enhanced-memoryEnhanced memory search with hybrid vector+keyword scoring, temporal routing, filepath scoring, adaptive weighting, pseudo-relevance feedback, salience scoring, and knowledge graph cross-references. Replaces the default memory search with a 4-signal fusion retrieval system. Use when searching memories, indexing memory files, building cross-references, or scoring memory salience. Requires Ollama with nomic-embed-text model.
Install via ClawdBot CLI:
clawdbot install JamesEBall/enhanced-memoryGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
http://localhost:11434/api/embedAudited Apr 18, 2026 · audit v1.0
Generated Mar 21, 2026
Law firms can use this skill to search through case files, contracts, and legal memos. The hybrid retrieval improves accuracy in finding relevant precedents or clauses, while temporal routing helps prioritize recent cases or deadlines.
Researchers can index and search academic papers, notes, and lab reports. The knowledge graph cross-references aid in discovering connections between studies, and salience scoring highlights important but overlooked findings for review.
Support teams can enhance search in internal knowledge bases for troubleshooting guides and FAQs. Adaptive weighting ensures relevant results even with vague queries, and JSON output integrates easily with ticketing systems.
Medical facilities can index patient records and clinical notes for quick retrieval. Filepath scoring helps locate documents by patient or date, and pseudo-relevance feedback refines searches for complex symptoms or treatments.
Engineering teams can search project documentation, meeting notes, and code comments. The 4-signal fusion retrieves relevant technical details, and cross-references link related modules or tasks for better collaboration.
Offer this memory enhancement as a cloud-based service with API access. Charge monthly fees based on usage tiers, such as number of documents indexed or search queries, targeting small to medium businesses.
Sell licenses for on-premise deployment to enterprises with strict data privacy needs. Include setup support and customization services, with revenue from one-time fees and annual maintenance contracts.
Provide consulting services to integrate this skill into existing AI systems or workflows. Revenue comes from project-based fees for customization, training, and ongoing optimization support.
💬 Integration Tip
Ensure Ollama is running locally and memory files are properly indexed before use; test with sample queries to tune weights for specific datasets.
Scored Apr 19, 2026
Structured reasoning through sequential thinking — break complex problems into steps, solve each independently, verify consistency, synthesize conclusions wi...
LLM-driven epistemic reasoning engine. Evaluates claims against evidence, outputs calibrated confidence and structured belief state (VERIFIED/CONTESTED/UNCER...
Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (>90 days), enriches context duri...
Turn scattered local sources into a source-constrained evidence notebook for incident, release, and maintainer decisions.
三级记忆管理系统 (Three-Tier Memory Management)。用于管理 AI 代理的短期、中期、长期记忆。包括:(1) 滑动窗口式短期记忆,(2) 自动摘要生成中期记忆,(3) 向量检索长期记忆 (RAG)。当需要管理对话历史、优化上下文、构建个人知识库、或实现记忆持久化时使用此 Skill。
Store secrets, long-term memory, daily logs, and anything custom in your Convex backend instead of local files