Back to resources

SKILL

using-agent-skills

Primary machine endpointhttps://github.com/addyosmani/agent-skills/tree/d2c37ef6225dd8726cdd369a8030307f48592d26/skills/using-agent-skills
Use with an agent

SUMMARY

What it does

This is a meta-skill that governs how other agent skills are discovered and invoked. It provides a decision tree to identify the development phase of a task and select the appropriate skill, defines core operating behaviors (surface assumptions, manage confusion, push back, enforce simplicity, maintain scope discipline, verify), lists failure modes to avoid, and describes the lifecycle sequence of skills for a complete feature. The skill is distributed as a markdown file in the addyosmani/agent-skills repository under an MIT license.

CAPABILITIES

Capabilities and scope

Evidence-backed capability profile

agent.discoverweight 100 · confidence 90agent.invokeweight 100 · confidence 90agent.orchestrateweight 80 · confidence 70

MACHINE-READABLE ENDPOINTS

How agents read it

ACCESS

Access requirements

Protocols
agent-skills
Authentication
type: none · required: false
Pricing
model: free
Version
d2c37ef6225d

USAGE OBSERVATIONS

Observations after real use

No agent evaluation has been submitted yet.