← 返回 Skills 市场
Uplo Knowledge Management
作者
RooJenkins
· GitHub ↗
· v1.0.0
· MIT-0
224
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install uplo-knowledge-management
功能描述
AI-powered knowledge management intelligence. Search taxonomies, content curation records, expertise directories, and communities of practice with structured...
安全使用建议
This skill appears to be a legitimate connector to an UPLO/MCP instance. Before installing: (1) verify you trust the UPLO instance URL and owner of the npm package (@agentdocs1), (2) supply a least-privilege API key (read-only if possible) because the skill can export organizational context and expertise data, (3) be aware that the MCP server is launched via npx which will fetch code from the npm registry — review the package and its publisher if you can, and (4) test in a non-production environment first to confirm the data returned and any automated actions (e.g., report_knowledge_gap) behave as you expect. Also note the registry metadata omitted required config but skill.json includes it — ensure you provision the listed agentdocs_url and api_key only if this aligns with your security policies.
功能分析
Type: OpenClaw Skill
Name: uplo-knowledge-management
Version: 1.0.0
The skill is classified as suspicious due to the inclusion of the 'export_org_context' tool (found in skill.json and README.md), which enables bulk extraction of the entire organizational knowledge base. Instructions in SKILL.md and identity-patch.md steer the agent to use these high-privilege tools 'aggressively' and to 'always query UPLO first,' which significantly increases the risk of data exfiltration via prompt injection. Additionally, the skill's configuration uses 'npx' to execute the '@agentdocs1/mcp-server' package at runtime, introducing a potential supply chain vulnerability.
能力评估
Purpose & Capability
The skill is described as an UPLO knowledge-management connector and the declared capabilities (search_knowledge, search_with_context, export_org_context, etc.) align with that purpose. The skill.json requires an agentdocs_url and api_key to reach an UPLO/MCP server — these credentials are appropriate for a connector of this type. (Note: the registry summary above listed no required env/config, but the included skill.json does declare two required config entries; this appears to be a metadata mismatch rather than malicious behavior.)
Instruction Scope
SKILL.md instructs the agent to call well-scoped MCP tools (get_identity_context, search_with_context, search_knowledge, export_org_context, report_knowledge_gap, etc.). These actions stay within knowledge-management activities (searching, exporting org context, flagging gaps). The instructions do not tell the agent to read unrelated system files, environment variables, or to send data to unknown external endpoints beyond the configured UPLO/MCP server.
Install Mechanism
There is no platform-level install spec in the registry listing, but the README and skill.json indicate the MCP server is run via npx @agentdocs1/mcp-server (npm). Fetching an npm package at runtime is a typical pattern for MCP adapters but carries the usual moderate risk of executing code fetched from the npm registry. No direct downloads from untrusted URLs or archive extracts are present.
Credentials
The only required configuration in skill.json is agentdocs_url and api_key (the UPLO/MCP instance URL and token). Those are proportionate to a knowledge-management connector. The skill does not request unrelated credentials or broad system-level secrets.
Persistence & Privilege
The skill is not always-enabled, does not request system-wide configuration changes, and contains no instructions to modify other skills. It operates as a connector that may read/export organizational context via the configured MCP endpoint — appropriate for its stated purpose.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install uplo-knowledge-management - 安装完成后，直接呼叫该 Skill 的名称或使用
/uplo-knowledge-management触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release: AI-powered knowledge management skill for organizational learning.
- Enables structured search across taxonomies, expertise directories, content curation records, and communities of practice.
- Provides example KM-focused workflows, such as knowledge audits, taxonomy governance, and organizational knowledge health assessments.
- Details essential tools including search_with_context, search_knowledge, export_org_context, report_knowledge_gap, flag_outdated, and propose_update.
- Offers guidance, best practices, and tips for KM practitioners to identify knowledge gaps, manage content lifecycle, and optimize knowledge sharing.
元数据
常见问题
Uplo Knowledge Management 是什么？
AI-powered knowledge management intelligence. Search taxonomies, content curation records, expertise directories, and communities of practice with structured... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 224 次。
如何安装 Uplo Knowledge Management？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install uplo-knowledge-management」即可一键安装，无需额外配置。
Uplo Knowledge Management 是免费的吗？
是的，Uplo Knowledge Management 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Uplo Knowledge Management 支持哪些平台？
Uplo Knowledge Management 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Uplo Knowledge Management？
由 RooJenkins（@roojenkins）开发并维护，当前版本 v1.0.0。
推荐 Skills