Skip to main content
Skills can be invoked three ways: auto-triggered by the LLM from the system-prompt listing, manually by the user via /skill-name slash commands, or programmatically through SkillManager.invoke().
This page covers the invocation layer added in v1.5+. For how to author skills, see Agent Skills.

​
How invocation works

Auto-trigger

Skill description is included in the system prompt. The LLM decides when to follow it.

Slash command

/deploy staging renders the skill body with $ARGUMENTS substituted and short-circuits the LLM call path.

​
Argument substitution

Inside SKILL.md bodies you can reference arguments passed after the skill name: 
Deploy $ARGUMENTS now.
/deploy staging prod becomes Deploy staging prod now.

​
Inline shell substitution

Disabled by default. Skills that embed !`cmd` blocks render as [shell execution disabled] until you explicitly opt in.
from praisonaiagents.skills import SkillManager

mgr = SkillManager()
mgr.add_skill("./skills/pr-summary")
rendered = mgr.invoke("pr-summary", raw_args="42", shell_exec=True)

Current branch: !`git rev-parse --abbrev-ref HEAD`

```!
node --version
npm --version
```

​
Invocation policy

​
disable-model-invocation
boolean
default:"false"
When true the skill is hidden from the system-prompt listing, so the LLM cannot auto-trigger it. Users can still invoke it via /skill-name. Use for side-effecting commands like /deploy.
​
user-invocable
boolean
default:"true"
When false the slash-router ignores the skill. Use for background knowledge you want auto-triggered by the LLM but not exposed as a user command.

​
Allowed tools pre-approval

​
allowed-tools
string | list[str]
Space-separated string (Read Grep) or YAML list. When a user invokes the skill, those tool names are pre-approved via the approval registry for the current agent so the LLM can run them without the interactive confirmation prompt.

​
Python API

from praisonaiagents import Agent

agent = Agent(
    name="assistant",
    skills=["./skills/deploy"],
)

# Slash command
agent.start("/deploy staging prod")

# Or directly
rendered = agent.skill_manager.invoke("deploy", raw_args="staging prod")

​
YAML

# agents.yaml
agents:
  assistant:
    role: Helper
    goal: Help the user
    backstory: You are helpful.
    skills:
      - ./skills/deploy
      - ~/.praisonai/skills/csv-summary

​
CLI

praisonai skills list
Set PRAISONAI_DISABLE_SKILL_TOOLS=1 to stop the agent from auto-injecting run_skill_script and read_file when skills are configured. Useful for hermetic tests and hosts that want full control over the tool surface.

​
Precedence

Skills are discovered in this order (first wins on name collision):
1

Project

./.praisonai/skills/ or ./.claude/skills/
2

Ancestors

Every .praisonai/skills or .claude/skills in a parent directory (monorepo support)
3

User

~/.praisonai/skills/
4

System

/etc/praison/skills/
Collisions are logged at INFO level so you can see which skill won.

​
See also