用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/SimHacker/moollm --skill return-stack命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
基于 SOC 职业分类
| name | return-stack |
| description | Where you've been is where you can go back to. |
| license | MIT |
| tier | 1 |
| allowed-tools | ["read_file","write_file"] |
| related | ["room","adventure","character","memory-palace","action-queue","card","session-log","prototype","debugging"] |
| tags | ["moollm","navigation","history","breadcrumbs","continuations","deoptimization","introspection"] |
"Where you've been is where you can go back to."
Return Stack treats navigation history as a first-class continuation — a stack of saved positions you can manipulate like browser history or a call stack.
| Programming | Browser | MOOLLM |
|---|---|---|
| Call stack | History | Return stack |
| Return address | Back button | Previous room |
| Stack frame | Tab | Room context |
| Push | Navigate | ENTER |
| Pop | Back | BACK |
| Command | Effect |
|---|---|
ENTER room | Push current room, enter new one |
BACK | Pop stack, return to previous room |
FORWARD | Redo after BACK (if available) |
HISTORY | Show the stack |
BOOKMARK | Save current position |
GOTO bookmark | Jump to saved position |
STACK | Show all open "tabs" (parallel stacks) |
FORK | Create new tab from current position |
> ENTER workshop
[Stack: lobby]
> ENTER storage
[Stack: lobby → workshop]
> ENTER archive
[Stack: lobby → workshop → storage]
> BACK
Returning to storage...
[Stack: lobby → workshop]
> BACK
Returning to workshop...
[Stack: lobby]
> HISTORY
1. lobby (start)
2. workshop
3. storage
4. archive ← furthest
Current: workshop (position 2)
Save positions for later:
> BOOKMARK "interesting-spot"
Bookmarked: workshop as "interesting-spot"
> ENTER research
> ENTER data-room
> ENTER sub-analysis
[Deep in the hierarchy]
> GOTO interesting-spot
Returning to workshop...
[Stack cleared, at bookmark]
Create parallel exploration paths:
> FORK
Created new tab from workshop.
Tab 1: lobby → workshop
Tab 2: workshop (active) ←
> ENTER experiment-A
[Tab 2: workshop → experiment-A]
> STACK
Tab 1: lobby → workshop
Tab 2: workshop → experiment-A ←
> TAB 1
Switching to Tab 1...
[Now at workshop via tab 1]
The return stack IS a continuation:
# Stored in character's pocket
return_stack:
- path: "./lobby"
context: {examining: "welcome-sign"}
- path: "./workshop"
context: {crafting: "blueprint-v2"}
- path: "./storage"
context: {searching: "rare-materials"}
# Current position
current: "./archive"
context: {reading: "old-records"}
When you BACK, you don't just return to the room — you restore the context you had there.
The stack travels with you:
> INVENT
Inventory:
- notebook
- pen
- return_stack: [lobby → workshop → storage]
You can:
HyperCard had:
MOOLLM extends this:
# character.yml
name: explorer
location: ./archive
navigation:
return_stack:
- room: ./lobby
entered: "2024-01-15T10:00:00"
- room: ./workshop
entered: "2024-01-15T10:05:00"
context:
active_task: "crafting"
- room: ./storage
entered: "2024-01-15T10:15:00"
bookmarks:
interesting-spot:
room: ./workshop
context: {task: "blueprint-review"}
start:
room: ./lobby
forward_stack: [] # After BACK, stores where you came from
The Self programming language (source of our prototype inheritance) pioneered dynamic deoptimization: aggressively inlining code for performance, then reconstructing the "logical" call stack on demand when debugging.
The LLM does this naturally for narrative:
| Self | MOOLLM |
|---|---|
| Inlined bytecode | Flattened conversation |
| Deoptimized frames | Reconstructed causality |
| Breakpoint trigger | "How did we get here?" |
| Stack trace | Causal chain from evidence |
The stack isn't explicitly maintained, but it's recoverable.
When you ask for history, the LLM examines:
evidence_sources:
- session_log: "Append-only narrative trail"
- room_state: "Accumulated changes"
- character_location: "Current position"
- file_timestamps: "Order of modifications"
- chat_context: "Recent decisions"
And synthesizes a virtual stack trace:
Deduced navigation:
1. lobby (start)
2. workshop (examining blueprints)
3. storage (found locked chest)
4. workshop (returned for key) ← BACK
5. storage (unlocked chest)
6. archive (following map) ← current
This is introspection without instrumentation — the same insight that made Self's debugger magical.
RETURN-STACK — Navigation history as data
BACK / FORWARD — Stack manipulation
BOOKMARK / GOTO — Saved positions
FORK — Parallel exploration
HYPERCARD-HIERARCHY — The room/card model
See: PROTOCOLS.yml