🛡️ Code Execution, Verification & Cleaning Skills

Reusable AI skills for a four-stage code workflow—planning, execution/building, verification, and review—plus verification, cleanup, runtime auditing, and security-focused review.

---

📋 Table of Contents

• Purpose
• Four-Stage Workflow
• Features
• Getting Started
• Skills.sh Listing
• Repository Structure
• Core Principles
• Workflow
• Resources
• License

---

🎯 Purpose

These skills guide AI agents through an explicit delivery workflow and empower them to:

Need	Owning sub-skill
Remove dead code, duplication, and unnecessary complexity	Clean Code
Run builds, tests, linters, and formatting checks	Code Verification
Inspect a running frontend with browser DevTools	Runtime Auditing
Review injection risks, exposed tokens, and client-side security issues	Security Review
Perform the complete scan, cleanup, verification, and reporting workflow	Code Verification & Cleaning bundle

---

🧭 Four-Stage Workflow

Use skills/code-execution-skill/ to coordinate every change through these ordered stages. Each stage has a required input and produces the handoff artifact required by the next stage.

Stage	Input	Output / handoff
1. Planning	Change request and repository context	Approved plan covering scope, approach, risks, acceptance criteria, and planned checks.
2. Execution / Building	Approved plan	Implementation summary recording completed work, changed files, build results, deviations, and known risks.
3. Verification	Implementation summary and changed code	Verification results with lint, test, runtime, security, and reporting evidence.
4. Review	Implementation summary and verification results	Final review findings with structural, security, and evidence-based disposition.

Shared verification and review skill

Both verification and review use the existing skills/code-verify-and-clean-skill/ skill. Do not move or rewrite that skill; it remains the shared source of truth.

• Verification follows its linting, tests, runtime checks, security checks, and reporting workflow. Record the commands, outcomes, evidence, remaining risks, and proceed/return recommendation in the verification results.
• Review follows its structural-cleanup standards, security-review guidance, review template, and verification evidence requirements. Record blocking issues, follow-ups, residual risks, and final disposition in the final review findings.

A change is complete only after all four artifacts are preserved: approved plan, implementation summary, verification results, and final review findings.

---

✨ Features

• Clean Code — owns dead-code removal, duplicate-code reduction, simplification, and modularity improvements.
• Code Verification — owns compilation, tests, linting, formatting, and other automated quality gates.
• Runtime Auditing — owns browser-based validation, console inspection, network checks, and UI runtime diagnostics.
• Security Review — owns security-focused review for injection points, credential exposure, and client-side risks.
• Code Verification & Cleaning — the optional bundle that combines every sub-skill and coordinates the end-to-end reporting workflow.

---

🚀 Installation

Install the smallest sub-skill that covers the task. For example, install Clean Code by itself:

Code Verification & Cleaning

npx skills add abozezo-dev/Code-Quality-Skill/clean-code

Project Planning

npx skills add abozezo-dev/Code-Quality-Skill/code-execution-skill

# Add the shared verification and review skill
npx skills add abozezo-dev/Code-Quality-Skill/code-verify-and-clean-skill

Quick Start

1. Add code-execution-skill and the shared code-verify-and-clean-skill to your AI agent configuration
2. Create and approve a plan, then implement and build the change
3. Use the existing verification-and-cleaning skill for verification and review
4. Preserve the four required handoff artifacts

---

🔗 Skills.sh Listing

View these skills on skills.sh:

• Code Execution Skill
• Code Verification & Cleaning Skill
• Project Planning Skill

The repository page is customized with skills.sh.json, and both skills live under skills/ for a clean skills.sh-compatible layout.

---

📁 Repository Structure

Code-Quality-Skill/
├── skills/
│   ├── code-execution-skill/
│   │   └── SKILL.md                            # Four-stage delivery workflow
│   └── code-verify-and-clean-skill/
│       ├── assets/                             # Bundle report and review templates
│       ├── reference/                          # Bundle workflow guides
│       ├── scripts/                            # Bundle automation
│       └── SKILL.md                            # All-in-one workflow
├── .github/workflows/ci.yml                    # CI checks
├── skills.sh.json                              # skills.sh repository configuration
├── LICENSE                                     # MIT license
└── README.md                                   # You are here

Each directory above links to its own SKILL.md: Clean Code, Code Verification, Runtime Auditing, Security Review, and the all-in-one bundle.

---

🧠 Core Principles

1. Trust But Verify — Code Verification and Runtime Auditing

Do not treat code that looks correct as code that is correct. Code Verification executes builds, tests, and static checks; Runtime Auditing validates the running application, including browser console output and network activity.

2. Keep Code Lean — Clean Code

Clean Code keeps codebases maintainable by pruning unused components, imports, and variables; reducing duplication; and simplifying complex logic into explicit, reusable modules.

3. Treat Security Findings as First-Class — Security Review

Security Review identifies injection opportunities, exposed tokens, and client-side exposure risks before they become production issues.

4. Use Clear Severity Tiers — All-in-One Bundle

The Code Verification & Cleaning bundle uses consistent markers when coordinating multiple sub-skills:

Marker	Meaning	Action
🔴 [breaking-error]	Code crashes, fails checks, or breaks a workflow	Blocks merge
🟡 [code-smell]	Code works but adds debt or avoidable complexity	Schedule remediation
🟢 [refactored]	A cleanup was applied and verified	Already resolved

---

⚙️ Workflow

1. Clean Code removes obvious dead code, duplication, and structural bloat.
2. Code Verification runs the repository's native build, test, lint, and formatting commands.
3. Runtime Auditing validates changed frontend behavior in a live browser when applicable.
4. Security Review checks the changed surface for security risks.
5. The all-in-one bundle coordinates the full workflow and records the pre-change SCAN.md and post-change REPORT.md when comprehensive reporting is required.

---

📚 Resources

The optional bundle supplies shared workflow resources; use the indicated sub-skill for the capability each resource supports.

Resource	Capability owner	Description
Code Cleaning Standards	Clean Code	Cleaning standards and patterns for reducing technical debt.
DevTools Verification Guide	Runtime Auditing	Browser, layout, console, and network-audit guidance.
Security Verification Guide	Security Review	Security checks for injection and client-side exposure.
Reporting Workflow Guide	Code Verification & Cleaning bundle	SCAN.md and REPORT.md workflow and evidence standards.
Verification Checklist	Code Verification	Checklist for automated verification gates.
Review Template	Security Review	Consistent review findings and remediation notes.
SCAN.md Template	Code Verification & Cleaning bundle	Baseline report template before modifications.
REPORT.md Template	Code Verification & Cleaning bundle	Final report template after remediation and validation.

---

Reporting workflow

This project is licensed under the MIT License.

---

Made with ❤️ by abozezo-dev