pensieve

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Pensieve

Route user requests to the correct tool. When uncertain, confirm first.

将用户请求路由到正确的工具。存在不确定性时请先确认。

Intent Routing

意图路由

Explicit intent takes priority: if the user explicitly names a tool or trigger word, route directly.
Infer from session stage (when no explicit command is given):
- New project or blank context →
```
init
```
  | Version uncertainty →
```
upgrade
```
  | Migration/residue uncertainty →
```
migrate
```
- Exploring codebase or locating issues → check
```
<USER_DATA_ROOT>/knowledge/
```
  first, then use
```
self-improve
```
  to write findings
- Development complete or retrospective signals →
```
self-improve
```
  | Complex task needing decomposition →
```
loop
```
When uncertain, confirm first.

<example> User: "Initialize pensieve for me" → Route: tools/init/_init.md User: "Check if there are any data issues" → Route: tools/doctor/_doctor.md User: "This task is complex, run it with loop" → Route: tools/loop/_loop.md </example>

显式意图优先：如果用户明确指定了工具或触发词，直接路由。
根据会话阶段推断（无显式命令时）：
- 新项目或空白上下文 →
```
init
```
  | 版本不确定 →
```
upgrade
```
  | 迁移/遗留问题不确定 →
```
migrate
```
- 探索代码库或定位问题 → 首先检查
```
<USER_DATA_ROOT>/knowledge/
```
  ，然后使用
```
self-improve
```
  写入发现内容
- 开发完成或出现复盘信号 →
```
self-improve
```
  | 需要拆解的复杂任务 →
```
loop
```
存在不确定性时先确认。

<example> 用户："帮我初始化pensieve" → 路由：tools/init/_init.md 用户："检查是否存在数据问题" → 路由：tools/doctor/_doctor.md 用户："这个任务很复杂，用loop运行" → 路由：tools/loop/_loop.md </example>

Global Rules (Summary)

全局规则（摘要）

Boundary priority: version/compatibility issues go through
```
upgrade
```
; migration/residue cleanup goes through
```
migrate
```
.
Confirm before executing: when the user has not explicitly issued a command, confirm first.
Keep links connected:
```
decision/pipeline
```
must have at least one
```
[[...]]
```
link.
Read spec before writing data: read the corresponding README before creating/checking user data.

Full rules in
references/shared-rules.md

边界优先：版本/兼容性问题走
```
upgrade
```
；迁移/遗留清理走
```
migrate
```
。
执行前确认：用户未明确下达命令时，先进行确认。
保持链接连通：
```
decision/pipeline
```
必须至少包含一个
```
[[...]]
```
链接。
写数据前先读规范：创建/检查用户数据前请先阅读对应的README。

完整规则见
references/shared-rules.md

Tool Execution Protocol

工具执行协议

Before executing any tool, read its

### Use when

section to confirm applicability. For tool boundaries and redirect rules, see

references/tool-boundaries.md

执行任何工具前，请先阅读其「### Use when」部分确认适用性。工具边界和重定向规则请参考

references/tool-boundaries.md

。

Routing Table

路由表

Intent	Tool spec (read first)	Trigger words
Initialize	`<SYSTEM_SKILL_ROOT>/tools/init/_init.md`	init, initialize
Version update	`<SYSTEM_SKILL_ROOT>/tools/upgrade/_upgrade.md`	upgrade, version
Structure migration	`<SYSTEM_SKILL_ROOT>/tools/migrate/_migrate.md`	migrate, migration, clean old paths
Health check	`<SYSTEM_SKILL_ROOT>/tools/doctor/_doctor.md`	doctor, check, format check
Archive experience	`<SYSTEM_SKILL_ROOT>/tools/self-improve/_self-improve.md`	self-improve, archive, reflect
Iterative execution	`<SYSTEM_SKILL_ROOT>/tools/loop/_loop.md`	loop, iterative execution, execute pipeline

意图	工具规范（请先阅读）	触发词
初始化	`<SYSTEM_SKILL_ROOT>/tools/init/_init.md`	init, initialize
版本更新	`<SYSTEM_SKILL_ROOT>/tools/upgrade/_upgrade.md`	upgrade, version
结构迁移	`<SYSTEM_SKILL_ROOT>/tools/migrate/_migrate.md`	migrate, migration, clean old paths
健康检查	`<SYSTEM_SKILL_ROOT>/tools/doctor/_doctor.md`	doctor, check, format check
经验归档	`<SYSTEM_SKILL_ROOT>/tools/self-improve/_self-improve.md`	self-improve, archive, reflect
迭代执行	`<SYSTEM_SKILL_ROOT>/tools/loop/_loop.md`	loop, iterative execution, execute pipeline

Routing Failure Fallback

路由失败降级方案

Ambiguous intent: return candidate routes and ask the user to confirm.
Tool entry unreadable: stop and report the missing path.
Incomplete input: collect missing information before executing.

<SYSTEM_SKILL_ROOT>

is injected by the SessionStart hook; user data path is fixed at

<project>/.claude/skills/pensieve/

意图模糊：返回候选路由请用户确认。
工具入口不可读：停止执行并报告缺失路径。
输入不完整：执行前收集缺失的信息。

<SYSTEM_SKILL_ROOT>

由SessionStart钩子注入；用户数据路径固定为

<project>/.claude/skills/pensieve/