using-agent-skills

Discovers and routes tasks to the appropriate engineering workflow skill.

Updated Sep 8, 2026
One-click install
npx skills add https://github.com/sasidhar4444/ai-receptionist --skill using-agent-skills-sasidhar4444
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: using-agent-skills
Source: https://github.com/sasidhar4444/ai-receptionist/tree/main/agent-skills/skills/using-agent-skills
Command: npx skills add https://github.com/sasidhar4444/ai-receptionist --skill using-agent-skills-sasidhar4444

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Engineering agents often start work without a defined process, leading to wrong assumptions, skipped verification, and scope creep. This meta-skill provides a decision framework that maps any incoming task to the correct workflow skill and enforces core operating behaviors across all of them. ## Core Features & Use Cases - Skill Discovery Flowchart: A decision tree routes tasks by development phase (define, plan, build, verify, review, ship) to one of 23 specialized skills such as spec-driven-development or test-driven-development. - Core Operating Behaviors: Six non-negotiable rules covering surfacing assumptions, managing confusion, pushing back on bad ideas, enforcing simplicity, maintaining scope discipline, and verifying results. - Lifecycle Sequencing: A canonical 16-step skill chain for full features, plus guidance on which subsets apply to smaller tasks like bug fixes. - Use Case: A developer receives a vague feature request. The meta-skill routes them to interview-me, then spec-driven-development, then planning-and-task-breakdown before any code is written. ## Quick Start Ask the agent to identify which skill applies to your current task and follow that skill's workflow steps in order.

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 engineering skill to use for a task?▼

Use the decision tree in this meta-skill: identify your development phase (define, plan, build, verify, review, or ship), then follow the branch matching your situation. For example, implementing code routes to incremental-implementation, while a broken feature routes to debugging-and-error-recovery.

What is the correct skill sequence for building a full feature?▼

The canonical lifecycle runs interview-me, idea-refine, spec-driven-development, planning-and-task-breakdown, context-engineering, source-driven-development, incremental-implementation, test-driven-development, code-review-and-quality, code-simplification, git-workflow-and-versioning, documentation-and-adrs, and shipping-and-launch.

Can multiple agent skills apply to one task?▼

Yes, multiple skills can apply and often chain in sequence. A bug fix might only need debugging-and-error-recovery, test-driven-development, and code-review-and-quality, while a full feature uses most of the lifecycle.

What should I do when requirements are unclear or conflicting?▼

Stop and do not proceed with a guess. Name the specific confusion, present the tradeoff or ask the clarifying question, and wait for resolution. Silently picking one interpretation is listed as a failure mode.

When is a task considered complete under these skills?▼

A task is complete only when verification passes with concrete evidence such as passing tests, build output, or runtime data. The project-wide Definition of Done requires tests passing, no regressions, runtime-verified behavior, and updated docs.