playbooks

home / skills / jeremylongshore / claude-code-plugins-plus-skills / overnight-development

overnight-development skill

/plugins/productivity/overnight-dev/skills/overnight-development

This skill automates overnight software development by enforcing test-driven development through git hooks, ensuring commits meet quality standards and reduce

npx playbooks add skill jeremylongshore/claude-code-plugins-plus-skills --skill overnight-development

Review the files below or copy the command above to add this skill to your agents.

Files (8)
SKILL.md
1.7 KB
---
name: overnight-development
description: Automates software development overnight using git hooks to enforce test-driven Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
version: 1.0.0
allowed-tools: "Read, Write, Edit, Grep, Glob, Bash(general:*), Bash(util:*)"
license: MIT
author: Jeremy Longshore <[email protected]>
---

# Overnight Development

## Overview

This skill automates software development overnight by leveraging Git hooks to enforce test-driven development (TDD). It ensures that all code changes are fully tested and meet specified quality standards before being committed. This approach allows Claude to work autonomously, building new features, refactoring existing code, or fixing bugs while adhering to a rigorous TDD process.

## Prerequisites

- Access to project files in {baseDir}/
- Required tools and dependencies installed
- Understanding of skill functionality
- Permissions for file operations

## Instructions

1. Identify skill activation trigger and context
2. Gather required inputs and parameters
3. Execute skill workflow systematically
4. Validate outputs meet requirements
5. Handle errors and edge cases appropriately
6. Provide clear results and next steps

## Output

- Primary deliverables based on skill purpose
- Status indicators and success metrics
- Generated files or configurations
- Reports and summaries as applicable
- Recommendations for follow-up actions

## Error Handling

See `{baseDir}/references/errors.md` for comprehensive error handling.

## Examples

See `{baseDir}/references/examples.md` for detailed examples.

## Resources

- Official documentation for related tools
- Best practices guides
- Example use cases and templates
- Community forums and support channels

Overview

This skill automates overnight software development by using Git hooks and a test-driven development (TDD) workflow to produce safe, test-covered changes while you sleep. It enforces tests, runs linters, and applies configurable quality gates so commits meet project standards before being pushed. The goal is autonomous, auditable progress on features, refactors, or bug fixes with clear outputs and next steps.

How this skill works

When triggered by configured phrases or contextual signals, the skill scans the codebase and applies a TDD loop: create failing tests, implement code to satisfy tests, run full test suites, and fix regressions. Git hooks enforce pre-commit and pre-push checks; failures abort commits and generate actionable reports. Outputs include changed files, test results, status indicators, and recommended follow-ups.

When to use it

  • Add or iterate on low-risk features outside core architecture when human review can follow
  • Perform scheduled refactors and technical debt reduction during non-production hours
  • Run targeted bug fixes that have clear reproducible tests and minimal external dependencies
  • Automate repetitive test-writing and scaffolding tasks to accelerate development
  • Enforce continuous quality gates before merging long-running branches

Best practices

  • Limit overnight changes to well-scoped tickets with clear acceptance criteria
  • Require test reproducibility locally before enabling autonomous runs
  • Use feature flags or isolated branches to avoid affecting production traffic
  • Configure strict but pragmatic quality gates (tests, linting, security scans)
  • Maintain comprehensive logging and human-review checkpoints for high-risk changes

Example use cases

  • Generate unit tests and implement straightforward functions to satisfy new API contracts
  • Refactor a module with full test coverage and produce a summary of changes for PR review
  • Fix a flaky test by reproducing the failure, patching the code, and adding regression tests
  • Apply consistent formatting and lint rules across the codebase and create a cleanup PR
  • Scaffold integration tests for a new service and produce status reports for reviewers

FAQ

What prerequisites are required to run the skill?

You need repository access, installed tools and dependencies, and file operation permissions. Ensure local tests run before enabling autonomous operation.

How does the skill handle failing tests or errors?

Git hooks abort commits on failures, log errors, and produce a report with reproduction steps and recommended fixes for human review.