Agent skill

subagent-driven-development

Use when executing implementation plans. Dispatches independent subagents for individual tasks with code review checkpoints between iterations for rapid, controlled development.

View SKILL.md on GitHub Repository
Stars 7
Forks 1

Install this agent skill to your Project

npx add-skill https://github.com/Bbeierle12/Skill-MCP-Claude/tree/main/skills/subagent-driven-development

SKILL.md

Subagent-Driven Development

Core Principle

Fresh context per task. Review between tasks.

Each task gets a clean subagent with no accumulated confusion. You review between tasks.

How It Works

  1. Load the implementation plan
  2. For each task:
    • Dispatch fresh subagent
    • Subagent implements ONLY that task
    • Review the changes
    • Approve or request fixes
    • Move to next task

Benefits

  • Clean Context: Each subagent starts fresh
  • Focused Work: One task at a time
  • Review Points: Catch issues early
  • Controlled Progress: You stay in charge

Execution Flow

Step 1: Load the Plan

markdown
Loading plan from: docs/plans/YYYY-MM-DD-feature-name.md

Tasks identified:
1. [ ] Task 1: Description
2. [ ] Task 2: Description
3. [ ] Task 3: Description

Starting with Task 1...

Step 2: Dispatch Subagent

For each task, create a focused prompt:

markdown
## Task: [Task Name]

### Context
- Project: [brief description]
- Current branch: [branch name]
- Dependencies: [relevant info]

### Instructions
[Exact instructions from plan]

### Files to Modify
- `path/to/file.ts`

### Test to Write First
[Test code from plan]

### Implementation
[Implementation code from plan]

### Success Criteria
- [ ] Test passes
- [ ] No other tests broken
- [ ] Code follows project style

Step 3: Review Changes

After subagent completes:

markdown
## Task 1 Complete

### Changes Made:
- Modified: `path/to/file.ts` (+25/-3)
- Added: `path/to/file.test.ts` (+40)

### Test Results:
✅ All tests passing (47 total)

### Review Checklist:
- [ ] Test covers the requirement
- [ ] Implementation is correct
- [ ] No unnecessary changes
- [ ] Code style matches project

**Approve and continue to Task 2?**

Step 4: Handle Issues

If review finds problems:

markdown
## Issues Found in Task 1

1. Test doesn't cover edge case X
2. Missing error handling for Y

**Options:**
A) Request fixes from subagent
B) Fix manually
C) Skip and note for later

Which approach?

Subagent Guidelines

What Subagents Should Do

  • Follow the plan exactly
  • Write tests first
  • Make minimal changes
  • Report what was done

What Subagents Should NOT Do

  • Make "improvements" outside scope
  • Skip tests
  • Refactor unrelated code
  • Change the plan

Progress Tracking

Maintain task status:

markdown
## Progress: Feature Name

- [x] Task 1: Setup database schema ✅
- [x] Task 2: Create API endpoint ✅
- [ ] Task 3: Add validation (IN PROGRESS)
- [ ] Task 4: Write integration tests
- [ ] Task 5: Update documentation

Current: Task 3 of 5

Checkpoints

After Each Task

  • Run all tests
  • Review diff
  • Commit if approved

After All Tasks

  • Run integration tests
  • Manual verification
  • Final review

Rollback

If things go wrong:

bash
# Revert last task
git revert HEAD

# Or reset to checkpoint
git reset --hard <commit-before-task>

Communication Pattern

Starting

"I'm using subagent-driven-development to implement [feature]. I'll dispatch a fresh subagent for each task and review between them."

Between Tasks

"Task [N] complete. Changes: [summary]. Ready to review before Task [N+1]?"

Completing

"All [N] tasks complete. Running final verification..."

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

Bbeierle12/Skill-MCP-Claude

r3f-materials

Three.js materials in R3F, built-in materials (Standard, Physical, Basic, etc.), ShaderMaterial with custom GLSL, uniforms binding and animation, and material properties. Use when choosing materials, creating custom shaders, or binding dynamic uniforms.

7 1
Explore
Bbeierle12/Skill-MCP-Claude

audio-router

Router for audio domain including playback, analysis, and audio-reactive visuals. Use when implementing any audio functionality including music, sound effects, visualizers, or audio-driven animations. Routes to 3 specialized skills.

7 1
Explore
Bbeierle12/Skill-MCP-Claude

case-studies-reference

Game building mechanics case studies and decision frameworks. Use when designing building systems, evaluating trade-offs, or learning from existing games. Reference-only skill with detailed analysis of Fortnite, Rust, Valheim, Minecraft, No Man's Sky, and Satisfactory building systems.

7 1
Explore
Bbeierle12/Skill-MCP-Claude

brainstorming

Use when starting any feature, project, or design work. Guides collaborative design refinement through incremental questioning before any code is written.

7 1
Explore
Bbeierle12/Skill-MCP-Claude

shader-router

Decision framework for GLSL shader projects. Routes to specialized shader skills (fundamentals, noise, SDF, effects) based on task requirements. Use when starting a shader project or needing guidance on which shader techniques to combine.

7 1
Explore
Bbeierle12/Skill-MCP-Claude

audio-playback

Audio playback using Tone.js including players, transport, scheduling, and loading audio. Use when implementing background music, sound effects, audio synchronization, or timed audio events. Essential for any audio-enabled web application.

7 1
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results