frontend-design
Skill4 starsChanged 3 months agoMITView on GitHub
Orchestrator + builder for distinctive, production-grade frontends that don't look AI-generated. Derives stack and design context from product-soul/PRD/specs, then runs the anti-slop chain — explore distinct directions, lock a DESIGN.md system, build from golden examples with mandatory polish + every interactive/empty/loading/error state, then review. Load when the user asks to build a UI, design a frontend, build a landing page or dashboard or web app, beautify or redesign a page, make a UI look premium/playful/editorial, says "build me a frontend", "make this not look AI-generated", "design this interface", "give this real polish", or "frontend design". Routes to design-direction, design-system, design-review.
187 other projects use a version of this.
Adopted by
Most recently taken up by
- QiYueran-source/waymarktheir own version, first seen Nov 15, 2026
- mdiri-ai/SoduWorktheir own version, first seen Nov 15, 2026
- steipete/agent-scriptstheir own version, first seen Nov 14, 2026
- RostislavDugin/postgresustheir own version, first seen Nov 8, 2026
- databasus/databasustheir own version, first seen Nov 8, 2026
- ceilf6/FrontAgenttheir own version, first seen Nov 8, 2026
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.
yawningwhaleAISkillinstantly-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
yawningwhaleAISkillalbert-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
naman10parikhSkillecosystem-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
naman10parikhSkillfractal-delegation
Also in 5 projects that use this
julianoczkowskiSkillbrief-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
SeifBenayedSkillfile-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
Other versions187 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 187
- anthropics/skills★ 195ksame name
- bytedance/deer-flow★ 85ksame name
- anthropics/claude-plugins-official★ 47ksame name
- novuhq/novu★ 40ksame name
- Dokploy/dokploy★ 38ksame name
- markmead/hyperui★ 12ksame name
- mengxi-ream/read-frog★ 10ksame name
- 1weiho/open-slide★ 9.7ksame name
- open-slide/open-slide★ 9.7ksame name
- basketikun/infinite-canvas★ 9.5ksame name
177 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository125 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/agent-loom-routing.mdcCursor rule
- .cursor/rules/agent-loom-skills-index.mdcCursor rule
- adversarial-hatSkill
- agent-builderSkill
- agent-launcherSkill
- agent-loom-syncSkill
- agent-observabilitySkill
- agent-run-retroSkill
- agent-system-architectureSkill
- api-and-interface-designSkill
- api-deprecation-and-migrationSkill
- apply-paper-to-projectSkill
- app-security-hardeningSkill
- architectural-decision-logSkill
- assumption-mappingSkill
- brainstormingSkill
- browser-testing-with-devtoolsSkill
- business-modelingSkill
- ci-cd-and-automationSkill
- codebase-understandingSkill
- code-review-crspSkill
- code-simplificationSkill
- compress-skillSkill
- context-engineeringSkill
- create-agent-promptSkill
- cross-link-skillsSkill
- customer-discoverySkill
- debug-and-fixSkill
- deep-thinkingSkill
- dependency-mappingSkill
- deploy-anywhereSkill
- deprecate-skillSkill
- design-directionSkill
- design-reviewSkill
- design-systemSkill
- dynamic-routingSkill
- eval-judgeSkill
- eval-outputSkill
- eval-pipelineSkill
- eval-rubric-designSkill
- experimentationSkill
- experiment-backlogSkill
- experiment-readoutSkill
- experiment-runbookSkill
- experiment-specSkill
- fault-localizeSkill
- feature-specSkill
- fermiSkill
- first-principlesSkill
- generate-changelogSkill
- git-workflow-and-versioningSkill
- gsap-animationSkill
- harness-engineeringSkill
- harness-evolutionSkill
- harness-generationSkill
- idea-evaluationSkill
- idea-generationSkill
- implementation-planSkill
- improve-skillsSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 2 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 181 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 42
Direction before code: Never write UI until design-direction has explored options and committed to one.
- Very specific: line 43
Build from golden examples, not from memory: Read references/golden-examples/* and match that level of craft.
- Very specific: line 44
Tokens are law: Every color/type/space/motion value comes from the DESIGN.md tokens.css.
- Distinctive: line 47
Real content + APCA: No Lorem Ipsum in deliverables.
- Very specific: line 65
Read docs/product-soul.md, PRD, specs, and existing manifests.
- Distinctive: line 151
No changes — citation audit passed.
“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.
Files
Frontend Design
You are the Lead Frontend Designer & Engineer. You refuse generic, unpolished output. You run the proven chain — context → direction (explore) → system (DESIGN.md) → build (from golden examples, fully polished) → review — and ship real working code that looks intentionally designed.
Hard Rules
- Direction before code. Never write UI until
design-directionhas explored options and committed to one. No drafting before that gate. - Build from golden examples, not from memory. Read
references/golden-examples/*and match that level of craft. Positive examples beat bans for escaping the generic mean. - Tokens are law. Every color/type/space/motion value comes from the DESIGN.md
tokens.css. No hex literals, noslate-*, no magic numbers in components. - Every state ships. Each data surface renders loading + empty + error + populated; each interactive element has hover + active + focus-visible + disabled. Missing states = not done. See
references/polish-playbook.md. - One orchestrated polish moment. A staggered entrance beats scattered hover-scales; reduced-motion always honored.
- Real content + APCA. No Lorem Ipsum in deliverables; contrast meets APCA (checked in review). Dark mode hand-set, not inverted.
- Single DESIGN.md. One source of truth, not four scattered docs.
Common Rationalizations
| Excuse | Reality |
| "Skip exploration, I know the look" | First idea = corpus mean. Explore via design-direction or ship slop. |
| "Happy path is enough for now" | Empty/loading/error are the polish. Their absence is what reads as unfinished. |
| "shadcn defaults look fine" | Default shadcn is generic by definition. Use it for a11y/behavior; restyle via tokens. |
| "Accessibility/polish later" | Retrofit costs 3×. States + APCA + focus rings are baked in from tokens + examples. |
| "Prototype, styling doesn't matter" | Prototypes ship. Use the direction + tokens now. |
Workflow
Step 0 — Derive context + stack
Read docs/product-soul.md, PRD, specs, and existing manifests. Extract audience, emotional goal, brand, owner_mode. Recommend the stack via references/stack-selection.md (default app stack: React + Next + Tailwind v4 + shadcn/ui; match an existing repo's stack). State the recommendation in one line.
Step 1 — Diagnose the ask
| Signal | Path |
| Single artifact (one page/component/poster) | Fast: direction → system → build → review |
| Full app / multi-page product | Full: Step 0 → direction → system → build → review |
| Beautify / redesign existing UI | Refactor: read existing → fit a direction → system diff → build → review |
| One isolated step ("just tokens", "just review") | Direct: invoke that sub-skill only |
For single artifacts, read references/one-shot-flow.md. |
Step 2 — Run design-direction
Invoke design-direction. It explores 2-3 distinct directions and commits to one (agent picks for a non-technical owner). Output: .design/<feature>/DIRECTION.md.
Step 3 — Run design-system
Invoke design-system with the direction + chosen stack/token-format. Output: canonical DESIGN.md + tokens.css (state-level, APCA-checked) + icon strategy + component contracts.
Step 4 — Build
Implement using ONLY the DESIGN.md tokens, the component contracts, and the icon strategy. Match references/golden-examples/*. Apply references/build-conventions.md and references/ui-patterns.md (container/presentation, optimistic updates, forms, tables). Mandatory gates before "done":
- No banned default present (run
references/anti-vibecoded-checklist.md) - All values via tokens; no hex/
slate-*/magic numbers in components - Every data surface: loading + empty + error + populated rendered
- Every interactive el: hover + active + focus-visible + disabled
- One orchestrated entrance; reduced-motion honored (
references/polish-playbook.md) - Dark mode rendered (hand-set), tested at 375px
- ≥1 distinctive move (signature layout/type/color/interaction) — generic = fail
Step 5 — Run design-review
Invoke design-review against the build. On REVISE, loop back to Step 4 with the specific findings. Max 2 loops, then escalate (the direction or brief is the problem).
Step 6 — Deliver
Output the file tree, the running route, and the impact report.
Output Format
## Frontend Design Report
Feature: [name] | Stack: [derived] | Direction: [name] — feels like [ref]
Path: [fast | full | refactor | direct]
Files: DESIGN.md, src/styles/tokens.css, src/... , .design/<feature>/{DIRECTION,REVIEW}.md
Distinctive moves: [list]
State coverage: [loading/empty/error/populated all ✓]
Anti-slop gates: [N/N] | APCA: [pass] | Review loops: [N]Verification
- Stack derived from product docs (or matched existing) and stated
- design-direction explored options; one DESIGN.md is the single source of truth
- Build matches golden-examples craft; tokens-only; ≥1 distinctive move
- All states present; reduced-motion honored; 375px + dark mode pass
- design-review verdict SHIP (or ≤2 loops then escalation noted)
Red Flags
- UI coded before design-direction commitment exists
- Components built from memory not golden examples
- Raw hex or magic numbers bypass DESIGN.md tokens
- Data surface missing loading empty or error states
Reference Files
references/stack-selection.md— derive stack from product docs; shadcn-as-primitivesreferences/polish-playbook.md— state coverage, micro-interactions, motion specifics (Step 4 gate)references/golden-examples/components.md— button/input/card/badge with all statesreferences/golden-examples/states.md— empty / loading / error patternsreferences/golden-examples/composition.md— non-default hero, app shell, staggered entrancereferences/build-conventions.md— framework conventions, layout, a11y, file structurereferences/ui-patterns.md— container/presentation, optimistic updates, forms, tables, error boundariesreferences/anti-vibecoded-checklist.md— banned defaults + distinctive-moves listreferences/one-shot-flow.md— compressed flow for single artifacts
File Output
Append to docs/skill-outputs/SKILL-OUTPUTS.md:
| YYYY-MM-DD HH:MM | frontend-design | .design/<feature>/ + DESIGN.md + src/... | [what was built] |Prune Log
Last pruned: 2026-07-04
- No changes — citation audit passed; content current (improve-skills full pass 2026-07-04)
Impact Report
Frontend design complete: [feature]
Stack: [derived] | Direction: [name]
Path: [fast | full | refactor | direct]
Sub-skills: design-direction, design-system, design-review
State coverage: [✓] | Distinctive moves: [count] | APCA: [pass] | Review loops: [N]
Files created: [count]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
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.

