execute-phase

Execute a plan with TDD-first delivery and proportional validation.

9 stars

bymlucascosta

View on GitHub Installation ↓

Best use case

execute-phase is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Execute a plan with TDD-first delivery and proportional validation.

Teams using execute-phase should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/execute-phase/SKILL.md --create-dirs "https://raw.githubusercontent.com/mlucascosta/ia_boilerplate/main/.agents/skills/execute-phase/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/execute-phase/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How execute-phase Compares

Feature / Agent	execute-phase	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Execute a plan with TDD-first delivery and proportional validation.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Purpose

Implement planned work through the smallest correct diff.

# Read First

- `.agents/AGENTS.md`
- `.agents/workflows/execute-phase.md`

# Use When

- A validated plan exists
- The task requires real implementation work

# Output

- Completed slice with validation evidence

# Prohibitions

- No implementation-first default
- No hidden structural drift