Skills
Skills are the core building blocks of Hubify — executable instructions that tell AI agents how to perform specific tasks.What is a Skill?
A skill is a structured document that contains:- Instructions — Step-by-step guidance for the agent
- Context — When and where to apply the skill
- Examples — Concrete demonstrations
- Metadata — Classification, trust metrics, lineage
Skill Structure
Every skill has these components:1. Overview
What the skill does and why it exists:2. When to Apply
Context for when the skill is relevant:3. Instructions
The core guidance, typically as numbered steps:4. Examples
Concrete code examples showing the skill in action:Advanced Usage
Skill Metadata
Skills include rich metadata in YAML frontmatter:Trust Metrics
Every skill has trust metrics computed from real execution data:| Metric | Description | Range |
|---|---|---|
confidence | Overall reliability | 0.0 - 1.0 |
executions | Total execution count | 0+ |
success_rate | Percentage of successful executions | 0% - 100% |
unique_agents | Different agents that used it | 0+ |
unique_platforms | Platforms it’s been used on | 0+ |
verification_level | Trust tier | 0-3 |
trend | Direction of confidence | improving/stable/declining |
Verification Levels
| Level | Name | Requirements |
|---|---|---|
| 0 | Untested | Schema validation only |
| 1 | Sandbox | Passed E2B sandbox testing |
| 2 | Field | 50+ successful executions |
| 3 | Battle-tested | 500+ executions, 90%+ success rate |
Finding Skills
Search by Keyword
Search with Filters
Browse Categories
Installing Skills
Local Installation
.hubify/skills/ in your project.
Global Installation
~/.hubify/skills/ for all projects.
With Confidence Threshold
Using Skills
Once installed, skills are automatically available to your AI agent.Implicit Usage
Your agent automatically applies relevant skills based on context:Explicit Reference
You can explicitly request a skill:Skill Categories
| Category | Description |
|---|---|
coding | Programming patterns and practices |
testing | Test writing and execution |
documentation | Documentation generation |
devops | CI/CD and deployment |
api | API design and integration |
security | Security patterns |
frontend | Frontend development |
backend | Backend development |
database | Database operations |
data | Data processing |
Skill Complexity
| Level | Description | Examples |
|---|---|---|
basic | Simple, focused patterns | Naming conventions, basic error handling |
intermediate | Multi-step patterns | API design, testing strategies |
advanced | Complex, architectural patterns | System design, performance optimization |
Skill Lineage
Skills track their evolution history:Skill Dependencies
Some skills depend on or recommend others:Creating Skills
Create your own skills:Skill Evolution
Skills improve automatically through collective learning:- Agents execute and report results
- Improvements aggregate across reports
- At threshold (3+ similar suggestions), evolution triggers
- New version drafted, tested, deployed