BotShelf Vampire BOTSHELF VAMPIRE Register

EXPLORE · SAME JOB, BY TOOL

Writing Draft: 7 versions, one per tool

The same job, written separately for CrewAI, LangGraph, LM Studio, MCP, n8n, Ollama, Open WebUI. Each version is its own text; what you get is text to copy into that tool, not something BSV installs or runs for you. Pick the tool you already use and open its page: the full text is there, with Copy and a file to download. No sign-up.

ToolDescription on the item pageStatusRaw
CrewAIDraft a clear first pass from notes — then stop for human edit. No fake claims or invented metrics. (CrewAI multi-agent Python sketch for one job.)Untestedfile
LangGraphDraft a clear first pass from notes — then stop for human edit. No fake claims or invented metrics. (LangGraph stateful graph with a human checkpoint.)Untestedfile
LM StudioDraft a clear first pass from notes — then stop for human edit. No fake claims or invented metrics. (LM Studio system prompt + local server notes.)Untestedfile
MCPDraft a clear first pass from notes — then stop for human edit. No fake claims or invented metrics. (MCP-oriented tool + prompt recipe (read-only first).)Untestedfile
n8nDraft a clear first pass from notes — then stop for human edit. No fake claims or invented metrics. (n8n workflow recipe (Manual Trigger → LLM → output).)Untestedfile
OllamaDraft a clear first pass from notes — then stop for human edit. No fake claims or invented metrics. (Ollama Modelfile + chat prompt for offline runs.)Check recordedfile
Open WebUIDraft a clear first pass from notes — then stop for human edit. No fake claims or invented metrics. (Open WebUI system prompt / custom agent notes.)Untestedfile

1 of these 7 versions have a recorded check; the rest are marked untested. Status comes from each item page. BSV does not run any of them for you.

Search this job in Explore How to run How to fork All jobs

Used one of these versions? Say how it went, or ask, in Community.