intent-and-automation
Installation
SKILL.md
Skill: TraceMem Intent and Automation Modes
Purpose
This skill explains how to choose the correct intent and automation_mode for a Decision Envelope. Correct classification is critical for potential policy checks and audit clarity.
⚠️ VALID AUTOMATION MODES - ONLY THESE 4 VALUES
When calling decision_create, the automation_mode parameter MUST be one of these exact values:
| Mode | Description | Use When |
|---|---|---|
propose |
Agent suggests, human decides | You're gathering info or proposing actions |
approve |
Agent executes after approval | You need human confirmation before acting |
override |
Human overrides policy | Breaking rules with explicit permission |
autonomous |
Agent acts independently | Fully automated within policy bounds |
INVALID values (these will cause errors):
- ❌
manual,auto,full_auto,automated - ❌
assisted,interactive,human_required
Related skills
More from tracemem/tracemem-skills
traces-and-audit
Auditing memory traces and debugging.
17approvals
Guidelines for seeking user approval for sensitive actions.
16notes-and-context
Managing context and notes within the memory system.
16decision-envelope
Using the decision envelope pattern for structured thinking.
15overview
Overview of TraceMem core features, rules, and best practices.
14writing-data
Instructions for writing and efficiently storing data in TraceMem.
14