Navigation and decision-making framework for autonomous agents.
Scanned 9/2/2026
Install to Claude Code
Skills Directorynpx -y skills add majiayu000/claude-skill-registry --skill agentic-compass --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Agentic Compass?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/majiayu000-agentic-compass-claude-skill-registry)More formats (shields.io, HTML) on the badges page.
---
name: agentic-compass
version: 1.0.0
description: Navigation and decision-making framework for autonomous agents.
metadata:
openclaw:
emoji: 🧭
category: productivity
---
# Agentic Compass
Navigation and decision-making framework for autonomous agents.
## Purpose
Helps agents make decisions about:
- Which skill to use
- When to ask for clarification
- How to prioritize tasks
- When to escalate to user
## Decision Matrix
| Situation | Action |
|-----------|--------|
| High confidence + Low risk | Execute autonomously |
| Low confidence + Low risk | Try, report outcome |
| High confidence + High risk | Ask for confirmation |
| Low confidence + High risk | Ask before acting |
## Usage
Use this skill when facing ambiguous situations requiring judgment calls.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
