frontend-patterns
Skill0 starsChanged 5 months agoMITView on GitHub
Scans the codebase to auto-detect frontend conventions (pages, containers, components, hooks, services) and caches them. Use when creating or modifying frontend code so new files follow existing patterns exactly.
- Reads credentials
87 other projects use a version of this.
Adopted by
Most recently taken up by
- Rojios/everything-claude-codetheir own version, first seen Nov 8, 2026
- lhbsaa/apex-unifiedtheir own version, first seen Nov 8, 2026
- ahmadvahidi/skill-atlastheir own version, first seen Nov 8, 2026
- smart-coder-labs/nexus-mindtheir own version, first seen Nov 8, 2026
- Ashfaqbs/ai-coding-agent-toolkittheir own version, first seen Nov 8, 2026
- KbWen/agentic-ostheir own version, first seen Nov 7, 2026
Used with
Projects with it also use brand-discovery, agent-sort 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.
ysyecustSkillbrand-discovery
Use when a brand needs to discover or articulate its identity through structured multi-session interviews. Covers purpose, positioning, audience, personality, voice, narrative, and founder-brand tension across 8 modules using laddering, 5 Whys, and projective techniques. Produces a resumable session with disk-persisted state and a master brandbook (90_SYNTHESIS.md).
Also in 6 projects that use this
niloykumarbarmanSkillagent-sort
Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.
Also in 14 projects that use this
royaluniondesign-sysSkillconfigure-ecc
Interactive installer for Everything Claude Code — guides users through selecting and installing skills and rules to user-level or project-level directories, verifies paths, and optionally optimizes installed files.
Also in 12 projects that use this
loulanyueSkillnuxt4-patterns
Nuxt 4 app patterns for hydration safety, performance, route rules, lazy loading, and SSR-safe data fetching with useFetch and useAsyncData.
Also in 10 projects that use this
ronmkrSkillvite-patterns
Vite build tool patterns including config, plugins, HMR, env variables, proxy setup, SSR, library mode, dependency pre-bundling, and build optimization. Activate when working with vite.config.ts, Vite plugins, or Vite-based projects.
Also in 8 projects that use this
royaluniondesign-sysSkillcontent-hash-cache-pattern
Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.
Also in 16 projects that use this
Other versions87 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 87
- affaan-m/ECC★ 246ksame name
- rommapp/romm★ 14ksame name
- xu-xiang/everything-claude-code-zh★ 1.9ksame name
- bybren-llc/safe-agentic-workflow★ 405same name
- loulanyue/awesome-claude-notes★ 272same name
- KbWen/agentic-os★ 229same name
- cloudnative-co/claude-code-starter-kit★ 153same name
- tpavanipradeep/everything-claude-code★ 104same name
- mturac/everything-openai-codex★ 89same name
- mit-network/everything-claude-code★ 76same name
77 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 repository38 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- api-contract-validationSkill
- architecture-scannerSkill
- auto-approve-policySkill
- auto-learningSkill
- backend-patternsSkill
- branch-syncSkill
- browser-testSkill
- browseSkill
- build-checkSkill
- cache-refreshSkill
- codebase-explainerSkill
- coding-standardsSkill
- commit-styleSkill
- context-switchingSkill
- continuous-learningSkill
- db-preflightSkill
- env-preflightSkill
- eval-harnessSkill
- feature-completenessSkill
- file-indexSkill
- function-extractSkill
- idev-initSkill
- import-graphSkill
- lessons-learnedSkill
- post-creation-verifySkill
- pre-ship-verifySkill
- project-mapSkill
- self-reviewSkill
- session-resumeSkill
- skill-benchmarkSkill
- skilloptSkill
- smart-contextSkill
- strategic-compactSkill
- task-journalSkill
- tdd-workflowSkill
- test-coverageSkill
- test-mapSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 26 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
When creating or modifying frontend code and no cached patterns exist yet.
- Distinctive: line 25
Run these checks to identify the technology:
- Very specific: line 125
After scanning, write all discovered patterns to: .claude/idev/frontend-patterns/cache.md
- Distinctive: line 182
Keep the cache under ~250 lines by trimming examples if it grows beyond that.
- Distinctive: line 189
When creating a new frontend feature, the scanner detects what files are needed:
“Common” is measured: kept by at least 6 in 10 of the 26 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 Pattern Scanner Skill
Purpose
Auto-detect frontend (React/Vue/Angular/Svelte) code conventions by scanning the codebase. Works on any project.
Activation
When creating or modifying frontend code and no cached patterns exist yet.
How It Works
This skill does NOT hardcode patterns. Instead, it scans the codebase to discover them.
Results are cached in .claude/idev/frontend-patterns/cache.md after first scan.
Phase 1: Detect Frontend Stack
Run these checks to identify the technology:
1. Read package.json → detect framework (react, vue, angular, svelte, next, nuxt)
2. Read package.json → detect key libraries:
- State: redux, zustand, mobx, pinia, @tanstack/react-query
- UI: antd, @mui/material, chakra-ui, tailwindcss, bootstrap
- Routing: react-router-dom, vue-router, @angular/router
- HTTP: axios, fetch wrapper, @tanstack/react-query
- Forms: react-hook-form, formik, vee-validate
- Date: dayjs, moment, date-fns, luxon
3. Read tsconfig.json or jsconfig.json → TypeScript or JavaScript
4. Glob for tailwind.config.* → Tailwind CSS
5. Glob for .eslintrc* → Linting rulesPhase 2: Discover Project Structure
Scan to find the architecture pattern:
1. Read src/ directory structure (ls src/)
2. Detect architecture style:
- Feature-based: src/features/ or src/modules/
- Layer-based: src/components/, src/services/, src/hooks/
- Page-based: src/pages/ or app/ (Next.js/Nuxt)
3. Glob **/*Container*.{tsx,jsx,vue} → Container components
4. Glob **/*Page*.{tsx,jsx,vue} → Page components
5. Glob **/hooks/*.{ts,js} or **/composables/*.{ts,js} → Custom hooks
6. Glob **/services/*.{ts,js} or **/api/*.{ts,js} → API services
7. Glob **/models/*.{ts,js} or **/types/*.{ts,js} → Type definitions
8. Glob **/store/*.{ts,js} or **/slices/*.{ts,js} → State management
9. Grep for "createBrowserRouter|Routes|Route" → Routing setup file
10. Grep for "API_URL|BASE_URL|baseURL" in .env* → API configurationPhase 3: Extract Patterns from Existing Code
For each discovered layer, read ONE representative file and extract the pattern:
3.1 Component Pattern
Pick one presentation/UI component
Extract: FC typing vs function declaration, props interface pattern, styling approach
Detect: CSS modules, Tailwind, styled-components, inline styles, UI library usage
Note: import ordering convention, export style (default vs named)3.2 Container/Smart Component Pattern
Pick one container component
Extract: how hooks are used, how data flows to children, callback patterns
Detect: useCallback/useMemo usage, data transformation location, error handling3.3 Hook Pattern
Pick one custom hook
Extract: return type, query/mutation pattern, error dispatching
Detect: query key pattern, cache invalidation strategy, optimistic updates
Note: query library version (v4 vs v5 differences)3.4 Service/API Pattern
Pick one service file
Extract: HTTP client (axios instance, fetch wrapper), URL construction, response typing
Detect: interceptors, auth headers, error transformation, base URL config
Note: how API URLs are organized (enum, constants file, inline)3.5 Type/Model Pattern
Pick one types file
Extract: interface vs type usage, enum style (string enum, const enum, object const)
Detect: DTO types, form data types, API response wrappers3.6 State Management Pattern
Find store/slice files
Extract: how global state is structured, dispatch patterns
Detect: Redux toolkit, Zustand, Context, or other3.7 Routing Pattern
Find routing config
Extract: route definition style, route constants, navigation pattern
Detect: lazy loading, guards/middleware, nested routesPhase 4: Generate Cache
After scanning, write all discovered patterns to:
.claude/idev/frontend-patterns/cache.md
Format:
# Frontend Patterns Cache
## Generated: [date]
## Project: [detected project name]
## Stack: [framework] + [UI lib] + [state mgmt] + [query lib]
### Paths
src root: [path]
Components: [path pattern]
Containers: [path pattern]
Hooks: [path pattern]
Services: [path pattern]
Types: [path pattern]
Routes: [file path]
Store: [path pattern]
### Component Template
[extracted pattern with placeholders]
### Container Template
[extracted pattern with placeholders]
### Hook Templates
Query hook: [pattern]
Mutation hook: [pattern]
### Service Template
[extracted pattern with placeholders]
### Type/Interface Template
[extracted pattern]
### Conventions
- Styling: [Tailwind/CSS Modules/styled-components/etc.]
- Exports: [default/named]
- Props: [interface naming]
- File naming: [kebab-case/PascalCase/camelCase]
- Error handling: [pattern]
- Navigation: [pattern]
### Function Index
[Compact list of exported/public functions, one per line:]
functionName — file:line — one-line purpose
[Cap at ~100 entries, most-used first. Used by function-extract for targeted
reads and by cache-refresh for incremental updates. Update entries whenever
adding or modifying functions.]Phase 5: Usage
On subsequent tasks, load only the cache file instead of rescanning. Keep the cache under ~250 lines by trimming examples if it grows beyond that. Rescan if user says "refresh patterns" or if cache is older than 7 days.
Checklist (generic, auto-populated from scan)
When creating a new frontend feature, the scanner detects what files are needed:
- Types/interfaces in [detected types path]
- Service methods in [detected services path]
- API URL entries in [detected URL config]
- Query/mutation hooks in [detected hooks path]
- Container component in [detected containers path]
- Presentation component in [detected presentation path]
- Route registration in [detected routes file]
- Hook barrel exports in [detected barrel file] (if applicable)
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.

