What makes Self Improving Domotics notable?

1.1K downloads. Trust evidence available

How should Self Improving Domotics be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Self Improving Domotics

Captures smart-home automation conflicts, sensor drift, device connectivity failures, integration regressions, safety rule gaps, and energy optimization opportunities for continuous domotics improvement. Use when: (1) Automations conflict, loop, or misfire, (2) Sensors become stale or inaccurate, (3) Devices are unreachable or intermittently offline, (4) Cloud or local integrations break, (5) Occupancy detection is inconsistent with reality, (6) Latency causes delayed or jittery automations, (7) Energy usage patterns are inefficient, (8) Safety automations need stronger guardrails. Skill: Self Improving Domotics Owner: jose-compu Summary: Captures smart-home automation conflicts, sensor drift, device connectivity failures, integration regressions, safety rule gaps, and energy optimization opportunities for continuous domotics improvement. Use when: (1) Automations conflict, loop, or misfire, (2) Sensors become stale or inaccurate, (3) Devices are unreachable or intermittently offline, (4) Cloud

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

1.0.1

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.1release · observed Aug 28, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17bzpdy0evfmqz6nx069npr3n84p7f2:self-improving-house

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-jose-compu-self-improving-house/snapshot"

Documentation

CLAWHUB

84,050 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: self-improving-domotics
description: "Captures smart-home automation conflicts, sensor drift, device connectivity failures, integration regressions, safety rule gaps, and energy optimization opportunities for continuous domotics improvement. Use when: (1) Automations conflict, loop, or misfire, (2) Sensors become stale or inaccurate, (3) Devices are unreachable or intermittently offline, (4) Cloud or local integrations break, (5) Occupancy detection is inconsistent with reality, (6) Latency causes delayed or jittery automations, (7) Energy usage patterns are inefficient, (8) Safety automations need stronger guardrails."
---

# Self-Improving Domotics Skill

Log domotics-specific learnings, issues, and feature requests to markdown files for continuous improvement of smart home systems.

This skill is documentation and reminder guidance only. It does not execute physical actuator actions directly.

Always prefer safe defaults and human confirmation for high-impact routines involving door locks, alarms, gas or water shutoff, and heaters.

## First-Use Initialisation

Before logging anything, ensure `.learnings/` exists in the project or workspace root and contains the required files:

```bash
mkdir -p .learnings
[ -f .learnings/LEARNINGS.md ] || printf "# Domotics Learnings\n\nSensor reliability lessons, automation quality findings, integration regressions, safety gaps, and energy optimization observations.\n\n**Categories**: automation_conflict | sensor_drift | device_unreachable | integration_break | energy_optimization | safety_rule_gap | occupancy_mismatch | latency_jitter\n**Areas**: lighting | climate | security | access_control | energy | sensors | routines | voice_assistants | integrations | network\n\n---\n" > .learnings/LEARNINGS.md
[ -f .learnings/DOMOTICS_ISSUES.md ] || printf "# Domotics Issues Log\n\nRecurring smart-home failures, rule conflicts, unreliable sensors, unreachable devices, and safety-relevant incidents.\n\n---\n" > .learnings/DOMOTICS_ISSUES.md
[ -f .learnings/FEATURE_REQUESTS.md ] || printf "# Domotics Feature Requests\n\nAutomation, observability, reliability, and safety capability requests.\n\n---\n" > .learnings/FEATURE_REQUESTS.md
```

Never overwrite existing files. The commands are no-op when already initialised.

Do not log secrets, access tokens, lock PINs, alarm codes, network credentials, or personal household schedules in plain text.

If automatic reminders are needed, enable hook integration (opt-in) in [Hook Integration](#hook-integration).

## Quick Reference

| Situation | Action |
|-----------|--------|
| Two automations fire opposite commands | Log in `.learnings/DOMOTICS_ISSUES.md` as `automation_conflict` |
| Zigbee/Z-Wave devices intermittently disappear | Log issue as `device_unreachable` with radio and topology details |
| Occupancy says "home" while house is empty | Log learning as `occupancy_mismatch` and add confidence notes |
| HVAC oscillates around target temperature | Log learning a

_meta.json

{
  "ownerId": "kn78jat5kd20evgyxzp9dmryax84qap0",
  "slug": "self-improving-house",
  "version": "1.0.1",
  "publishedAt": 1787945176220
}

references/examples.md

# Domotics Entry Examples

Concrete examples for `LRN`, `DOM`, and `FEAT` entries.

## Example 1: Conflicting Automations (Lighting)

```markdown
## [DOM-20260413-001] hallway_light_conflict

**Logged**: 2026-04-13T19:10:00Z
**Priority**: high
**Status**: pending
**Area**: lighting

### Summary
Night motion routine turns hallway lights on while sleep routine turns them off every 20 seconds.

### Incident Timeline
| Time | Event |
|------|-------|
| T+0m | Motion trigger fires after 23:00 |
| T+1m | Sleep routine "all-off" executes |
| T+2m | Motion retriggers and loop starts |

### Root Cause
Overlapping conditions without precedence or cooldown.

### Prevention
Add precedence: sleep mode dominates. Add 120s cooldown.

---
```

## Example 2: Occupancy False Positive

```markdown
## [LRN-20260413-001] occupancy_mismatch

**Logged**: 2026-04-13T19:30:00Z
**Priority**: high
**Status**: pending
**Area**: sensors

### Summary
Home marked occupied due to stale BLE beacon, preventing alarm arming.

### Details
Presence remained true for 9 hours after all residents left.

### Safe Operating Notes
- High-impact actuator involved: yes
- Human confirmation required: yes
- Fallback on uncertainty: notify-only

### Metadata
- Pattern-Key: occupancy.stale_ble_presence

---
```

## Example 3: HVAC Overshoot

```markdown
## [LRN-20260413-002] latency_jitter

**Logged**: 2026-04-13T20:00:00Z
**Priority**: medium
**Status**: pending
**Area**: climate

### Summary
HVAC overshoots target by 2.3C due to delayed temperature updates and aggressive rule.

### Suggested Action
Use moving average from two sensors + minimum runtime and cooldown.

---
```

## Example 4: Lock Automation Safety Guard

```markdown
## [LRN-20260413-003] safety_rule_gap

**Logged**: 2026-04-13T20:15:00Z
**Priority**: critical
**Status**: pending
**Area**: access_control

### Summary
Auto-unlock at arrival can trigger from low-confidence geofence event.

### Safe Operating Notes
- High-impact actuator involved: yes
- Human confirmation required: yes
- Fallback on uncertainty: no action

### Suggested Action
Require dual signal (geofence + BLE) and explicit user confirmation after 22:00.

---
```

## Example 5: Integration API Change

```markdown
## [DOM-20260413-002] weather_api_schema_break

**Logged**: 2026-04-13T21:00:00Z
**Priority**: high
**Status**: pending
**Area**: integrations

### Summary
Weather provider changed `temp_c` to `temperature.celsius`, breaking climate preheat routine.

### Root Cause
Integration parser had hard-coded field names and no schema version checks.

### Prevention
Add schema validation, feature flags, and fallback parser.

---
```

## Example 6: Energy Optimization Pattern

```markdown
## [LRN-20260413-004] energy_optimization

**Logged**: 2026-04-13T21:20:00Z
**Priority**: medium
**Status**: pending
**Area**: energy

### Summary
Shifting water heater preheat outside peak tariff reduced daily usage cost by 14%.

### Details
Preheat moved from 18:00 to 16:30 with o

references/hooks-setup.md

# Domotics Hook Setup Guide

Configure optional hooks for domotics self-improvement reminders.

## Overview

Hooks help maintain logging discipline:
- `UserPromptSubmit`: injects reminder to evaluate `LRN` / `DOM` / `FEAT`
- `PostToolUse (Bash)`: scans tool output for high-signal domotics failure patterns

All hooks are reminder-only and must not execute direct physical actions.

## Claude Code Setup

Create `.claude/settings.json`:

```json
{
  "hooks": {
    "UserPromptSubmit": [
      {
        "matcher": "sensor|actuator|automation|iot|scene|device|home.?assistant",
        "hooks": [
          {
            "type": "command",
            "command": "./skills/self-improving-domotics/scripts/activator.sh"
          }
        ]
      }
    ],
    "PostToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "./skills/self-improving-domotics/scripts/error-detector.sh"
          }
        ]
      }
    ]
  }
}
```

## Codex Setup

Use equivalent settings file and same script paths.

## Verification

```bash
chmod +x ./skills/self-improving-domotics/scripts/*.sh
bash -n ./skills/self-improving-domotics/scripts/activator.sh
bash -n ./skills/self-improving-domotics/scripts/error-detector.sh
bash -n ./skills/self-improving-domotics/scripts/extract-skill.sh
```

Start a new session and confirm reminder tags appear.

## Troubleshooting

1. Check script permissions.
2. Validate relative paths from project root.
3. Restart the session after hook config changes.
4. If overhead is too high, keep only `UserPromptSubmit`.

## Safety Notes

- Hook output should stay concise.
- Avoid logging secrets, lock codes, or personal occupancy schedules.
- Keep automation commands out of hook scripts; reminders only.

references/openclaw-integration.md

# OpenClaw Integration (Domotics)

Complete setup for `self-improving-domotics` in OpenClaw.

## Install

```bash
clawdhub install self-improving-domotics
```

Manual alternative:

```bash
git clone https://github.com/jose-compu/self-improving-domotics.git ~/.openclaw/skills/self-improving-domotics
```

## Optional Hook

```bash
cp -r hooks/openclaw ~/.openclaw/hooks/self-improving-domotics
openclaw hooks enable self-improving-domotics
```

## Workspace Files

Ensure:

```bash
mkdir -p ~/.openclaw/workspace/.learnings
```

Required files:
- `LEARNINGS.md`
- `DOMOTICS_ISSUES.md`
- `FEATURE_REQUESTS.md`

## Promotion Targets

- Home automation playbooks
- Device compatibility matrix
- Automation rule library
- Safety automations

## Detection Focus

- Rule conflict and automation loops
- Sensor drift and stale occupancy
- Device offline / unreachable behavior
- Integration/webhook/API regressions
- Latency and schedule miss patterns
- Energy optimization opportunities
- Safety rule gaps for high-impact routines

## Safety Boundary

This integration captures reminders and documentation only.
It does not execute direct physical actuator actions.
Human confirmation is required for lock/alarm/gas/water/heater high-impact routines.

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/jose-compu/skills/self-improving-house",
      "sourceUrl": "https://clawhub.ai/jose-compu/skills/self-improving-house",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-11T09:51:02.581Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-jose-compu-self-improving-house/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-jose-compu-self-improving-house/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-11T09:51:02.581Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "1.1K downloads",
      "href": "https://clawhub.ai/jose-compu/self-improving-house",
      "sourceUrl": "https://clawhub.ai/jose-compu/self-improving-house",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-11T09:51:02.581Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "1.0.1",
      "href": "https://clawhub.ai/jose-compu/self-improving-house",
      "sourceUrl": "https://clawhub.ai/jose-compu/self-improving-house",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-08-28T19:26:16.220Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-jose-compu-self-improving-house/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-jose-compu-self-improving-house/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 1.0.1",
      "description": "Security review: narrow hook matchers, explicit promotion approval, project-scoped hooks.",
      "href": "https://clawhub.ai/jose-compu/self-improving-house",
      "sourceUrl": "https://clawhub.ai/jose-compu/self-improving-house",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-08-28T19:26:16.220Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 11, 2026.

About

Avoid when

Public facts

Install and run

Documentation

Extracted files

SKILL.md

_meta.json

references/examples.md

references/hooks-setup.md

references/openclaw-integration.md

Related agents

AionUi

activepieces

cherry-studio

CopilotKit

Machine-readable data