Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub Β· AI
Gpt Analyzer
GPT-specific pattern detection with model fingerprinting and version identification
skill openclawclawhub Free
GPT-specific pattern detection with model fingerprinting and version identification
β¬ 0 downloads β
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- SKILL.md
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 1.0.0
Provenance
- Publisher
- raghulpasupathi
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
GPT Analyzer
Specialized detection for GPT-generated content with model-specific pattern recognition.
Implementation
/** * Analyze text for GPT-specific patterns and fingerprints * @param {string} text - Text to analyze * @param {object} options - Configuration options * @returns {object} Analysis result with model identification */ async function analyzeGPTContent(text, options = {}) { const { detectVersion = true, checkWatermarks = true, minConfidence = 0.7 } = options; const normalizedText = text.toLowerCase(); const wordCount = text.split(/\s+/).length; // GPT-specific phrases (stronger indicators) const gptPhrases = { 'gpt-4': [ 'delve into', 'landscape of', 'realm of', 'it\'s important to note', 'multifaceted', 'nuanced', 'comprehensive', 'holistic approach' ], 'gpt-3.5': [ 'as an ai language model', 'i don\'t have personal', 'i apologize for', 'certainly', 'absolutely', 'furthermore', 'moreover' ], 'common': [ 'it\'s worth noting', 'keep in mind', 'in conclusion', 'to summarize', 'in summary', 'navigate the', 'tapestry of' ] }; // Model fingerprinting let gpt4Score = 0; let gpt35Score = 0; let commonScore = 0; const foundPhrases = []; // Check GPT-4 specific patterns for (const phrase of gptPhrases['gpt-4']) { if (normalizedText.includes(phrase)) { gpt4Score += 0.2; foundPhrases.push({ phrase, model: 'gpt-4' }); } } // Check GPT-3.5 specific patterns for (const phrase of gptPhrases['gpt-3.5']) { if (normalizedText.includes(phrase)) { gpt35Score += 0.2; foundPhrases.push({ phrase, model: 'gpt-3.5' }); } } // Check common GPT patterns for (const phrase of gptPhrases['common']) { if (normalizedText.includes(phrase)) { commonScore += 0.1; foundPhrases.push({ phrase, model: 'common' }); } } // Structure analysis const hasNumberedLists = (text.match(/\n\d+\./g) || []).length >= 3; const hasBulletPoints = (text.match(/\n[β’\-\*]/g) || []).length >= 3; const structureScore = (hasNumberedLists || hasBulletPoints) ? 0.15 : 0; // Sentence uniformity const sentences = text.split(/[.!?]+/).filter(s => s.trim()); const avgLength = sentences.reduce((sum, s) => sum + s.length, 0) / sentences.length; const variance = sentences.reduce((sum, s) => sum + Math.pow(s.length - avgLength, 2), 0) / sentences.length; const uniformityScore = variance < 500 ? 0.1 : 0; // Calculate confidence const totalScore = gpt4Score + gpt35Score + commonScore + structureScore + uniformityScore; const confidence = Math.min(totalScore, 1.0); // Determine model let detectedModel = 'unknown'; if (gpt4Score > gpt35Score && gpt4Score > 0) { detectedModel = 'gpt-4'; } else if (gpt35Score > gpt4Score && gpt35Score > 0) { detectedModel = 'gpt-3.5'; } else if (commonScore > 0) { detectedModel = 'gpt-family'; } const isGPT = confidence >= minConfidence; return { isGPT, confidence: Math.round(confidence * 100), detectedModel: isGPT ? detectedModel : 'not-gpt', scores: { gpt4: Math.round(gpt4Score * 100) / 100, gpt35: Math.round(gpt35Score * 100) / 100, common: Math.round(commonScore * 100) / 100, structure: Math.round(structureScore * 100) / 100, uniformity: Math.round(uniformityScore * 100) / 100 }, indicators: { foundPhrases: foundPhrases.length, hasStructure: hasNumberedLists || hasBulletPoints, avgSentenceLength: Math.round(avgLength), sentenceVariance: Math.round(variance) }, recommendation: confidence >= 0.85 ? 'Very likely GPT' : confidence >= 0.70 ? 'Likely GPT' : confidence >= 0.50 ? 'Possibly GPT' : 'Unlikely GPT or human-written' }; } // Export for OpenClaw module.exports = { analyzeGPTContent };
Usage
const result = await skills.gptAnalyzer.analyzeGPTContent(text); if (result.isGPT) { console.log(`GPT detected: ${result.detectedModel} (${result.confidence}% confidence)`); }
Configuration
{ "detectVersion": true, "minConfidence": 0.7 }
Category context
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
1 Docs
- SKILL.md