Skip to content

Skills ​

The Context Agent plugin contains nine Skills. Four are entries you invoke, one is an authoring assistant you start in plain language, and four are Indexers the workflow selects. All of them leave workspace state and lifecycle decisions to the context CLI. For a short tour aimed at first-time users, see Commands and Skills.

Entries ​

SkillActivates whenDoesHands off to
contextYou invoke Context explicitly, ask to reorganize an existing knowledge map or site navigation, or continue an active Context workflow to build, inspect, update, recover or package knowledgeCreates or continues a Context knowledge workspace and follows the CLI's current Route through production, review, update and buildThe CLI; Indexers selected for each stage
context-planYou ask for project planning or continue a PLAN-*.md, or an authorized Context task involves more than 30 source documents or substantive investigation of at least two repositoriesResearches in temporary storage and writes a root PLAN-YYYYMMDD-topic.md for review, then runs the project one stage at a timecontext, which performs each stage
context-inspect-searchYou ask a knowledge question, or a host or Bot configuration routes questions hereAnswers from knowledge packages or approved knowledge and traces answers to their sources; read-only, no workspace requiredcontext for accepted improvement suggestions
context-repo-contentYou ask to create, edit or register documentation and authored Skills in the same repositoryMaintains repo-content.yaml and its symlink view, keeping one original in its project directory; never starts production, builds, publishes or commits—

None of them starts on its own for ordinary planning, design or coding.

Authoring assistant ​

SkillActivates whenDoes
context-indexer-createYou explicitly ask to create a new Indexer Skill for code, documents, notes or session summariesWrites a reusable Skill into the directory you choose; does not initialize a workspace or start production. It has no menu command — ask in plain language. See Creating an Indexer.

Indexers ​

SkillInterpretsSelected
context-code-indexerCode skeletons of an authorized module, to write source-grounded articlesFor the current planning or writing task — not as a standalone repository audit
context-markdown-indexerOutlines of captured documentsFor the current authorized planning or writing task — not as an import workflow
context-note-indexerSaved notes, excerpts and observationsWhen the current authorized task selects it — not for importing sources or scanning conversation history
context-sessions-indexerSaved conversation summariesWhen the current authorized task selects it — same limits as notes

Installing an Indexer makes it discoverable, not enabled for every workspace: the Agent chooses Indexers for the current sources and requirements, and the CLI supplies task directories and checks every source reference. Indexers are installed without a plugin namespace, so their names are the same in every host. See Community Indexers.

Host spelling ​

HostEntries
Claude Code/c4a:context, /c4a:context-plan, /c4a:context-inspect-search, /c4a:context-repo-content
Cursor/c4a-context, /c4a-context-plan, /c4a-context-inspect-search, /c4a-context-repo-content
CodexSkills by name: context, context-plan, context-inspect-search, context-repo-content

A local install into one repository with context plugin install --local has no plugin namespace; the host discovers the entries in its own directory. Restart the Agent session after installing or updating the plugin.

技能清单 ​

Context Agent 插件包含九个 Skill。其中四个是由你调用的入口,一个是用自然语言启动的创作助手,另外四个是由工作流选用的 Indexer。它们都把知识工作区状态和生命周期决策交给 context CLI。面向初次使用者的简要介绍见命令与技能。

入口 ​

Skill何时激活作用交给
context你显式调用 Context,要求重新组织已有的知识地图或站点导航,或继续进行中的 Context 工作流以构建、检查、更新、恢复或打包知识创建或继续 Context 知识工作区,并按照 CLI 的当前 Route 完成生产、审核、更新和构建CLI;每个阶段选用的 Indexer
context-plan你要求做项目规划或继续某个 PLAN-*.md,或某个已授权的 Context 任务涉及 30 份以上来源文档,或需要实质性调查至少两个仓库在临时存储中调研,并在根目录写出 PLAN-YYYYMMDD-topic.md 供审核,然后逐个阶段运行项目context,由它执行每个阶段
context-inspect-search你提出知识问题,或宿主或 Bot 配置把问题路由到这里基于知识包或已批准的知识回答,并把答案追溯到来源;只读,不需要知识工作区对于被接受的改进建议,交给 context
context-repo-content你要求创建、编辑或登记同一仓库中的文档和自编 Skill维护 repo-content.yaml 及其符号链接视图,在项目目录中只保留一份原件;绝不启动生产、构建、发布或提交—

在普通的规划、设计或编码中,它们都不会自行启动。

创作助手 ​

Skill何时激活作用
context-indexer-create你明确要求为代码、文档、笔记或会话摘要创建新的 Indexer Skill把一个可复用的 Skill 写入你选择的目录;不会初始化知识工作区,也不会启动生产。它没有菜单命令——用自然语言提出即可。参见创建 Indexer。

Indexer ​

Skill解读对象选用时机
context-code-indexer已授权模块的代码骨架,用于撰写基于来源的文章用于当前的规划或写作任务——不作为独立的仓库审计
context-markdown-indexer已采集文档的大纲用于当前已授权的规划或写作任务——不作为导入工作流
context-note-indexer已保存的笔记、摘录和观察记录当前已授权的任务选用它时——不用于导入来源或扫描对话历史
context-sessions-indexer已保存的对话摘要当前已授权的任务选用它时——限制与笔记相同

安装某个 Indexer 只是让它可被发现,并不会在每个知识工作区中启用:Agent 根据当前的来源和需求选择 Indexer,CLI 提供任务目录并检查每一处来源引用。Indexer 安装时不带插件命名空间,因此在每个宿主中名称都相同。参见社区 Indexer。

各宿主中的写法 ​

宿主入口
Claude Code/c4a:context、/c4a:context-plan、/c4a:context-inspect-search、/c4a:context-repo-content
Cursor/c4a-context、/c4a-context-plan、/c4a-context-inspect-search、/c4a-context-repo-content
Codex按名称调用的 Skill:context、context-plan、context-inspect-search、context-repo-content

通过 context plugin install --local 只安装到单个仓库时,没有插件命名空间;宿主会在该仓库自己的目录中发现这些入口。安装或更新插件后,请重启 Agent 会话。