fleet-embeddingsEmbeddings with nomic-embed-text, mxbai-embed, and snowflake-arctic-embed across your device fleet. Fleet-routed via Ollama for RAG, semantic search, and vec...
Install via ClawdBot CLI:
clawdbot install twinsgeeks/fleet-embeddingsGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → http://localhost:11435/dashboard/api/pullCalls external URL not in known-safe list
https://github.com/geeks-accelerator/ollama-herdAI Analysis
The skill routes embeddings through a local fleet router (localhost:11435) for distributed processing, which aligns with its stated purpose and keeps data on-premises. The external GitHub reference is for documentation/installation, not runtime data transmission. The 'UNKNOWN_DATA_SINK' signal appears to be a false positive, as the endpoint is part of the local fleet management dashboard.
Audited Apr 16, 2026 · audit v1.0
Generated May 6, 2026
Embed thousands of document chunks for a retrieval-augmented generation pipeline. The fleet distributes embedding loads across nodes, allowing large-scale indexing without blocking LLM inference.
Enable semantic search on a fleet of devices by embedding user queries and documents. Fleet routing ensures low-latency responses even with many concurrent requests.
Use embeddings to find near-duplicate documents or messages across a large corpus. Batch embedding across nodes speeds up comparison and deduplication.
Generate item embeddings for a recommendation engine, then compute similarities to find top candidates for users. Fleet parallelism accelerates embedding updates.
Index text descriptions from images or audio transcripts into embeddings for cross-modal search. The fleet handles the embedding workload while other nodes do inference.
Offer basic embedding API access for free with rate limits, then charge for higher throughput or batch processing. Revenue comes from subscription tiers or pay-per-request.
License the fleet embedding solution to companies that want to embed documents privately on their own infrastructure. Revenue from licensing and support contracts.
Provide a fully managed embedding fleet with monitoring, scaling, and maintenance. Charge monthly based on number of nodes and embedding volume.
💬 Integration Tip
Start with the curl or Python examples—just replace localhost:11435 with your fleet router address. Use batch embedding for RAG to maximize throughput.
Scored May 6, 2026
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.
Chat with Grok models via xAI API. Supports Grok-3, Grok-3-mini, vision, and more.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Humanize AI-generated text to bypass detection. This humanizer rewrites ChatGPT, Claude, and GPT content to sound natural and pass AI detectors like GPTZero,...
Humanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 24 pattern detectors, 500+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。