How do I install the Low Spec Optimizer skill?

Run npx skillmds@latest add dvcrn/low-spec-optimizer in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Low Spec Optimizer safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: executes scripts. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Low Spec Optimizer?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Low Spec Optimizer free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Low Spec Optimizer?

dvcrn (@dvcrn) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Low Spec Optimizer by dvcrn — Agent Skill

Name: Low Spec Optimizer
Rating: 4.2 (5 reviews)
Author: dvcrn

Low Spec Optimizer

Optimize OpenClaw performance on machines with limited resources (4GB RAM or less, old CPUs). Use when (1) user mentions slow performance, high RAM usage, or system lag, (2) running on Raspberry Pi, old laptops, or budget VPS, (3) proactively during heartbeats to check system health, (4) before spawning multiple subagents on low-resource machines. Provides resource monitoring, automatic cleanup, session management, and configuration recommendations for constrained environments.

dvcrn Updated Sep 8, 2026 32 repo stars

File contents

Low-Spec Optimizer

Help OpenClaw run smoothly on machines with limited resources.

Quick Start

Check current resources:

bash <skill-dir>/scripts/check_resources.sh

Parse output with jq:

bash <skill-dir>/scripts/check_resources.sh | jq '.alert, .ram.pct, .cpu.pct'

Workflow

1. Check resources before heavy operations

Before spawning subagents, opening browser, or running intensive tasks:

bash <skill-dir>/scripts/check_resources.sh

Decision matrix based on alert field:

OK (< 60% RAM): Proceed normally
ELEVATED (60-75%): Limit to 1 subagent, close browser first
WARNING (75-90%): Run cleanup, avoid spawning, warn user
CRITICAL (> 90%): Emergency cleanup, ask user before proceeding

2. Cleanup when needed

# Dry run first
bash <skill-dir>/scripts/cleanup_sessions.sh --dry-run

# Execute cleanup
bash <skill-dir>/scripts/cleanup_sessions.sh

# Aggressive (includes npm/pip/journal)
bash <skill-dir>/scripts/cleanup_sessions.sh --aggressive

3. Apply config recommendations

For machines with ≤4GB RAM, suggest OpenClaw config changes. See references/config-guide.md for full details.

Key recommendations:

Use free/lightweight models (hunter-alpha, GLM-4.5-air)
Set thinking to "off" unless needed
Limit concurrent subagents to 2 max
Always close browser after use
Prefer web_fetch over browser automation
Use mode: "run" for subagents (auto-cleanup)

4. Proactive monitoring (heartbeat)

During heartbeats on low-spec machines:

bash <skill-dir>/scripts/check_resources.sh | jq -r '.alert'

If alert is WARNING or CRITICAL, notify the user with specifics:

Which process is consuming most memory
How much is free
Recommended action (cleanup, close apps, restart)

Rules for constrained environments

One browser at a time — never parallel browser sessions
Close everything after use — browser, subagent sessions, temp files
Check before opening — always check RAM before heavy operations
Prefer lightweight alternatives — web_fetch > browser, mode: "run" > mode: "session"
Batch operations — combine tasks instead of spawning separate sessions
Use cron over heartbeat — for precise scheduling, use cron with isolated sessions

---name: low-spec-optimizerdescription: Optimize OpenClaw performance on machines with limited resources (4GB RAM or less, old CPUs). Use when (1) user mentions slow performance, high RAM usage, or system lag, (2) running on Raspberry Pi, old laptops, or budget VPS, (3) proactively during heartbeats to check system health, (4) before spawning multiple subagents on low-resource machines. Provides resource monitoring, automatic cleanup, session management, and configuration recommendations for constrained environments.---# Low-Spec OptimizerHelp OpenClaw run smoothly on machines with limited resources.## Quick StartCheck current resources:```bashbash <skill-dir>/scripts/check_resources.sh```Parse output with `jq`:```bashbash <skill-dir>/scripts/check_resources.sh | jq '.alert, .ram.pct, .cpu.pct'```## Workflow### 1. Check resources before heavy operationsBefore spawning subagents, opening browser, or running intensive tasks:```bashbash <skill-dir>/scripts/check_resources.sh```Decision matrix based on `alert` field:- **OK** (< 60% RAM): Proceed normally- **ELEVATED** (60-75%): Limit to 1 subagent, close browser first- **WARNING** (75-90%): Run cleanup, avoid spawning, warn user- **CRITICAL** (> 90%): Emergency cleanup, ask user before proceeding### 2. Cleanup when needed```bash# Dry run firstbash <skill-dir>/scripts/cleanup_sessions.sh --dry-run# Execute cleanupbash <skill-dir>/scripts/cleanup_sessions.sh# Aggressive (includes npm/pip/journal)bash <skill-dir>/scripts/cleanup_sessions.sh --aggressive```### 3. Apply config recommendationsFor machines with ≤4GB RAM, suggest OpenClaw config changes.See [references/config-guide.md](references/config-guide.md) for full details.Key recommendations:- Use free/lightweight models (hunter-alpha, GLM-4.5-air)- Set thinking to `"off"` unless needed- Limit concurrent subagents to 2 max- Always close browser after use- Prefer `web_fetch` over browser automation- Use `mode: "run"` for subagents (auto-cleanup)### 4. Proactive monitoring (heartbeat)During heartbeats on low-spec machines:```bashbash <skill-dir>/scripts/check_resources.sh | jq -r '.alert'```If alert is `WARNING` or `CRITICAL`, notify the user with specifics:- Which process is consuming most memory- How much is free- Recommended action (cleanup, close apps, restart)## Rules for constrained environments1. **One browser at a time** — never parallel browser sessions2. **Close everything after use** — browser, subagent sessions, temp files3. **Check before opening** — always check RAM before heavy operations4. **Prefer lightweight alternatives** — `web_fetch` > browser, `mode: "run"` > `mode: "session"`5. **Batch operations** — combine tasks instead of spawning separate sessions6. **Use cron over heartbeat** — for precise scheduling, use cron with isolated sessions

Frequently asked questions