context-pack

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Context Pack

上下文包

Store and retrieve context through Epismo context packs — so knowledge survives tool switches, session ends, and team handoffs.

The unit of organization is a block inside a pack. The goal is one well-structured pack per topic, grown over time by adding and refining blocks — not many small packs.

For Epismo connection setup, CLI/MCP surface conventions, scope model, share URL resolution, and error handling, see Epismo Basics.

Surface selection: CLI and MCP connect to the same Epismo service. Use CLI if available; fall back to MCP if not. Never use both in the same session.

通过Epismo上下文包存储和检索上下文——让知识在工具切换、会话结束和团队交接后得以保留。

组织的基本单元是包内的block（模块）。目标是每个主题对应一个结构清晰的包，通过添加和优化模块逐步完善，而非创建大量小型包。

关于Epismo连接设置、CLI/MCP界面约定、范围模型、共享URL解析和错误处理，请查看Epismo基础。

界面选择： CLI和MCP连接到同一Epismo服务。优先使用CLI；若不可用则退而使用MCP。同一会话中切勿同时使用两者。

Commands

命令

Command	Natural language triggers	→
`pack`	pack this, save this, summarize session	PACK
`new`	new pack, start fresh, hand off a task, share project status	NEW
`publish [<id>]`	publish this, make this public, publish a guide, share with community	PUBLISH
`get <id\|alias>`	get this ID, load this ID, restore from ID, read alias, open alias	GET
`find <query>`	what context do I have, load my context, search	FIND
`update [<id\|alias>]`	edit this pack, update my last pack	UPDATE
`organize`	reorganize blocks, split this, clean up	ORGANIZE
—	unclear intent	Ask once

命令	自然语言触发词	→
`pack`	pack this, save this, summarize session	PACK
`new`	new pack, start fresh, hand off a task, share project status	NEW
`publish [<id>]`	publish this, make this public, publish a guide, share with community	PUBLISH
`get <id\|alias>`	get this ID, load this ID, restore from ID, read alias, open alias	GET
`find <query>`	what context do I have, load my context, search	FIND
`update [<id\|alias>]`	edit this pack, update my last pack	UPDATE
`organize`	reorganize blocks, split this, clean up	ORGANIZE
—	意图不明确	询问一次

Operations (context packs)

操作（上下文包）

Operation	CLI	MCP
`search pack`	`epismo pack search --type context [--query <keywords>] [--filter '{...}']`	`epismo_pack_search`
`get pack`	`epismo pack get --id <id> [--full] [--block-id <id>]` <br> `epismo pack get --alias <alias>`	`epismo_pack_get`
`create pack`	`epismo pack create --input '<json>'`	`epismo_pack_create`
`update pack`	`epismo pack update --id <id> --input '<json>'`	`epismo_pack_update`
`delete pack`	`epismo pack delete --id <id>`	`epismo_pack_delete`
`like pack`	`epismo pack like --id <id> --liked`	`epismo_pack_like`
`upsert alias`	`epismo alias upsert --type context --id <id> --alias <name>`	—
`get alias`	`epismo alias get --alias <name>`	—
`list aliases`	`epismo alias list --type context`	—
`delete alias`	`epismo alias delete --alias <name>`	—

操作	CLI	MCP
`search pack`	`epismo pack search --type context [--query <keywords>] [--filter '{...}']`	`epismo_pack_search`
`get pack`	`epismo pack get --id <id> [--full] [--block-id <id>]` <br> `epismo pack get --alias <alias>`	`epismo_pack_get`
`create pack`	`epismo pack create --input '<json>'`	`epismo_pack_create`
`update pack`	`epismo pack update --id <id> --input '<json>'`	`epismo_pack_update`
`delete pack`	`epismo pack delete --id <id>`	`epismo_pack_delete`
`like pack`	`epismo pack like --id <id> --liked`	`epismo_pack_like`
`upsert alias`	`epismo alias upsert --type context --id <id> --alias <name>`	—
`get alias`	`epismo alias get --alias <name>`	—
`list aliases`	`epismo alias list --type context`	—
`delete alias`	`epismo alias delete --alias <name>`	—

PACK

Goal: save current context as a block inside the right pack. Find an existing pack and add or refine a block; create a new pack only when nothing relevant exists.

目标： 将当前上下文保存为对应包内的一个模块。查找现有包并添加或优化模块；仅当无相关包存在时才创建新包。

Step 1 — Find the right pack

步骤1 — 找到对应包

Infer 2–4 topic keywords from the current session. Search private packs (titles only — one fast call).

search pack

—

type: context

query: <inferred topic>

filter: { visibility: ["private"] }

Result	Action
One clear match	Fetch it → add or update a block → upsert
Multiple candidates	Show titles and IDs → ask user to pick
No match	Proceed as NEW

从当前会话中推断2-4个主题关键词。搜索私有包（仅标题——快速调用）。

search pack

—

type: context

query: <推断的主题>

filter: { visibility: ["private"] }

结果	操作
唯一明确匹配项	获取包 → 添加或更新模块 → 插入更新
多个候选包	显示标题和ID → 请求用户选择
无匹配项	按NEW流程处理

Step 2 — Identify the right block

步骤2 — 确定对应模块

get pack

— fetch the pack and read its existing blocks. Decide:

Update an existing block — if the new content belongs to a block that already exists (e.g., decisions, next steps), integrate it there. Rewrite the block so it reads as a coherent whole, not as an append.
Add a new block — if the new content is a distinct topic not covered by any existing block.

The pack should read well from scratch at any point. Do not leave stale or contradicted information in place.

get pack

— 获取包并读取现有模块。决定：

更新现有模块 — 如果新内容属于已存在的模块（如决策、下一步计划），则整合到该模块中。重写模块使其内容连贯，而非简单追加。
添加新模块 — 如果新内容是现有模块未覆盖的独立主题。

包在任何时候都应易于从头阅读。请勿保留过时或矛盾的信息。

Step 3 — Update and return

步骤3 — 更新并返回

update pack

json

{
  "id": "<existing-id>",
  "content": "<top-level summary or intro — does not include block content>",
  "blocks": [
    { "op": "update", "id": "<existing-block-id>", "title": "<block-title>", "content": "<updated block content>" },
    { "op": "add", "title": "<new-block-title>", "content": "<new block content>" }
  ]
}

Omitted fields are left unchanged. Omitting
```
"blocks"
```
means no block changes.
```
"op": "update"
```
updates an existing block by ID.
```
"op": "add"
```
adds a new block.
```
"op": "remove"
```
deletes a block by ID (only
```
"id"
```
needed).
```
"content"
```
at the top level is a brief intro or summary. Block content lives in
```
"blocks[]"
```
, not in the top-level
```
"content"
```
.

context  <context-id>  <context-title>
block    <block-id>    <block-title>

update pack

json

{
  "id": "<existing-id>",
  "content": "<顶级摘要或介绍——不包含模块内容>",
  "blocks": [
    { "op": "update", "id": "<existing-block-id>", "title": "<block-title>", "content": "<updated block content>" },
    { "op": "add", "title": "<new-block-title>", "content": "<new block content>" }
  ]
}

省略的字段保持不变。省略
```
"blocks"
```
表示不修改模块。
```
"op": "update"
```
按ID更新现有模块。
```
"op": "add"
```
添加新模块。
```
"op": "remove"
```
按ID删除模块（仅需
```
"id"
```
）。
顶级
```
"content"
```
是简短的介绍或摘要。模块内容位于
```
"blocks[]"
```
中，而非顶级
```
"content"
```
。

context  <context-id>  <context-title>
block    <block-id>    <block-title>

NEW

Goal: create a fresh pack with an initial block structure. Use when no relevant pack exists, or when the content is clearly a separate topic.

目标： 创建一个带有初始模块结构的新包。当无相关包存在，或内容明显属于独立主题时使用。

Step 1 — Design the block structure

步骤1 — 设计模块结构

Before writing, decide how the content divides into blocks. Each block should be focused enough to update independently and broad enough to stay relevant over time.

Design for selective fetch. Because blocks can be loaded individually with

--block-id

, a well-split pack lets future sessions load only what they need without pulling the whole pack. Aim for blocks where any one block answers a distinct question on its own.

Use case	Starting blocks
Session / tool handoff	Context, Decisions, Next Steps
Source summary (YouTube, blog, paper)	Source, Summary, Key Takeaways, Reuse Notes
Project memory / working context	Purpose, Constraints, Decisions, References
Prompt or instruction pack	When To Use This, Inputs, Instructions, Output Expectations
Project status	Summary, Progress, Blockers
Team rules or plan	Purpose, Rules, Plan
Task handoff	Current State, What Remains, Context for Recipient

Good block boundaries: topic changes, audience changes, or update frequency changes (e.g., "Decisions" is stable; "Next Steps" changes every session — keep them separate).

For templates, see Content Templates.

编写前，确定内容如何划分为模块。每个模块应足够聚焦，可独立更新；同时足够宽泛，能长期保持相关性。

为选择性获取设计。 因为可以通过

--block-id

单独加载模块，结构合理的包能让后续会话仅加载所需内容，无需获取整个包。目标是每个模块能独立回答一个明确的问题。

使用场景	初始模块建议
会话/工具交接	上下文、决策、下一步计划
资源摘要（YouTube、博客、论文）	来源、摘要、关键要点、复用提示
项目记忆/工作上下文	目的、约束条件、决策、参考资料
提示词或指令包	使用场景、输入、指令、输出预期
项目状态	摘要、进展、阻塞点
团队规则或计划	目的、规则、计划
任务交接	当前状态、剩余工作、接收方上下文

合理的模块边界：主题变化、受众变化或更新频率变化（例如，“决策”模块稳定；“下一步计划”模块每次会话都会变化——应分开）。

模板请查看内容模板。

Step 2 — Write

步骤2 — 编写内容

Content rules:

Each block is self-contained — no "see above" references
Prefer scannable structure: bullets, short paragraphs, and small tables only when they help
Include IDs, URLs, and precise names so the reader can act without searching
Title: infer from session topic. Do not ask unless genuinely ambiguous.

内容规则：

每个模块独立完整——避免“参见上文”的引用
优先采用易于扫描的结构：项目符号、短段落，仅在必要时使用小型表格
包含ID、URL和精确名称，让读者无需搜索即可采取行动
标题： 从会话主题推断。除非确实存在歧义，否则无需询问用户。

Step 3 — Publish

步骤3 — 发布

Default

private

. Use PUBLISH to go public.

create pack

json

{
  "title": "<title>",
  "content": "<top-level summary or intro>",
  "type": "context",
  "visibility": "private",
  "blocks": [
    { "title": "<block-title>", "content": "<block content>" },
    { "title": "<block-title>", "content": "<block content>" }
  ]
}

Blocks are passed as a separate
```
"blocks[]"
```
array — not embedded in the top-level
```
"content"
```
string.
```
"content"
```
at the top level is a brief intro only. All substantive content belongs in blocks.

Who needs it	`visibility`	Access target
Just me	`"private"`	omit `targets`
My team	`"private"`	`targets.projectIds=["pj_xxx"]`

context  <context-id>  <context-title>
block    <block-id>    <block-title>

默认

private

（私有）。使用PUBLISH转为公开。

create pack

json

{
  "title": "<title>",
  "content": "<顶级摘要或介绍>",
  "type": "context",
  "visibility": "private",
  "blocks": [
    { "title": "<block-title>", "content": "<block content>" },
    { "title": "<block-title>", "content": "<block content>" }
  ]
}

模块作为独立的
```
"blocks[]"
```
数组传递——不要嵌入到顶级
```
"content"
```
字符串中。
顶级
```
"content"
```
仅为简短介绍。所有实质性内容都应放在模块中。

受众	`visibility`	访问目标
仅自己	`"private"`	省略 `targets`
我的团队	`"private"`	`targets.projectIds=["pj_xxx"]`

context  <context-id>  <context-title>
block    <block-id>    <block-title>

PUBLISH

Goal: make a pack publicly discoverable. Always requires explicit user confirmation before writing.

Two paths:

Situation	Path
Existing private pack worth sharing	Promote — change visibility to `public`
New content written for a broad audience	Create new public pack

目标： 让包可被公开发现。写入前始终需要用户明确确认。

两种路径：

场景	路径
现有私有包值得分享	升级——将可见性改为 `public` （公开）
为广泛受众创作的新内容	创建新的公开包

Promote: private → public

升级：私有→公开

```
get pack
```
— fetch the pack. Run the Public Review Gate. Flag issues before proceeding.
Confirm with user: "Publish '{title}' (
{id}
) as public under category
{category}
?"
```
update pack
```
:

json

{
  "id": "<id>",
  "visibility": "public",
  "category": "<category>"
}

```
get pack
```
— 获取包。运行公开审核门槛。继续前标记问题。
向用户确认：“是否将'{title}'（
{id}
）作为
{category}
分类下的公开包发布？”
```
update pack
```
:

json

{
  "id": "<id>",
  "visibility": "public",
  "category": "<category>"
}

Create new public

创建新公开包

Write for an external reader using the public guide template in Content Templates. Content must be self-contained and pass the Public Review Gate.

Choose category carefully — it determines how people find this pack. See Category Reference.

Confirm with user, then

create pack

json

{
  "title": "<title>",
  "content": "<content>",
  "type": "context",
  "visibility": "public",
  "category": "<category>"
}

Return ID, title, and share URL. For share URL resolution, see Epismo Basics — Resolving Share URLs.

context  <context-id>  <context-title>
share    https://epismo.ai/hub/contexts/<id>

使用内容模板中的公开指南模板为外部读者编写内容。内容必须独立完整，并通过公开审核门槛。

谨慎选择分类——它决定了人们如何找到这个包。查看分类参考。

向用户确认后，执行

create pack

json

{
  "title": "<title>",
  "content": "<content>",
  "type": "context",
  "visibility": "public",
  "category": "<category>"
}

返回ID、标题和共享URL。关于共享URL解析，请查看Epismo基础——解析共享URL。

context  <context-id>  <context-title>
share    https://epismo.ai/hub/contexts/<id>

GET

Goal: fetch a pack by ID, alias, or explicit read/open target.

目标： 通过ID、别名或明确的读取/打开目标获取包。

Route intent before resolving

解析前先路由意图

Prefer alias-first unless the input is obviously a search query.

Input pattern	Route	Why
`get ...` , `use ...` , `load ...` , `open ...` , `read ...` , `restore ...`	GET	Explicit retrieval
`find ...` , `search ...` , `what context do I have` , `show my packs`	FIND	Explicit discovery
Bare UUID	GET	IDs are unambiguous
Short ambiguous phrase	GET	Try alias first, then search if it misses
Obvious search query, question, or long descriptive phrase	FIND	Discovery intent is clearer than alias intent

优先别名优先，除非输入明显是搜索查询。

输入模式	路由	原因
`get ...` , `use ...` , `load ...` , `open ...` , `read ...` , `restore ...`	GET	明确的检索意图
`find ...` , `search ...` , `what context do I have` , `show my packs`	FIND	明确的发现意图
纯UUID	GET	ID无歧义
简短歧义短语	GET	先尝试别名，失败则执行FIND
明显的搜索查询、问题或长描述性短语	FIND	发现意图比别名意图更清晰

Resolve the input

解析输入

UUID →
```
get pack --id
```
.
```
@handle/name
```
or one compact token like
```
weekly-handoff
```
→
```
get pack --alias
```
; if it misses, run FIND with the same text.
Short phrase like
```
auth refactor handoff
```
→ try
```
get pack --alias
```
first; if it misses, run FIND.
Question, explicit search wording, or long descriptive text → FIND first.
```
get/read/open/use <target>
```
always counts as retrieval intent.

get pack

— by

id

, or by

alias

. Default returns outline only; pass

--full

for all blocks, or

--block-id

to load a single block.

Read the most relevant block first. Continue from there without re-reading history.

UUID →
```
get pack --id
```
。
```
@handle/name
```
或类似
```
weekly-handoff
```
的紧凑标识 →
```
get pack --alias
```
；如果失败，使用相同文本执行FIND。
短短语如
```
auth refactor handoff
```
→ 先尝试
```
get pack --alias
```
；如果失败，执行FIND。
问题、明确的搜索措辞或长描述性文本 → 先执行FIND。
```
get/read/open/use <target>
```
始终视为检索意图。

get pack

— 通过

id

或

alias

获取。默认仅返回大纲；传递

--full

获取所有模块，或传递

--block-id

加载单个模块。

先读取最相关的模块。从该模块继续，无需重新读取历史。

FIND

Goal: discover the right pack when the ID is not known.

search pack

— scan titles only (no full content). Use this for natural-language discovery requests and multi-keyword topic phrases. Search in this order:

type: context

query: <topic>

filter: { visibility: ["private"] }

type: context

query: <topic>

filter: { like: "liked" }

type: context

query: <topic>

filter: { visibility: ["public"] }

Present the title list; if the match is clear,

get pack

immediately.

For filter keys and search recipes, see Search & Discovery.

目标： 在未知ID的情况下找到正确的包。

search pack

— 仅扫描标题（不扫描完整内容）。用于自然语言发现请求和多关键词主题短语。按以下顺序搜索：

type: context

query: <topic>

filter: { visibility: ["private"] }

type: context

query: <topic>

filter: { like: "liked" }

type: context

query: <topic>

filter: { visibility: ["public"] }

展示标题列表；如果匹配明确，立即执行

get pack

。

关于过滤键和搜索方案，请查看搜索与发现。

UPDATE

Goal: edit an existing pack directly.

目标： 直接编辑现有包。

ID or alias known

已知ID或别名

Always fetch before writing.

get pack

→ inspect current blocks →

update pack

with

id

and block operations using

op

fields.

For

update <alias> based on this conversation

merge new context into the right existing blocks
rewrite blocks coherently instead of appending raw notes
add a new block only for a distinct new topic

写入前始终先获取包。

get pack

→ 检查当前模块 → 使用

id

和带

op

字段的模块操作执行

update pack

。

对于

update <alias> based on this conversation

将新上下文合并到对应的现有模块中
连贯重写模块，而非追加原始笔记
仅为全新的独立主题添加新模块

ID unknown

未知ID

search pack

—

type: context

query: <inferred topic>

filter: { visibility: ["private"] }

One clear match → fetch and update without asking.
Multiple candidates → show titles and IDs, ask the user to pick.
No match → fall back to NEW.

"Last pack" shortcut: search private context packs and take the first result from the default recent-first outline.

search pack

—

type: context

query: <推断的主题>

filter: { visibility: ["private"] }

唯一明确匹配项 → 获取并更新，无需询问用户。
多个候选包 → 显示标题和ID，请求用户选择。
无匹配项 → 退而执行NEW。

“上一个包”快捷方式： 搜索私有上下文包，从默认的“最近优先”大纲中选取第一个结果。

ORGANIZE

Goal: improve the block structure of an existing pack.

The most common need is not managing many packs — it's making the blocks inside one pack cleaner and more useful.

目标： 优化现有包的模块结构。

最常见的需求不是管理多个包——而是让单个包内的模块更清晰、更有用。

Actions

操作

Situation	Action
A block has grown too large or covers multiple topics	Split — divide into two focused blocks, rewrite each
Two blocks overlap or one has become redundant	Merge — combine into one coherent block, remove the other
A block is no longer relevant	Remove — delete the block from the pack
The whole pack is no longer needed	Delete — delete the pack (needs approval)

All changes are applied via

update pack

using

op

fields. Use

"op": "add"

for new blocks,

"op": "update"

for existing ones,

"op": "remove"

to delete a block by ID.

delete pack

requires explicit user approval.

场景	操作
模块过大或涵盖多个主题	拆分 — 拆分为两个聚焦模块，分别重写
两个模块重叠或其中一个已冗余	合并 — 合并为一个连贯模块，移除另一个
模块不再相关	移除 — 从包中删除该模块
整个包不再需要	删除 — 删除包（需用户批准）

所有变更通过

update pack

使用

op

字段应用。使用

"op": "add"

添加新模块，

"op": "update"

更新现有模块，

"op": "remove"

按ID删除模块。

delete pack

需要用户明确批准。

Write Safety

写入安全

Default private —
```
pack
```
,
```
new
```
, and
```
update
```
always write private. Use PUBLISH to go public.
No silent writes — if scope is unclear, ask once before writing.
Approval required — public publication, deletion, and overwriting another owner's pack require explicit user confirmation before writing.

For the full approval matrix, see Visibility & Sharing — Approval Boundary.

默认私有 —
```
pack
```
、
```
new
```
和
```
update
```
始终写入私有包。使用PUBLISH转为公开。
无静默写入 — 如果范围不明确，写入前询问一次。
需要批准 — 公开发布、删除包或覆盖其他所有者的包需要用户明确确认后才能写入。

完整的批准矩阵请查看可见性与共享——批准边界。

Operation Output

操作输出

After every operation, return in this order:

Context and block — always return both ID and title at each level that was affected
What changed — one sentence
Next action — single most useful next step (omit if none)

context  <context-id>  <context-title>
block    <block-id>    <block-title>    # when a specific block was created or updated

Skip analysis and evidence unless the user asked for it.

每次操作后，按以下顺序返回：

上下文和模块 — 始终返回受影响层级的ID和标题
变更内容 — 一句话说明
下一步操作 — 最有用的单个后续步骤（若无则省略）

context  <context-id>  <context-title>
block    <block-id>    <block-title>    # 当特定模块被创建或更新时显示

除非用户要求，否则跳过分析和证据。

Source of Truth

事实来源

Repository:

https://github.com/epismoai/skills

仓库:

https://github.com/epismoai/skills