langalpha-doc
/langalpha-doc
How the platform under you works: the computer and its workspaces, files and what survives a restart, conversation transcripts, saved tool results, memory, chat apps, and adding skills, MCP servers, brokerages or plugins. Read it when the user points back at an earlier conversation, when something is missing or behaves unexpectedly, before adding any of those, and when the user asks how the platform works and you don't know.
- Author
- ginlix-ai ↗
- Repository
- langalpha ↗
- Licence
- Apache-2.0
- Last repository change
- 27.10.2026
Assessment and security
- Files in this package
- 8
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 27.10.2026, without references to retired models or APIs.
Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.
What it does and when to use it
How the platform under you works: the computer and its workspaces, files and what survives a restart, conversation transcripts, saved tool results, memory, chat apps, and adding skills, MCP servers, brokerages or plugins. Read it when the user points back at an earlier conversation, when something is missing or behaves unexpectedly, before adding any of those, and when the user asks how the platform works and you don't know.
Original author description
How the platform under you works: the computer and its workspaces, files and what survives a restart, conversation transcripts, saved tool results, memory, chat apps, and adding skills, MCP servers, brokerages or plugins. Read it when the user points back at an earlier conversation, when something is missing or behaves unexpectedly, before adding any of those, and when the user asks how the platform works and you don't know.
How it works
- Reference files
- Traps
- Facts
SKILL.md preview
--- name: langalpha-doc description: "How the platform under you works: the computer and its workspaces, files and what survives a restart, conversation transcripts, saved tool results, memory, chat apps, and adding skills, MCP servers, brokerages or plugins. Read it when the user points back at an earlier conversation, when something is missing or behaves unexpectedly, before adding any of those, and when the user asks how the platform works and you don't know." --- # How LangAlpha Works You run on a **computer**: one sandbox machine that belongs to the user. Each of the user's **workspaces** on it is a folder, side by side at the computer root; yours is your working directory, so the root is `..`. A **thread** is one conversation in one workspace, and a **turn** is one user message and everything done to answer it. Workspaces on one computer share its disk, OS user, CPUs, `/tmp` and installed packages, and can read each other's folders. ## Reference files - The user points back at an earlier conversation or at work done in another thread or workspace; a compaction summary; a background task's steps; a tool result saved to a file: `.agents/skills/langalpha-doc/references/history.md`. - Where things live, how a path resolves, why Grep or Glob missed a file, memory and memo storage, what the user sees in the file panel: `.agents/skills/langalpha-doc/references/files.md`. - Processes, output and timeouts, CPUs and disk, installed packages, what survives a stop or a rebuild, data-server tools from code, secrets: `.agents/skills/langalpha-doc/references/computer.md`. - Installing, writing or changing a skill, here or for every workspace: `.agents/skills/langalpha-doc/references/skills.md`. - The user wants a new data source, MCP server, brokerage connection or plugin, a server needs a key, or a server you expected is missing: `.agents/skills/langalpha-doc/references/plugins.md`. - Talking with the user in a chat app, or sending a message or file to Slack, Discord, Telegram, iMessage or Feishu: `.agents/skills/langalpha-doc/references/chat.md`. ## Traps - Every ExecuteCode and Bash call is a fresh process started in your workspace folder: Python variables, `cd` and `export` do not carry to the next call. - When ExecuteCode fails you get its stderr, not what it printed before the crash. - The file tools read a leading slash as your workspace folder; `open()` and Bash read it as the real filesystem root. Glob, Grep and Write print workspace files with a leading slash (`/task/file.md`), so drop it before pasting a path into code. - Grep skips hidden and git-ignored files and folders, `.agents/` included (`.agents/memory/` aside), unless `path` points inside one. - Only workspace folders are backed up, and not their virtual environments. Installed packages, the computer root and `/tmp` survive a stop but not a rebuild of the computer. - A turn is written to its thread's transcript when it completes, so do not look there for the turn in progress. - Memory, memos, the profile, workflows and automations are held by the server. Bash and code reach them only through the file mount, where a save the server refuses shows under NOT SAVED in the result, not in the exit status. Without the mount, a command naming a memory, memo or automations path is refused before it runs. The chat-app settings in `.agents/user/channels/` are file tools only: a command naming them is always refused. - In a markdown file, an image path resolves from the workspace folder, not from the file's own folder. - `plt.show()` output goes nowhere. Save charts with `savefig` into `<task>/charts/` and link the file. ## Facts How the platform behaves, for answering the user. Your work doesn't need these pages, so don't read them ahead of time. When the user asks how something on the platform works and you don't know, read the matching page and answer from it instead of guessing. - Channels (Slack, Discord, Telegram, iMessage, Feishu): which conversation or workspace a message the user sends there reaches, why an answer came from another conversation, how `/new`, `/workspace` and replies pick one, and where your own sends land and whether replies to them come back: `.agents/skills/langalpha-doc/facts/channel-routing.md`.
Files in this package (8)
- SKILL.md 4 KB
- facts/channel-routing.md 13 KB
- references/chat.md 5 KB
- references/computer.md 4 KB
- references/files.md 8 KB
- references/history.md 8 KB
- references/plugins.md 10 KB
- references/skills.md 6 KB
Versions
The database has no other skills named langalpha-doc.
Database snapshot: 13.11.2026 · package version a296efc1f5d8 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90migrate-to-antigravity
Move an existing Claude Code setup onto the Antigravity CLI (agy) — user skills, CLAUDE.md, auto-memory, MCP servers, installed plugins, permissions and trusted workspaces. Use when the user says "migrate to Antigravity", "move my Claude Code config to agy", "bring my… - 90claude-platform-reference
Use when you need details about SpawnForge's Claude Code platform setup — hooks, skills inventory, MCP servers, validation tools, or plugin config. Reference for the automation infrastructure. - 90agent-tooling-audit
Use when the user asks which skills, plugins, extensions, MCP servers, hooks, rules or subagents fit a project — "what should I use for this project", "find me useful skills/MCP servers", "is my agent setup right for this", "what am I missing", or when starting work in a new… - 90qveris-langalpha
QVeris-native adaptation of candidate 2, LangAlpha. Use for DCF, earnings analysis, earnings preview, and sector overview workflows that preserve LangAlpha-style schemas while routing all financial data through qveris_finance.* CAP tools. - 100working-with-claude-code
Use when working with Claude Code CLI, plugins, hooks, MCP servers, skills, configuration, or any Claude Code feature - provides comprehensive official documentation for all aspects of Claude Code - 87remove-mcp-and-skills
Find the MCP servers, MCP tools and skills you carry but never use (never built-in tools), show what carrying them costs and what earlier removals have measurably saved, and filter them after one yes. Use when asked what to remove, which MCP servers or skills are unused, or to undo a removal.