feature-dev
SkillDev toolsfeature-dev is a skill that guides an AI agent through building new features by first exploring and understanding the existing codebase. It focuses on architecture, so the agent plans changes that fit the project instead of guessing. Use it when you want a structured path from feature request to implementation.
Use feature-dev in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add feature-dev and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the feature-dev skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.
No other account needed.
Have an AI agent that can load and use skills.
What your AI can do with it
- Explores the codebase to understand existing structure and patterns
- Guides the agent through planning a new feature before coding
- Focuses on architecture so changes fit the project
- Walks the agent from feature request to implementation
Getting started
- Have an AI agent that can load and use skills.
- Add the feature-dev skill to that agent's available skills.
- Give the agent a feature request and let it explore the codebase first.
- Review the agent's plan and implementation as it works.
What this skill tells your AI
The instructions your AI receives, as published by ledgerhq/ledger-live in .agents/skills/feature-dev/SKILL.md and read by Ahel’s review.
description: Guided feature development with codebase understanding and architecture focus argument-hint: Optional feature description
Feature Development
You are helping a developer implement a new feature for Ledger Wallet applications. Follow a systematic approach: understand the codebase deeply, identify and ask about all underspecified details, design elegant architectures, then implement.
References
New features must be implemented in src/mvvm/ following the MVVM architecture (.agents/skills/mvvm-architecture/SKILL.md).
Shared logic extracted out of an app goes to shared/, domain/ or features/, not to libs/.
Core Principles
- Ask clarifying questions: Identify all ambiguities, edge cases, and underspecified behaviors. Ask specific, concrete questions rather than making assumptions. Wait for user answers before proceeding with implementation. Ask questions early (after understanding the codebase, before designing architecture).
- Understand before acting: Read and comprehend existing code patterns first
- Read files identified by agents: When launching agents, ask them to return lists of the most important files to read. After agents complete, read those files to build detailed context before proceeding.
- Simple and elegant: Prioritize readable, maintainable, architecturally sound code
- Use TodoWrite: Track all progress throughout
Phase 1: Discovery
Goal: Understand what needs to be built
Initial request: $ARGUMENTS
Actions:
- Create todo list with all phases
- If feature unclear, ask user for:
- What problem are they solving?
- What should the feature do?
- Any constraints or requirements?
- Summarize understanding and confirm with user
Phase 2: Codebase Exploration
Goal: Understand relevant existing code and patterns at both high and low levels
Actions:
-
Launch 2-3 code-explorer agents in parallel. Each agent should:
- Trace through the code comprehensively and focus on getting a comprehensive understanding of abstractions, architecture and flow of control
- Target a different aspect of the codebase (eg. similar features, high level understanding, architectural understanding, user experience, etc)
- Include a list of 5-10 key files to read
Example agent prompts:
- "Find features similar to [feature] and trace through their implementation comprehensively"
- "Map the architecture and abstractions for [feature area], tracing through the code comprehensively"
- "Analyze the current implementation of [existing feature/area], tracing through the code comprehensively"
- "Identify UI patterns, testing approaches, or extension points relevant to [feature]"
-
Once the agents return, please read all files identified by agents to build deep understanding
-
Present comprehensive summary of findings and patterns discovered
Phase 3: Clarifying Questions
Goal: Fill in gaps and resolve all ambiguities before designing
CRITICAL: This is one of the most important phases. DO NOT SKIP.
Actions:
- Review the codebase findings and original feature request
- Identify underspecified aspects: edge cases, error handling, integration points, scope boundaries, design preferences, backward compatibility, performance needs
- Present all questions to the user in a clear, organized list
- Wait for answers before proceeding to architecture design
If the user says "whatever you think is best", provide your recommendation and get explicit confirmation.
Phase 4: Architecture Design
Goal: Design multiple implementation approaches with different trade-offs
Actions:
- Launch 2-3 code-architect agents in parallel with different focuses: minimal changes (smallest change, maximum reuse), clean architecture (maintainability, elegant abstractions), or pragmatic balance (speed + quality)
- Review all approaches and form your opinion on which fits best for this specific task (consider: small fix vs large feature, urgency, complexity, team context)
- Present to user: brief summary of each approach, trade-offs comparison, your recommendation with reasoning, concrete implementation differences
- Ask user which approach they prefer
Phase 5: Implementation
Goal: Build the feature
DO NOT START WITHOUT USER APPROVAL
Actions:
- Wait for explicit user approval
- Read all relevant files identified in previous phases
- Implement following chosen architecture
- Follow codebase conventions strictly (see References)
- Write clean, well-documented code
- Update todos as you progress
Phase 6: Quality Review
Goal: Ensure code is simple, DRY, elegant, easy to read, and functionally correct
Actions:
- Launch 3 code-reviewer agents in parallel with different focuses: simplicity/DRY/elegance, bugs/functional correctness, project conventions/abstractions
- Consolidate findings and identify highest severity issues that you recommend fixing
- Present findings to user and ask what they want to do (fix now, fix later, or proceed as-is)
- Address issues based on user decision
Phase 7: Summary
Goal: Document what was accomplished
Actions:
- Mark all todos complete
- Summarize:
- What was built
- Key decisions made
- Files modified
- Suggested next steps
Signals
- GitHub stars
- 621
- Forks
- 491
- Last commit
- Oct 2026
Questions
- What kind of tool is feature-dev?
- It is a skill for an AI agent. It guides the agent through feature development with codebase understanding and architecture focus.
- Does feature-dev write code for me?
- It guides your agent through building features. The agent does the work, with the skill providing the structured approach.
- What does feature-dev focus on?
- It focuses on understanding the existing codebase and architecture before making changes, so new features fit the project.
- Can I use feature-dev with any AI agent?
- It works with an AI agent that can load and use skills. The skill itself is client-agnostic.
- Do I need to know the codebase before using it?
- No. The skill starts by exploring and understanding the existing codebase, so the agent can work with what is there.
Advanced
- Item type
- skill
- Key
feature-dev- Source
- github.com/ledgerhq/ledger-live
github.com/ledgerhq/ledger-live