Skip to main content

​
Overview

Beyond basic skill loading, the Skills system provides advanced features for production use:
FeatureDescription
CachingIn-memory TTL cache for skill content
Auto-SelectionEmbedding-based skill relevance filtering
DependenciesDeclare and validate inter-skill dependencies
VersioningSemantic versioning and constraint filtering
CallbacksHook into skill load, reference, and script events
Safety PoliciesContent filtering via the safety engine
Knowledge BaseSemantic search across skill references via RAG

​
Skills Constructor Reference

All advanced features are configured via the Skills constructor: 
from upsonic.skills import Skills, LocalSkills

skills = Skills(
    loaders=[LocalSkills("./my-skills")],     # Required — skill sources
    strict_deps=False,                         # Raise on dependency issues
    cache_ttl=300,                             # Cache TTL in seconds (None = disabled)
    on_load=my_load_callback,                  # Callback on skill load
    on_script_execute=my_script_callback,      # Callback on script execution
    on_reference_access=my_ref_callback,       # Callback on reference access
    auto_select=True,                          # Enable embedding-based selection
    max_skills=5,                              # Max skills in system prompt
    embedding_provider=my_provider,            # Provider for auto-select
    policy=my_safety_policy,                   # Safety policy or list of policies
)

​
Merging Skills

Combine multiple Skills instances into one: 
from upsonic.skills import Skills, LocalSkills, BuiltinSkills

base = Skills(loaders=[BuiltinSkills()])
custom = Skills(loaders=[LocalSkills("./custom")])

merged = Skills.merge(base, custom)
# Later instances override on name conflict

​
Tool Binding

Skills can declare which external tools they work best with: 
# In SKILL.md frontmatter
allowed-tools:
  - code_execution
  - file_search
Access the union of allowed tools from all actively used skills: 
active_tools = skills.get_active_skill_tools()
# Returns: {'code_execution', 'file_search'}
A skill becomes “active” when the agent calls get_skill_instructions() for it.