semantic-memory-search为 OpenClaw Markdown 记忆文件添加向量驱动的语义搜索。使用 memsearch 库,支持混合搜索(稠密向量 + BM25),SHA-256 智能去重,本地 embedding 无需 API Key。
Install via ClawdBot CLI:
clawdbot install sunnyhot/semantic-memory-searchGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/sunnyhot/semantic-memory-searchAudited Apr 18, 2026 · audit v1.0
Generated Mar 21, 2026
Law firms can use this skill to semantically search through case notes, legal precedents, and client documents stored as markdown files. It helps lawyers quickly find relevant past cases or arguments without relying on exact keywords, improving research efficiency and case preparation.
Universities or research institutions can index academic papers, lecture notes, and project documentation in markdown format. Researchers and students can perform semantic searches to discover related studies or concepts, facilitating interdisciplinary collaboration and literature reviews.
Tech companies can apply this skill to search through internal documentation, code comments, and meeting notes stored as markdown files. Developers can find relevant information about caching schemes, API changes, or bug fixes using natural language queries, speeding up onboarding and troubleshooting.
Media agencies or podcast producers can use it to semantically search through production notes, script drafts, and editorial guidelines in markdown files. This helps teams quickly recall past decisions, such as Discord channel reorganizations or podcast workflows, ensuring consistency in content creation.
Financial institutions can index compliance reports, audit trails, and configuration histories in markdown format. Analysts can perform semantic searches to track changes in financial systems or find related regulatory updates, aiding in risk management and reporting accuracy.
Offer this skill as a cloud-based service with additional features like advanced analytics, team collaboration tools, and premium embedding models. Charge organizations a monthly or annual subscription fee based on usage tiers, such as number of documents indexed or search queries.
Provide consulting services to help businesses integrate this skill into their existing workflows, such as customizing the search algorithms or embedding models for specific industries. Charge one-time setup fees or ongoing support contracts for maintenance and updates.
Release the core functionality as open-source to attract users and developers, then offer premium add-ons like real-time synchronization dashboards, priority support, or integration with proprietary tools. Monetize through paid upgrades and enterprise licenses.
💬 Integration Tip
Ensure Python 3.10+ and memsearch library are installed, and configure the local embedding model in the config file for offline use without API keys.
Scored Jun 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