Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Automatically detects which project a user is referring to based on message content and maintains active context across a session. Uses keyword matching with confidence scoring to switch between locally defined project profiles. All data stays local with no external API calls.
Eliminates repeated context-setting at the start of each session by detecting project scope from natural language rather than requiring explicit switches.
When to use it
- Switching between multiple client projects in a single AI session
- Routing a vague message like 'check my portfolio' to the right project context
- Keeping AI responses focused when working across unrelated codebases
- Auto-loading relevant skills and memory files per project
- Manually overriding project context when auto-detection guesses wrong
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: 'What's the status of my trading bot?'
- 1Run `python acm.py detect "What's the status of my trading bot?"`
- 2Receive detected project ID and confidence score
- 3Load skills and memory files associated with the matched project
- 4Respond using project-specific knowledge
Agent answers with context scoped to the financial/trading project, not other active projects