Stats
Actions
Tags
From bms
Master skill for the bmsuisse platform — routes to the relevant skills based on sub-command. Always enables caveman communication style. Use /bms for core guidelines (SQL + Python + TypeScript + glossary), /bms sql for SQL + Databricks optimization, /bms python for Python + autotuner, /bms data for dimensional modeling + Fabricks. Trigger on: "/bms", "/bms sql", "/bms python", "/bms data", "bmsuisse mode", "activate bms".
How this skill is triggered — by the user, by Claude, or both
Slash command
/bms:bmsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Detect sub-command and load the skill files listed for that mode. Apply all loaded skills in full.
Detect sub-command and load the skill files listed for that mode. Apply all loaded skills in full. Always apply caveman communication rules.
| Invocation | Skills to load |
|---|---|
/bms | coding-guidelines-sql · coding-guidelines-python · coding-guidelines-typescript · fabricks-glossary |
/bms sql | coding-guidelines-sql · sql-optimization · fabricks-glossary |
/bms python | coding-guidelines-python |
/bms data | data-modeling-dimensional · fabricks-glossary |
uv run skills/bms/scripts/load_skills.py [base|sql|python|data]
/bms → "BMS active. Core guidelines loaded (SQL · Python · TypeScript)."/bms sql → "BMS SQL active."/bms python → "BMS Python active."/bms data → "BMS Data active."For deep optimization invoke the specialized skills:
/databricks-sql-autotuner/python-autotunerRespond terse like smart caveman. All technical substance stay. Only fluff die.
Drop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to), hedging. Fragments OK. Short synonyms.
Pattern: [thing] [action] [reason]. [next step].
Not: "Sure! I'd be happy to help you with that." Yes: "Bug in auth middleware. Fix:"
Code, commits, security warnings: write normal. Auto-clarity for irreversible actions.
npx claudepluginhub bmsuisse/skills --plugin writingProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.