← 返回 Skills 市场
qy-zhang

knowledge-capture

作者 Fitzwilliam Zhang · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
152
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install personal-knowledge-capture
功能描述
知识库捕获与自适应复习系统。触发词:「记住」「记下来」「加入知识库」「这个值得记」「帮我记住」「值得记录」。将对话中的知识点整理成结构化 Markdown 笔记,写入对应分类目录,自动生成题目加入题库(question-bank.json),并更新掌握度状态文件(mastery-status.json)和复习计划...
安全使用建议
This skill appears to do what it says: create structured Markdown notes, generate questions, and update local mastery/plan JSON files. Before installing, consider: 1) Confirm the exact workspace path (/root/.openclaw/workspace/knowledge/) — if your agent environment differs or you want files elsewhere, ask the skill author to make the path configurable. 2) Back up any existing data in that directory to avoid accidental overwrites. 3) Ask how the skill handles filename normalization, duplicates, and path traversal (e.g., titles containing ../). 4) Verify where scheduled review notifications will appear and whether the agent needs extra permissions to send them. 5) Because the skill writes persistent files, restrict the agent's filesystem permissions to the intended workspace if possible. If you see the skill later trying to contact external URLs or requesting credentials not mentioned here, revoke it and re-evaluate.
功能分析
Type: OpenClaw Skill Name: personal-knowledge-capture Version: 1.0.0 The skill bundle implements a structured knowledge capture and spaced-repetition (SRS) system. It manages markdown notes and JSON-based tracking files within a designated workspace directory (/root/.openclaw/workspace/knowledge/). There is no evidence of data exfiltration, malicious execution, or unauthorized access to sensitive system files; all operations are strictly aligned with the stated purpose of organizing and reviewing user-provided information.
能力评估
Purpose & Capability
Name/description (capture notes + adaptive review) matches the instructions: extract knowledge from conversation, generate Markdown notes, generate questions, and update local JSON mastery/plan files. There are no unrelated credential or binary requirements.
Instruction Scope
Instructions are limited to reading/writing structured files under a specific workspace and to interacting with the user for clarifications and scoring. However, the SKILL.md hardcodes an absolute path (/root/.openclaw/workspace/knowledge/) and instructs writing files there even though no config paths are declared in the metadata; this is a minor misalignment and means the skill expects filesystem write access to that location. Also the guidance does not mention input/path sanitization or conflict-handling (risk of overwriting existing files if titles/IDs are not safely normalized).
Install Mechanism
Instruction-only skill with no install spec and no code files — nothing is downloaded or installed by the skill itself.
Credentials
The skill requests no environment variables, credentials, or external endpoints. All required artifacts are local files within the workspace; the requested access is proportional to the stated purpose.
Persistence & Privilege
The skill will create and modify persistent files (notes, learning/question-bank.json, mastery-status.json, review plan). It does not set always:true and does not request system-wide privileges. Users should be aware these writes are persistent and could overwrite or conflict with other data in the same workspace path.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install personal-knowledge-capture
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /personal-knowledge-capture 触发
  4. 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 of knowledge-capture skill with adaptive review system: - Transforms conversation highlights into structured Markdown notes, auto-classifies, and saves in organized directories. - Generates multiple self-test questions per knowledge point, updating a centralized question bank. - Maintains mastery status and review plan files to track learning progress and schedule spaced repetition reviews. - Scores user quiz answers, updates mastery status, and dynamically adjusts the review schedule based on performance. - Provides detailed feedback, helping users strengthen weak points and advance toward mastery.
元数据
Slug personal-knowledge-capture
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

knowledge-capture 是什么?

知识库捕获与自适应复习系统。触发词:「记住」「记下来」「加入知识库」「这个值得记」「帮我记住」「值得记录」。将对话中的知识点整理成结构化 Markdown 笔记,写入对应分类目录,自动生成题目加入题库(question-bank.json),并更新掌握度状态文件(mastery-status.json)和复习计划... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 152 次。

如何安装 knowledge-capture?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install personal-knowledge-capture」即可一键安装,无需额外配置。

knowledge-capture 是免费的吗?

是的,knowledge-capture 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

knowledge-capture 支持哪些平台?

knowledge-capture 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 knowledge-capture?

由 Fitzwilliam Zhang(@qy-zhang)开发并维护,当前版本 v1.0.0。

💬 留言讨论