using-agent-skills

Discovers and routes tasks to the appropriate engineering workflow skill.

2|Updated Jul 6, 2026
One-click install
npx skills add https://github.com/NAMEWTA/learning-open-code --skill using-agent-skills-namewta
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: using-agent-skills
Source: https://github.com/NAMEWTA/learning-open-code/tree/main/translator/open-ai-skills/addyosmani-agent-skills/skills/using-agent-skills
Command: npx skills add https://github.com/NAMEWTA/learning-open-code --skill using-agent-skills-namewta

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? When working with a large collection of agent skills, it is hard to know which skill applies to the current task and in what order to combine them. This meta-skill acts as the discovery and routing layer that maps any incoming task to the correct engineering workflow skill. ## Core Features & Use Cases - Skill Discovery Decision Tree: Routes tasks by development phase (define, plan, build, verify, review, deliver) to one of 20+ skills such as spec-driven-development, test-driven-development, or code-review-and-quality. - Core Behavioral Rules: Enforces six non-negotiable practices across all skills, including exposing assumptions, managing confusion, disagreeing when necessary, enforcing simplification, keeping scope discipline, and verifying with evidence. - Lifecycle Sequencing: Defines the canonical skill chain for a full feature, from interview-me through shipping-and-launch, and shows how to trim it for smaller tasks like bug fixes. - Use Case: You receive a vague feature request. The skill routes you to interview-me to extract real requirements, then spec-driven-development, then incremental-implementation with test-driven-development, ending with code review and a safe launch checklist. ## Quick Start Describe your current task and ask which agent skill applies to it and in what order the skills should be combined.

Frequently Asked Questions about using-agent-skills

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

FAQPage Schema
How do I choose which agent skill to use for a task?▼

Identify the development phase your task belongs to, then follow the decision tree: unclear goals route to interview-me, new features to spec-driven-development, implementation to incremental-implementation, and failures to debugging-and-error-recovery.

Can multiple agent skills be combined in one workflow?▼

Yes, skills are designed to chain. A full feature typically runs interview-me, spec-driven-development, planning-and-task-breakdown, incremental-implementation, test-driven-development, code-review-and-quality, and shipping-and-launch in sequence.

What should I do when a task has no specification?▼

Start with spec-driven-development before writing any code. The skill rules state that any non-trivial task without a spec should begin there, since building without requirements is a listed failure mode.

When is it acceptable to skip skills in the lifecycle?▼

Not every task needs every skill. A bug fix may only require debugging-and-error-recovery, test-driven-development, and code-review-and-quality, while small changes can skip definition and planning phases entirely.

What are the most common failure modes when using agent skills?▼

The documented failure modes include acting on unchecked assumptions, ignoring confusion, sycophantic agreement with flawed plans, over-complicating solutions, touching unrelated code, and skipping verification because output looks correct.