HalosHalosDocs

Skills & Trust

Skills determine what your agents can do. Trust tiers determine what they're allowed to do. Together they form a progressive permission system where agents earn capabilities over time.

Skills

Skills are modular capabilities that you install on individual agents. They come from ClawHub, the OpenClaw skill marketplace with 5,700+ available skills.

How Skills Work

Each agent starts with a default set of skills based on its specialty:

| Agent Type | Default Skills | |-----------|---------------| | Email | Email Triage, Draft Replies, Smart Labels | | Calendar | Schedule Management, Conflict Detection, Smart Reminders | | Research | Web Search, Article Summary, Trend Tracking | | Code | Code Review, Debugging, Code Generation |

You can install additional skills from the Skills library or remove ones you don't need.

Skill XP

Each skill has its own XP and level, separate from the agent's overall level. Skills level up as the agent uses them:

  • Level 1 — Basic capability
  • Level 5 — Proficient
  • Level 10 — Expert

Higher skill levels mean the agent has more experience with that particular capability.

Installing & Removing Skills

From the Skills page in the app:

  1. Browse available skills by category
  2. Tap a skill to see its description
  3. Choose which agent to install it on
  4. The skill is available immediately

If the agent's container is running, skills are hot-installed without a restart. Otherwise they load on next wake.

Trust Tiers

Trust tiers are a progressive permission system. Every agent starts at the lowest tier and can be promoted as you build confidence in its behavior.

The Four Tiers

Observer (Default)

The starting tier for all new agents.

  • Can: Read and observe data, summarize, analyze, suggest actions
  • Cannot: Modify, send, delete, or create anything
  • Philosophy: Look but don't touch

This is intentionally restrictive. A brand-new agent should prove it understands your needs before it gets more power.

Helper

The first promotion. The agent can now assist more actively.

  • Can: Read data, draft content, organize, label, categorize
  • Cannot: Send, publish, or delete without your explicit approval
  • Philosophy: Prepare but don't execute

At this tier, an email agent can draft replies for you to review, but can't send them on its own.

Partner

A significant trust upgrade. The agent can act autonomously on routine tasks.

  • Can: Act autonomously on low-risk, routine tasks. Send pre-approved types of responses.
  • Cannot: Message new contacts, take financial actions, or delete without approval
  • Philosophy: Handle the routine, escalate the unusual

At this tier, your calendar agent might automatically accept recurring meeting invites but still ask before scheduling with a new contact.

Trusted

The highest tier. Near-full autonomy.

  • Can: Act autonomously on most tasks
  • Cannot: Bulk deletions, purchases, or external sharing without approval
  • Philosophy: Full trust with safety rails

Even at this level, destructive or high-stakes actions still require your sign-off.

Permissions

Within each trust tier, individual permissions provide granular control. Permissions are specific capabilities that unlock at certain agent levels.

How Permissions Work

Each agent type has a set of permissions that unlock progressively:

Email Agent Example:

| Permission | Unlock Level | Description | |-----------|-------------|-------------| | Read data | Level 1 | Access and read connected accounts | | Summarize | Level 1 | Create summaries and digests | | Suggest actions | Level 1 | Recommend actions for approval | | Draft replies | Level 3 | Write reply drafts for review | | Apply labels | Level 5 | Organize emails with labels | | Send emails | Level 8 | Send emails on your behalf | | Delete emails | Level 15 | Delete or archive emails |

Locked permissions show a lock icon on the agent's profile. As the agent levels up through XP, new permissions unlock — but they're still off by default. You choose which unlocked permissions to enable.

Enabling Permissions

On the agent's profile page, scroll to the Permissions section. Each permission has a toggle:

  • Locked (grayed out) — Agent hasn't reached the required level yet
  • Unlocked, disabled — Available but not turned on
  • Unlocked, enabled — Active and the agent can use it

This two-layer system (level-gating + manual toggle) means you're always in control.

Agent Leveling

Agents gain XP by completing tasks and earn levels over time.

How XP Works

  • Completing a task: +10 XP
  • XP required scales with level: 100 + (level x 50) XP per level
  • Level 1 needs 100 XP, Level 2 needs 150 XP, Level 3 needs 200 XP, etc.

What Leveling Unlocks

  • New permissions become available (see above)
  • The agent's profile shows its level and XP progress bar
  • Higher levels signal a more experienced, trusted agent

The Heartbeat

Each agent has a configurable heartbeat — a proactive check-in interval. When enabled, the agent periodically checks in with updates, summaries, or suggestions without being asked.

Heartbeat Intervals

You can set the interval on the agent's profile:

  • Disabled — Agent only responds when you message it
  • Every 15 minutes — Very frequent check-ins
  • Every hour — Balanced (default)
  • Every 8 hours — Twice a day
  • Once a day — Daily summary

What Heartbeats Do

During a heartbeat, the agent proactively:

  • Checks connected integrations for new data
  • Summarizes anything notable
  • Suggests actions you might want to take
  • Reports on completed background tasks

This is what makes agents proactive rather than just reactive. Your email agent can flag an urgent message before you even open your inbox.

Stats & Tracking

Every agent tracks its own performance:

  • Tasks completed — Total tasks the agent has handled
  • Time saved — Estimated minutes/hours saved for you
  • Accuracy — How often the agent gets it right

These stats appear on the agent's profile page and contribute to the platform-wide time-saved tracker in your settings.

Next Steps