wshobson avatar

Parallel Feature Development

This is the playbook for splitting feature work across multiple AI agents without them stepping on each other's toes. It covers file ownership strategies (by directory, module, or layer), the cardinal rule of one owner per file, and integration patterns like vertical slices versus horizontal layers. The interface contract approach is smart: create a shared types file that nobody touches, so both the UI and API implementers can work in parallel against the same agreed upon signature. The troubleshooting section is honest about what actually goes wrong, like when barrel files create conflicts or when your initial decomposition turns out to be wrong mid-stream. If you're orchestrating multiple agents on the same codebase, this gives you the structure to avoid merge hell.

skills.sh installs
10.3K
GitHub stars
42.4K
last updated
Aug 21, 2026

Install

$ npx -y skills add wshobson/agents --skill parallel-feature-development --agent claude-code

Installs into .claude/skills of the current project.

Files

Parallel Feature Development

Strategies for decomposing features into parallel work streams, establishing file ownership boundaries, avoiding conflicts, and integrating results from multiple implementer agents.

When to Use This Skill

  • Decomposing a feature for parallel implementation
  • Establishing file ownership boundaries between agents
  • Designing interface contracts between parallel work streams
  • Choosing integration strategies (vertical slice vs horizontal layer)
  • Managing branch and merge workflows for parallel development

File Ownership Strategies

By Directory

Assign each implementer ownership of specific directories:

implementer-1: src/components/auth/
implementer-2: src/api/auth/
implementer-3: tests/auth/

Best for: Well-organized codebases with clear directory boundaries.

By Module

Assign ownership of logical modules (which may span directories):

implementer-1: Authentication module (login, register, logout)
implementer-2: Authorization module (roles, permissions, guards)

Best for: Feature-oriented architectures, domain-driven design.

By Layer

Assign ownership of architectural layers:

Sponsors

Details

Repository
github.com/wshobson/agents
Categories
DevOps & CI/CD, Git & Pull Requests, AI & Agent Building, Automation & Workflows, Rust

More from wshobson/agents

All 174
1wshobson avatartask-coordination-strategieswshobson/agentsDecompose complex tasks, design dependency graphs, and coordinate multi-agent work with proper task descriptions and workload balancing. Use this skill when bre10.2Kskills.sh installs
2okx avatarokx-cex-botokx/agent-skillsManage Grid bots (spot/contract/coin-margined) and DCA Martingale bots (Spot DCA 现货马丁 / Contract DCA 合约马丁) on OKX. Covers create, stop, amend, monitor P&L, TP/S10.2Kskills.sh installs
3ljagiello avatarctf-pwnljagiello/ctf-skillsProvides binary exploitation techniques for CTF challenges. Use when you already have a vulnerable native target or service and need to turn memory corruption o10.1Kskills.sh installs
4langchain-ai avatarmanaged-deep-agentslangchain-ai/langchain-skillsINVOKE THIS SKILL when building, testing, or deploying Managed Deep Agents in LangSmith with the mda CLI. Covers the code-first, file-based project layout; defi10Kskills.sh installs
5figma avatarfigma-usefigma/mcp-server-guide**MANDATORY prerequisite** — you MUST invoke this skill BEFORE every `use_figma` tool call. NEVER call `use_figma` directly without loading this skill first. Sk9.8Kskills.sh installs
6ljagiello avatarctf-forensicsljagiello/ctf-skillsProvides digital forensics and signal analysis techniques for CTF challenges. Use when analyzing disk images, memory dumps, event logs, network captures, crypto9.7Kskills.sh installs