clawzembic

Lighthouse-style efficiency audit for OpenClaw. Scores your instance A+ to F across 6 categories (context injection, cron health, session bloat, config, skills, transcripts). Identifies wasted tokens, bloated sessions, misconfigured crons, and model right-sizing opportunities. Zero dependencies (Python stdlib only).

3,891 stars

byopenclaw

View on GitHub Installation ↓

Best use case

clawzembic is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Teams using clawzembic should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/clawzembic/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/anna-claudette/clawzembic/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/clawzembic/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How clawzembic Compares

Feature / Agent	clawzembic	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

AI Agents for Coding

Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.

AI Agent for YouTube Script Writing

Find AI agent skills for YouTube script writing, video research, content outlining, and repeatable channel production workflows.

AI Agents for Marketing

Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.

SKILL.md Source

# Clawzembic — Weight Loss for Your OpenClaw Instance

**Lighthouse-style audit for OpenClaw efficiency.** Run it, get a grade (A+ to F), shed the bloat.

Scans your installation and scores it across six critical categories: context injection, cron health, session bloat, config health, skill bloat, and transcript size. You get one overall letter grade plus category-by-category breakdown with actionable findings.

**Zero dependencies.** Python 3.8+ stdlib only.

## Quick Start

```bash
# Audit this machine
bash skills/clawzembic/lean-audit.sh

# Audit a remote instance (VM, etc.)
bash skills/clawzembic/lean-audit.sh --remote user@host

# JSON output for dashboards/integrations
bash skills/clawzembic/lean-audit.sh --json

# Show automated fix suggestions
bash skills/clawzembic/lean-audit.sh --fix

# Custom .openclaw directory
bash skills/clawzembic/lean-audit.sh --dir /path/to/.openclaw
```

## What It Checks

| Category | Weight | What Gets Flagged |
|----------|--------|-------------------|
| Context Injection | 25% | Oversized MEMORY.md, bloated workspace files eating tokens |
| Cron Health | 25% | Wrong models, high thinking on routine tasks, main-session pollution |
| Session Bloat | 20% | Stale sessions hogging context, waste ratio above 35% |
| Config Health | 15% | Heartbeat too frequent, subagent defaults, missing compaction |
| Skill Bloat | 10% | Too many skills injected, unused skills inflating system prompt |
| Transcript Size | 5% | Disk hogs, oversized transcripts (>10MB files) |

## Grade Scale

- **A+/A** (90-100): Lean machine 💪
- **B+/B** (75-89): Good shape, minor tweaks
- **C+/C** (60-74): Needs a diet 🍕
- **D+/D** (45-59): Significant bloat 🫠
- **F** (<45): Emergency Clawzembic needed 💊

## Agent Usage

When Jeffrey asks you to audit or optimize an OpenClaw instance:

1. Run `bash skills/clawzembic/lean-audit.sh` (or `--remote user@claudette` for the VM)
2. Review the report and present key findings with context
3. Offer `--fix` mode for automated remediation if score < 75

For remote instances, ensure SSH key-based auth is configured. The skill uses SSH to execute the audit remotely — no agent installation needed on the target.

Related Skills

---

3891

from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891

from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891

from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891

from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891

from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891

from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891

from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891

from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891

from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure