Athena Graphs
Orchestrate complex work as explicit agent graphs using the Athena Graphs MCP tools. Use when the user explicitly asks for Athena Graphs, asks to graph/orchestrate a task, wants parallel specialized agents, needs branching or review/retry paths, requests human approval checkpoints, or has a multi-stage task whose control flow should be inspectable and durable.
Dynamic Resources
Example skill loaded from resources_discover
Pptx
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
Docx
Corporate Word document generation and editing for .docx files. Use when Claude needs to create professional Word documents from structured input, preserve document templates, or produce styled report outputs.
Orchestrate Specialists
Coordinate software delivery by keeping Claude Code as lead and delegating backend work to Codex, design and frontend work to Kimi, and domain-neutral tooling or mechanical maintenance to Grok Build through the frontier-orchestrator MCP server. Use for feature implementation, refactors, reviews, bug fixes, migrations, or planning whenever specialist delegation would improve a task.
Athena Loops
Backend-agnostic AI agent orchestration loop in Python — the orchestrator→worker→reviewer pattern as a deterministic harness. Drive any LLM backend (Claude, Codex, opencode, aider); ships as an MCP server + CLI.
Frontier Orchestrator
Multi-agent orchestration for Claude Code: MCP server + skill that keeps Claude as lead engineer while delegating backend work to OpenAI Codex and frontend/design work to Kimi
Xlsx
Corporate workbook generation, spreadsheet editing, and formula recalculation for .xlsx files. Use when Claude needs to create professional Excel workbooks from structured input, preserve workbook templates, or recalculate formulas with LibreOffice.
Grok
Offload heavy-duty implementation work to a Grok build agent as a background worker, routing each task to the appropriate available Grok model, while Claude stays the orchestrator and reviewer. Use when the user types /grok, asks to delegate/offload/route work to Grok or xAI, or when a task is a large mechanical lift—big refactors, bulk migrations, wide test fixes, boilerplate-heavy features—that…
Auto Reasoning
Use when the user wants automatic task-difficulty routing for reasoning effort only, asks to run or configure the auto-reasoning harness, wants Codex/OpenAI calls to keep the model fixed while varying reasoning depth, or asks for an auditable effort-selection workflow.