Generic Feature Developer logo

Generic Feature Developer

Community
travisjneuman
generic-feature-developer

Guide feature development with architecture patterns for any tech stack. Covers frontend, backend, full-stack, and automation projects. Use when adding new features, modifying systems, or planning changes.

Overview

Publishertravisjneuman
Repository.claude
Skill namegeneric-feature-developer
Stars
98
Forks
22
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by travisjneuman on GitHub. Read the source before you install it.

Installation

Install the Generic Feature Developer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/travisjneuman/.claude.git /tmp/.claude
mkdir -p .claude/skills
cp -r /tmp/.claude/skills/generic-feature-developer .claude/skills/generic-feature-developer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Generic Feature Developer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Generic Feature Developer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Generic Feature Developer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Generic Feature Developer

Guide feature development across any tech stack.

When to Use This Skill

Use for:

  • Adding new features to existing codebase
  • Modifying or extending current systems
  • Planning architectural changes
  • Choosing between implementation approaches
  • Designing data flow for new functionality

Don't use when:

  • Pure UI/styling work → use generic-design-system
  • UX design decisions → use generic-ux-designer
  • Code review → use generic-code-reviewer

Development Workflow

  1. Understand - Read CLAUDE.md, identify affected files, list constraints
  2. Plan - Choose patterns, design data flow, identify edge cases
  3. Implement - Small testable changes, commit frequently
  4. Test & Document - Write tests, update docs, performance check

Architecture by Project Type

Static Sites

project/
├── index.html
├── css/           # variables.css, style.css
├── js/            # main.js, utils.js
└── assets/

Patterns: CSS variables, ES modules, event delegation

React/Next.js

src/
├── components/    # ui/, features/, layout/
├── hooks/
├── stores/
├── services/
└── types/

Patterns: Container/Presentational, custom hooks, Zustand/React Query

NestJS Backend

src/
├── modules/[feature]/
│   ├── feature.module.ts
│   ├── feature.controller.ts
│   ├── feature.service.ts
│   └── dto/
└── common/        # guards, decorators

Patterns: Module organization, DTOs, Guards, Prisma

Feature Decision Framework

Scope Assessment (First)

ScopeAction
Single componentImplement directly
Cross-cutting concernDesign interface first
New subsystemCreate architecture doc, get approval

Build vs Integrate

FactorBuild CustomUse Library
Core to productYes
Commodity featureYes
Tight integration neededYes
Time-criticalYes
Long-term ownershipYes

State Management Selection

ScopeSolution
Component-localuseState/useReducer
Feature-wideContext or Zustand slice
App-wideZustand/Redux store
Server stateReact Query/SWR
Form stateReact Hook Form

API Design Checklist

  • RESTful or GraphQL decision documented
  • Authentication method chosen
  • Error response format standardized
  • Pagination strategy defined
  • Rate limiting considered

Common Features

Adding UI Component

  1. Create component → 2. Export → 3. Add tests → 4. Document

Adding API Endpoint

  1. Define route → 2. Add validation → 3. Implement service → 4. Test

Adding State Management

  1. Define shape → 2. Create store → 3. Add actions → 4. Connect components

Database Changes

  1. Design schema → 2. Create migration → 3. Update models → 4. Add service

Data Flow Patterns

Frontend Data Flow

User Action → Event Handler → State Update → Re-render → UI Feedback
  • Optimistic updates: Update UI immediately, rollback on error
  • Pessimistic updates: Wait for server confirmation
  • Decision: Optimistic for low-risk (likes), pessimistic for high-risk (payments)

API Request Flow

Request → Auth Check → Validation → Business Logic → Database → Response
  • Early exit on validation failure
  • Transaction boundaries around multi-step operations
  • Consistent error response format

Event-Driven Patterns

Event TypeApproach
User eventsImmediate feedback
Server eventsWebSocket/SSE for real-time
Background tasksQueue for long operations

Error Handling Strategy

Error TypeFrontendBackend
ValidationInline field errors400 + field errors
AuthRedirect to login401/403
Not FoundEmpty state or redirect404
Server ErrorGeneric message + retry500 + log
NetworkOffline indicator + queueN/A

Frontend Pattern

typescript
try {
  await apiCall();
} catch (error) {
  if (error instanceof ValidationError) showFieldErrors(error.fields);
  else showGenericError();
}

Backend Pattern

typescript
if (err instanceof ValidationError)
  return res.status(400).json({ errors: err.errors });
if (err instanceof AuthError)
  return res.status(401).json({ message: "Unauthorized" });

Testing Strategy

LayerTypeTools
UIComponentTesting Library
LogicUnitJest, Vitest
APIIntegrationSupertest
E2EEnd-to-endPlaywright

Performance

Frontend: Code splitting, lazy loading, memoization, debounce Backend: DB indexing, caching, connection pooling, background jobs

Feature Implementation Checklist

Before marking feature complete:

  • Works for happy path
  • Error states handled
  • Loading states implemented
  • Edge cases tested
  • TypeScript types complete
  • Tests written
  • Documentation updated

See Also

  • Code Review Standards - Quality checks
  • Design Patterns - UI patterns
  • generic-design-system - For styling and visual consistency
  • generic-ux-designer - For UX flow decisions
  • Project CLAUDE.md - Workflow rules

READ shared standards when:

  • Complex feature design → CODE_REVIEW_STANDARDS.md (architecture section)
  • UI component patterns → DESIGN_PATTERNS.md (component section)

Frequently asked questions

What does the Generic Feature Developer AI skill do?

Guide feature development with architecture patterns for any tech stack. Covers frontend, backend, full-stack, and automation projects. Use when adding new features, modifying systems, or planning changes.

Why use Generic Feature Developer on TypingMind?

Because you install it once and use it with any model. Generic Feature Developer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Generic Feature Developer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/travisjneuman/.claude/tree/master/skills/generic-feature-developer. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Generic Feature Developer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Generic Feature Developer?

As many as you like. As long as a model supports skills, you can use Generic Feature Developer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Generic Feature Developer AI skill free?

Yes. It is published on GitHub by travisjneuman under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇