ebooks) so you read the right amount the right way instead of blindly running cat on a binary. Triggers: any mention of /mnt/user-data/uploads/, an uploaded_files section, a file_path tag, or a user asking about an uploaded file you have not yet read. Do NOT use this skill if the file content is already visible in your context inside a documents block — you already have it.

    Also in 6 projects that use this

  • +6 more from naman10parikh

The file

We split this skill into the rules it gives an agent

11 rules. 0 are common, 9 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 181 edited versions we read keep these.

  • 9

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Follow the parent workflow's ownership and $adversarial-review's finding-handling contract.

    line 10
  2. Distinctive:

    Do not use this skill as the authority for backend behavior, security, data modeling, or final correctness.

    line 42
  3. Distinctive:

    Do not carry rejected recommendations forward as noise.

    line 62
  4. Distinctive:

    read the target components and adjacent component patterns

    line 74
  5. Very specific:

    read relevant token/theme/layout files

    line 75
  6. Distinctive:

    keep changes inside the planned frontend paths unless the plan changes

    line 81
  7. Distinctive:

    use existing components, icons, layout primitives, and token conventions

    line 82
  8. Distinctive:

    avoid compatibility shims, old aliases, dual paths, and legacy UI surfaces unless the plan records an explicit requirement

    line 85
  9. Distinctive:

    After editing, record this status block in the work item or final notes:

    line 88
  10. Distinctive:

    When the parent or current agent selects implementation review, gather the diff, planning artifacts, rendered evidence, component and token …

    line 110
  11. Distinctive:

    Ask the reviewer to look for serious issues in:

    line 121

“Common” is measured: kept by at least 6 in 10 of the 181 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Frontend Design

Ownership

Follow the parent workflow's ownership and $adversarial-review's finding-handling contract. Implementation agents mutate frontend code and gather evidence only in their assigned worktrees. When invoked directly without parent workers, the current agent owns the workflow.

The parent or current agent selects any frontend-specific review packet. This lens contributes to that review and schedules none.

Preconditions

  • Work in the worktree assigned by the parent workflow, or the current worktree when invoked directly.
  • Inspect the existing design system, component patterns, CSS strategy, token files, layout primitives, and validation commands before changing UI.
  • For Svelte or SvelteKit work, use official Svelte docs or the Svelte MCP tools when available before changing Svelte-specific patterns.
  • For third-party frontend APIs, use Context7 or official documentation before relying on library-specific syntax or configuration.
  • For rendered UI, DOM, console, network, accessibility, responsive behavior, or browser smoke evidence, use Playwright, Chrome DevTools, browser tools, or equivalent local validation.

Use The Lens

Evaluate frontend work for:

  • product fit, visual hierarchy, information density, layout, responsive states
  • component composition, CSS strategy, design tokens, interaction states
  • loading, empty, error, permission, disabled, dense-data, and mobile states
  • design-system fit, accessibility, keyboard behavior, and visual polish
  • design-to-code direction, implementation risk, and validation evidence

Do not use this skill as the authority for backend behavior, security, data modeling, or final correctness.

Planning Pass

The planning agent identifies:

  • the strongest UI shape for the feature
  • design-system files and components likely to matter
  • responsive, empty, loading, error, permission, disabled, and dense-data states
  • implementation slices that protect visual coherence
  • screenshots, browser observations, or accessibility evidence needed before closeout
  • validation commands that prove the frontend result

Contribute frontend planning evidence when the parent or current agent selects a plan review. Follow the parent scheduling and $adversarial-review contract; this lens does not schedule planning critique.

Accepted recommendations must be reflected in decision.md or execplan.md. Do not carry rejected recommendations forward as noise.

Implementation Pass

Implementation agents write frontend code in their assigned worktrees, use the existing design system and tokens, implement applicable loading, empty, error, disabled, permission, mobile, and dense-data states, and gather evidence after editing. Return the evidence to the main workflow agent for integration and acceptance.

Before editing:

  • read the target components and adjacent component patterns
  • read relevant token/theme/layout files
  • inspect existing tests and validation scripts
  • gather rendered evidence first when the issue is visual or responsive

While editing:

  • keep changes inside the planned frontend paths unless the plan changes
  • use existing components, icons, layout primitives, and token conventions
  • implement expected loading, empty, error, disabled, permission, mobile, and dense-data states when they apply
  • avoid compatibility shims, old aliases, dual paths, and legacy UI surfaces unless the plan records an explicit requirement

After editing, record this status block in the work item or final notes:

---FRONTEND_IMPLEMENTATION_STATUS---
implementer: <agent or provider>
status: changed | no_change | blocked
changed_files:
docs_evidence:
browser_evidence:
validation:
critical:
high:
medium:
low:

The pass succeeds only when the diff contains the intended frontend changes and validation evidence exists for the risk level. If docs or browser evidence were needed but unavailable, record the gap as a blocker or residual risk.

Independent Frontend Review

When the parent or current agent selects implementation review, gather the diff, planning artifacts, rendered evidence, component and token files, and validation output. Contribute a frontend-specific lens to that selected independent review, covering design, ordinary correctness, validation, and adversarial risks in its single packet. Use $adversarial-review's provider-selection and status contract; do not create a separate review for this lens.

Any repeat review follows the parent scheduling and $adversarial-review contract and is never scheduled by this lens.

Ask the reviewer to look for serious issues in:

  • visual hierarchy, density, spacing, typography, and responsive behavior
  • missing UI states or accessibility regressions
  • component boundaries, duplicated styling, token misuse, and brittle CSS
  • mismatch between plan, implementation, screenshots, and validation evidence
  • unnecessary backwards compatibility or legacy UI noise

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.