OneStream XF Domain Intelligence Skill

A modular skill package that helps AI agents answer OneStream XF questions with real domain judgement — disambiguating overloaded terminology, preserving compound concepts, and respecting architectural boundaries.

Anoop Sharma

12 May 2026 — 1 min read

GitHub: anoop22/onestreamxf-skill

A modular skill package that helps AI agents answer OneStream XF questions from official reference documents with better domain judgement. Drop it into Claude Code, Claude Projects, or any agent SDK and the agent stops drifting between "Cube" and "Cube View" — or splitting compound concepts that should travel together.

What it solves

Without the skill, an agent asked about "Cube View performance" tends to wander into generic Cube documentation. With it, the agent stays scoped to Cube Views and pulls in Member Filters, Parameters, POV, and suppression when relevant — because the skill encodes the conceptual rules a OneStream practitioner already knows.

Key capabilities

Prevents concept confusion — 45+ compound terms that shouldn't split (Cube View, Data Unit, Workflow Profile, etc.)
Disambiguates overloaded terminology — View, Profile, Rule, Consolidation, and friends
Respects architectural boundaries — 7 layers with interaction rules
Includes prerequisites automatically — 6-tier knowledge hierarchy
Intelligent retrieval rules — 55+ inclusion/exclusion/disambiguation rules

Install for Claude Code

git clone https://github.com/anoop22/onestreamxf-skill.git \
  ~/.claude/skills/onestreamxf

That's the entire setup. The SKILL.md frontmatter tells Claude Code when to surface the skill — no config edits, no plugin manifest. Invoke explicitly with /onestreamxf or let the agent pick it up automatically for any OneStream question.

Also works as an instruction bundle for Claude Projects or any agent that can read a skill folder and consult OneStream reference docs.

Vikram AI — The Evolved Form of Vaman

Trivikrama, the evolved form of Vaman AI. The codebase Vaman is growing into — an autonomous, self-learning domain expert agent built on the same OpenClaw and pi-mono foundation.

Voice App QA Recorder — Catching Bugs Automated Tests Miss

A reusable local QA harness for voice-first and multimodal apps. Records a real browser session as synchronized screen video, microphone audio, system audio, console logs, app events, and stills — then generates a review file.

OneStream XF Skill Chat — A Browser-Only Demo

A static GitHub Pages demo that answers OneStream XF questions with the public onestreamxf-skill loaded as the agent's working skill — running entirely in the browser, no backend.

Agentic RAG Lab — A Minimal LangGraph Demo

A single-file version of LangGraph's Agentic RAG tutorial. Useful as a starting point for reading the agentic-RAG pattern end-to-end without wading through a multi-module example.