LLMBooster Skill#

A Thinking Framework, Not an Automation Tool

LLMBooster is a 4-step thinking framework that improves LLM output quality through structured reasoning. No LLM endpoint needed - the LLM follows the framework itself.

Core Philosophy#

Problem with low-end LLMs: Jump to conclusions, miss details, lack self-review.

Booster solution: Enforce structured thinking process.

text

Plan → Draft → Self-Critique → Refine

Trigger Conditions#

• User says "use booster", "booster", or "/booster"
• User requests: "detailed analysis", "in-depth analysis", "help me analyze"
• User requests: "improve quality", "detailed analysis"
• User asks for evaluation, comparison, or decision support
• User requests code review or technical documentation
• User asks complex questions (lengthy tasks, multi-step problems)

How It Works#

LLM executes the framework itself, no Python calls needed:

1. LLM reads prompts/plan.md → Create structured plan
2. LLM reads prompts/draft.md → Write complete draft
3. LLM reads prompts/self_critique.md → Review issues
4. LLM reads prompts/refine.md → Polish final output

Command Handling#

When user enters /booster command, execute:

bash

cd ~/.openclaw/workspace/skills/llmbooster && python3 -c "
from config_loader import ConfigLoader
from state_manager import SkillStateManager
from cli_handler import CLICommandHandler

loader = ConfigLoader()
config = loader.load('config.schema.json')
state_mgr = SkillStateManager(config)
cli = CLICommandHandler(state_mgr)
result = cli.handle('/booster status')
print(result.message)
"

CLI Commands#

CommandDescription/booster enableEnable LLMBooster/booster disableDisable LLMBooster/booster statusShow current status/booster statsShow usage statistics/booster depth <1-4>Set thinking depth/booster helpShow help

Thinking Depth#

DepthStepsQualitySpeedUse Case1Plan★★☆☆FastestQuick analysis, brainstorm2Plan → Draft★★★☆FastGeneral tasks, simple Q&A3+ Self-Critique★★★★MediumCode review, technical docs4Full pipeline★★★★★SlowestImportant docs, complex analysis

Visual Feedback#

When executing, Booster displays:

text

🚀 **Booster Pipeline Started**: Analyzing task...
────────────────────────────────────────
🚀 Booster [█░░░░] Step 1/4: **Plan**
✅ Plan completed (2.3s)

🚀 Booster [██░░░] Step 2/4: **Draft**
✅ Draft completed (5.1s)

🚀 Booster [███░░] Step 3/4: **Self-Critique**
✅ Self-Critique completed (1.8s)

🚀 Booster [████] Step 4/4: **Refine**
✅ Refine completed (3.2s)
────────────────────────────────────────
✅ **Booster Complete** - 4 steps, 12.4s total

Prompt Templates#

All templates are in prompts/ directory:

• plan.md - Step 1: Create structured plan
• draft.md - Step 2: Write complete draft
• self_critique.md - Step 3: Review and list improvements
• refine.md - Step 4: Apply improvements

Why It Works#

Low-End LLM ProblemBooster SolutionJumps to conclusionsPlan step forces structured thinkingMisses detailsDraft step requires complete coverageNo self-reviewSelf-Critique step finds issuesRough outputRefine step polishes final result

Usage Statistics#

bash

/booster stats
# 📊 **Booster Statistics**
# ───────────────────────
# Status: enabled
# Thinking Depth: 4
# Tasks Processed: 5
# Last Used: 2026-03-22T09:30:00

Files#

FilePurposeSKILL.mdSkill definition + trigger conditionsREADME.mdDocumentationbooster.pyCore module + helperscli_handler.pyCLI command processingstate_manager.pyState + statisticsstream_handler.pyVisual feedbackconfig_loader.pyConfig loadingprompts/*.mdStep prompt templates