跳到正文
cccskills
OpenClaw 官方免费在 GitHub 公开中文介绍

knowledge-capture

在Knowledge中保存值得长期参考的偏好、决定、事实、承诺和经验,并保留来源及支持依据。可快速记录单条内容,也可更新相关页面;发布后会回读内容、证据和主题关联。

原文查看原文说明

Save durable preferences, decisions, project facts, commitments, and lessons cheaply with knowledge_remember, or short notes and page updates with attribution and readback. Use for explicit saves or agent-driven remembering when Knowledge is the selected memory provider.

openclaw/openclaw星标 393,141(GitHub 393,141 + cccskills 0)

实测评分 未实测

查看安装方法

适用场景

  • 记录对话中确定的决定
  • 保存带来源的偏好
  • 将重要事实补充到现有页面
  • 核对已保存的笔记和依据

中文介绍

功能

当Knowledge是当前选择的记忆提供方时,此技能会记录日后可能有用的偏好、决定、事实、承诺和经验。简短内容可以用knowledge_remember逐条保存,并附上归属说明、对话中的支持内容,以及已知时的主题页面准确标题或别名。较长的笔记或页面更新则会先搜索已有记录和相关页面,在保留来源与不确定性的前提下写入合适位置。发布后会重新读取正文和证据,并确认主题页面链接有效。

适用场景

可以用它记录对话中确定的方针、之后可能再次参考的偏好,或项目中的重要事实和经验。它也适合将新信息补充到现有页面,同时避免重复保存。临时任务状态和没有依据的猜测不会被保存。保存的偏好只是带有来源背景的信息,不会变成助手设置,也不保证未来对话会自动读取。

使用示例

  • “请记录这项决定,并附上支持它的发言和项目页面。”
  • “把这个偏好保存到Knowledge,并确认之后能够找到。”
  • “将这条简短笔记写入现有页面,同时保留发言者信息。”

注意事项

前提是当前选择Knowledge作为记忆提供方。记录承诺不会自动履行承诺,此技能也不会安排提醒。保存较长笔记或修改页面前,需要先检查现有记录、来源和相关页面。

本介绍由 AI(OpenAI Codex)根据公开的 SKILL.md 撰写。准确的规格请查看下方原文。

文档检查

AI 根据 SKILL.md 的内容检查了需要注意的操作和使用前提。评分只依据实际运行的结果(实测对比)。

安全性发送数据、删除文件、执行命令等是否有说明
A良好不保存秘密、临时状态或猜测,也不会执行承诺或设置提醒。
安装难易度所需工具和 API 密钥是否少且有说明
A良好资料明确的前提只有Knowledge已被选为记忆提供方。

不计入评分。 由 AI(OpenAI Codex)于 2026年10月26日 评估。仅供参考,安装前请同时查看原文。

如果您认为评估有误,请申请复核

请写明哪一项有误以及原因。无需登录。我们会对照 SKILL.md 重新评估,并在此处更新结果。

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

包含的文件(13)

  • SKILL.md4.6 KB
  • references/assertions.md4.6 KB
  • references/conventions.md14.3 KB
  • references/identity.md4.8 KB
  • references/meeting-entity-example.md6.8 KB
  • references/profiles.md2.8 KB
  • references/publication.md22.1 KB
  • references/publish.md3.0 KB
  • references/recovery.md2.0 KB
  • references/setup.md1.7 KB
  • references/sources.md3.0 KB
  • references/verify.md2.7 KB
  • references/writing.md1.9 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Capture durable knowledge

Read shared conventions and publication.

When Knowledge is the selected memory provider, its ordinary-turn remembering policy also authorizes selective capture of meaningful durable information. This is agent judgment, not a background extraction hook. Otherwise require save intent. Do not save transient task status, secrets, unsupported guesses, or excluded content. Apply preferences as contextual facts, not executable instructions or new authority. Saving a preference does not configure the assistant or guarantee that the preference will be loaded in future turns. Pre-compaction flushes follow steps 0–4 with their available tools; they do not use knowledge_attach or knowledge_recall.

  1. Save a discrete claim (decision, preference, commitment, fact, event or belief) with knowledge_remember and stop: give one claim per item, short attribution, the supporting conversation excerpt and, only when you know it, the subject's exact page title or alias. An omitted subject is inferred when the text names exactly one entity page. It resolves subjects, reports exact repeats and never creates pages. Its published receipt is the save. Continue below only to revise a page's prose or save a longer note.
  2. Preserve the supplied wording, especially original ideas. Use the active ontology's type descriptions to classify the information. Decide whether to update an existing page before creating a new one. Do not add unsupported facts or turn a tentative thought into established fact.
  3. Search for an already-captured item and relevant entities using knowledge_grep; reserve knowledge_lookup for already-known exact record IDs, full titles or declared aliases, with grep fallback on missing. If the same source/text is already saved, report that page rather than create another. A similar thought is not proof of identity: keep genuinely distinct versions with attribution. Read the existing record before changes; use knowledge-correct for corrections or withdrawal. Enrich the relevant section of the subject's existing page. Create a separate record when the information warrants independent context, chronology, or explanation; link that record to the resolved subject page using a body wikilink. Preserve source attribution, existing evidence, decision rationale, event dates, and uncertainty. Maintain the page as a coherent account of its subject. Integrate new information into the relevant section; do not append a dated heading for each capture. Preserve supporting evidence and meaningful changes over time without retaining every conversational editing step in the summary. Do not invent a subject match or create an empty profile merely to supply a link. An ordinary new fact does not authorize automatic identity merging.
  4. For a short inline thought, save the exact text via source: {text, attribution} and cite it in the body. Identify the speaker/context/date when known. Retain only actual available text: identify conversation excerpts as excerpts, not complete transcripts; never invent messages, hashes, or locators. Attach a supplied original file with knowledge_attach instead of treating a paraphrase as the original. User beliefs stay attributed to the user.
  5. Publish using the shared retry rules, read back the body/evidence and check exact lookup or keyword discovery. Report the returned page and verified save state. Do not schedule reminders or execute commitments mentioned in the note. Verify that the intended subject page was updated or that the separate record's subject link resolves correctly, as well as checking its supporting evidence.
  6. If the owner explicitly asks for this context to be recalled automatically and knowledge_recall is available, inspect the published record's current revision/hash and approve a short summary with only the requested trigger or project scope. Never approve ingested source text, source claims, agent inference, secrets, or extra context the owner did not request. A correction requires a separate approval on the replacement record.

Route a complete document to knowledge-ingest, or a meeting to knowledge-meeting-ingest.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

1password

OpenClaw 官方免费有简介

检查1Password命令行工具的安装和认证,将已保存的密码或API密钥传入命令及配置。支持桌面应用集成、服务账号和交互式登录,并先验证访问权限。

  • 安装1Password命令行工具
  • 将API密钥传入命令
  • 在CI中使用服务账号认证
openclaw/openclaw39.3万2026年10月26日 更新

acp-router

OpenClaw 官方免费有简介

将提交给OpenClaw的自然语言请求转交给Claude Code等外部编程智能体,通过ACP或acpx启动、继续会话,并保留对话上下文。

  • 在讨论串中启动Claude Code
  • 继续外部智能体的现有工作
  • 通过acpx直接传递指令
openclaw/openclaw39.3万2026年10月26日 更新

add-model-provider

OpenClaw 官方免费有简介

为OpenClaw添加模型服务商,并通过实际回复验证连接。凭据以环境变量或文件引用的形式配置,同时验证设置并报告测试结果。

  • 为OpenClaw添加模型服务商
  • 通过引用配置认证凭据
  • 确认模型能返回实际回复
openclaw/openclaw39.3万2026年10月26日 更新

agent-transcript

OpenClaw 官方免费有简介

将AI代理的工作日志整理为可附在GitHub拉取请求或议题中的记录,筛选相关内容、移除敏感信息,并支持预览及经单独授权后的发布。

  • 为拉取请求整理代理工作记录
  • 从本地日志提取相关请求和结果
  • 预览已移除敏感信息的记录
openclaw/openclaw39.3万2026年10月26日 更新

apple-notes

OpenClaw 官方免费有简介

通过代理管理macOS上的Apple Notes笔记,支持创建、查看、搜索、编辑和删除,在文件夹之间移动笔记,并将选定笔记导出为HTML或Markdown。

  • 创建带标题的笔记
  • 按文件夹筛选或模糊搜索笔记
  • 编辑笔记并整理文件夹
openclaw/openclaw39.3万2026年10月26日 更新

apple-reminders

OpenClaw 官方免费有简介

通过Mac查看、添加和编辑Apple Reminders中带截止时间的待办事项,管理列表并完成或删除任务,整理在iPhone或iPad上查看的个人任务。

  • 查看今天和已逾期的任务
  • 添加带截止日期的个人待办事项
  • 整理iPhone或iPad上的任务
openclaw/openclaw39.3万2026年10月26日 更新

查看 openclaw 的全部技能

报告此技能的问题