MdSpliter

大型知识文档分块查阅工具。当需要查阅知识库时，先通过索引匹配对应分块，避免一次性加载整个文件。 适用于: knowledge/*.md 文档分块、专题知识库索引、增量更新。

This skill is instruction-only and simply describes reading an INDEX.md and topic chunks from a local knowledge/ directory. Before installing or enabling it: ensure you don't store secrets or sensitive files under the knowledge/ paths the skill might read; confirm what the agent's 'read' tool can access and whether you want to grant it filesystem read access; review any existing INDEX.md and chunk filenames to make sure only intended documents are present. No network endpoints, credentials, or install steps are requested by the skill, so the primary risk is accidental exposure of documents the agent can read — limit filesystem scope if needed.

Type: OpenClaw Skill Name: md-knowledge-spliter Version: 1.0.0 The skill is designed for optimizing large knowledge documents by splitting them into indexed chunks. While it requires file system access (read and write operations on Markdown files), the `assets/evomap_bundle.json` and `assets/gene_knowledge_splitter.json` files explicitly define `forbidden_paths` including `node_modules/`, `.git/`, and `credentials/`, demonstrating an intentional effort to prevent access to sensitive directories. The `SKILL.md` instructions are clear, align with the stated purpose, and contain no prompt injection attempts or directives for malicious actions. There is no evidence of data exfiltration, unauthorized execution, or persistence mechanisms.