sp-coding-agent

Extract missing context across 9 SP-categories before executing file changes.

32|16|Updated Jan 29, 2026

Search Tags:#codebase #prompt-engineering #coding-agent #context-extraction #smart-pole #plan-and-verify

Ready to run

npx skills add https://github.com/cuongpt083/smart-pole-skill --skill sp-coding-agent

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: sp-coding-agent
Source: https://github.com/cuongpt083/smart-pole-skill/tree/main/skills/sp-coding-agent
Command: npx skills add https://github.com/cuongpt083/smart-pole-skill --skill sp-coding-agent

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

The SMART POLE Coding Agent turns vague coding tasks into precise execution plans by applying the SMART POLE framework to code-native contexts, reducing ambiguity and misinterpretation before any code is touched.

Core Features & Use Cases

ORIENT: scans the project root to gather context
CLASSIFY: determines task type and primary SP-cats
EXTRACT: maps the user request to the 9 SP categories
DETECT FLAWS: identifies missing context, conflicts, and overlaps
PLAN: creates a concrete implementation plan with scoped file changes
EXECUTE: applies code changes with strict guardrails
VERIFY: runs linting, type checks, and tests; self-heals on failures
Use cases: clarifying vague coding tasks like "add pagination" or "refactor a module across multiple files"

Quick Start

Use the SMART POLE Coding Agent to orient the codebase, extract SP-atoms, and produce a test-ready plan before touching any files.

Frequently Asked Questions about sp-coding-agent

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I clarify vague coding tasks before the agent modifies files?▼

To clarify vague coding tasks, the agent scans the project root to orient, classifies the task type, and extracts missing context across 9 code-native categories to produce a test-ready plan before touching any files.

What is the best way to refactor a module across multiple files safely?▼

Refactoring a module across multiple files safely requires orienting the codebase, extracting context, and creating a concrete implementation plan with strict guardrails, ensuring the agent verifies file changes and self-heals on test failures.

How does context extraction work for codebase migrations?▼

Context extraction for codebase migrations works by mapping the user request to 9 SP-categories, detecting missing context, conflicts, and overlaps to satisfy deterministic mapping requirements before applying any code changes.

Can I use this coding agent for large refactors without providing detailed specifications?▼

Yes, you can use this coding agent for large refactors without detailed specifications because it applies the SMART POLE framework to identify missing context and generate deterministic, test-ready implementation plans automatically.

Why does my coding agent fail when executing vague requests like add pagination?▼

Coding agents fail executing vague requests like add pagination due to missing context and ambiguity; applying a plan-and-verify framework extracts necessary SP-categories and enforces guardrails before execution to prevent misinterpretation.

Do I need to set up testing frameworks before using a plan-and-verify coding agent?▼

You do not need to set up testing frameworks beforehand, as the agent's verify step runs linting, type checks, and tests after execution, self-healing on failures to ensure the implementation plan meets test-ready standards.