🎯

subagent-driven-development

🎯Skill

from bbeierle12/skill-mcp-claude

What it does

Rapidly implement complex features by dispatching focused subagents for individual tasks with iterative code review checkpoints.

📦

Part of

bbeierle12/skill-mcp-claude(74 items)

subagent-driven-development

Installation

pip installInstall dependencies

pip install -r requirements.txt

PythonRun Python server

python skills_manager_api.py

PythonRun Python server

python server.py

pip installInstall Python package

pip install pyinstaller

PythonRun Python server

python -m PyInstaller --onefile --name "SkillsManager" --console ^

Server ConfigurationMCP server configuration block

{
  "name": "skill-name",
  "description": "One-line description",
  "tags": ["t...

📖 Extracted from docs: bbeierle12/skill-mcp-claude

Need more details? View full documentation on GitHub →

8Installs

AddedFeb 4, 2026

View on GitHub Back to Skills

Skill Details

SKILL.md

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

Overview

# 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

Load the implementation plan
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:

[ ] Task 1: Description
[ ] Task 2: Description
[ ] 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

Test doesn't cover edge case X
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

```

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..."

More from this repository10

🎯

gsap-react🎯Skill

gsap-react skill from bbeierle12/skill-mcp-claude

🎯

gsap-scrolltrigger🎯Skill

Enables advanced scroll-based animations and interactions using GSAP ScrollTrigger, allowing precise control of element animations triggered by scrolling.

🎯

gsap-fundamentals🎯Skill

gsap-fundamentals skill from bbeierle12/skill-mcp-claude

🎯

gsap-sequencing🎯Skill

gsap-sequencing skill from bbeierle12/skill-mcp-claude

🎯

shader-effects🎯Skill

shader-effects skill from bbeierle12/skill-mcp-claude

🎯

gsap-router🎯Skill

gsap-router skill from bbeierle12/skill-mcp-claude