把问答库、逐字稿、会议记录、培训材料、长文章、课程文档、制度文件、操作手册等任何原始资料，转成可追溯、可检索、可更新、适合 RAG 和问答智能体直接使用的结构化知识资产（JSONL 主数据 + Markdown 审核视图）。用户说"把这些材料整理成知识库""把这份文档存进知识库""转成能检索的资料""拆成知识块""喂给智能体""结构化一下""做知识卡片""增量入库""去重查冲突"时触发。比 AI 通用能力强在：单一事实源双视图机制、来源可追溯、检索与回答字段分离、冲突/版本/回滚可见可管、10 万字级增量接入。不用于直接回答领域问题，不补写原始资料中没有的专业知识。
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/知识资产化巧匠SKILL.mdRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/知识资产化巧匠SKILL.mdRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/知识资产化巧匠SKILL.mdRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.
clawhub install @jeasonhaitao/knowledge-asset-craftsmanclawhub inspect @jeasonhaitao/knowledge-asset-craftsman --version 1.0.0This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:f4e16069b9fee0061960622c4101e4e137152f211eed6f6a20597c9c43286f43assets/knowledge-block-template.mdreferences/conv-semantic-splitting.mdreferences/knowledge-schema.mdreferences/tag-rules.mdscripts/doc_reader.pyscripts/generate_markdown.pyscripts/validate_dual_view.pyskill-card.mdSKILL.md知识资产化巧匠 1.0.0 - 首次发布，面向多来源资料自动转化为可追溯、可检索、可更新的结构化知识资产。 - 实现“单一事实源+双视图”机制：以 JSONL 为主数据，自动生成 Markdown 审核视图，便于机器处理与人工审核。 - 支持问答库、逐字稿、会议记录、长文章等按统一规范原子化拆分、标签化、去重、冲突管理和增量更新。 - 明确检索与回答字段分离，支持低 token 消耗高精度召回，满足 RAG 应用需求。 - 不擅自补全或回答资料未涵盖的知识，确保每条可回溯具体来源和状态。 - 内嵌标准流程、字段规范及质量门控，保障大规模知识库可靠落库和后续可控运营。