wh:handoff
25Command Claude Code
Use when Wheeler research tasks should be queued for background execution by Wheeler workers.
Command Claude Code
Use when Wheeler research tasks should be queued for background execution by Wheeler workers.
Command Claude Code
Bootstrap knowledge graph from existing data files.
Command Claude Code
Initialize a new Wheeler project (fresh or restored from a backup archive).
Command Claude Code
Use when the user wants to discover or fit a closed-form equation from a dataset via LLM-SR and ingest the result into the Wheeler knowledge graph.
Command Claude Code
Use when the user wants to test whether an LLM-SR discovered equation's FORM generalizes to a recording the search never scored, and ingest both transfer numbers into the Wheeler knowledge graph.
Command Claude Code
Use when the user wants to capture a research insight as a Wheeler knowledge-graph note.
Command Claude Code
Use when the user wants interactive live analysis co-work with Wheeler, scientist driving.
Command Claude Code
Use when the user is stopping a Wheeler investigation and needs to save state in STATE.md for later.
Command Claude Code
Use when the user wants to structure a Wheeler research investigation in .plans/ from a sharpened question.
Command Claude Code
Background task execution (used by wh queue headless runner).
Command Claude Code
Use when returning to a Wheeler session after background Wheeler workers have completed, to review results.
Command Claude Code
Use when the user wants a work-log summary of recent Wheeler research activity over a time period.
Command Claude Code
Verify, fresh-restore, or merge a Wheeler backup archive into a project. Supports --verify, --fresh, and --merge modes.
Command Claude Code
Use when starting a new session and restoring Wheeler context from STATE.md or .plans/.continue-here.md.
Command Claude Code
Route a research task to the right registered external service (Asta literature, LLM-SR equation discovery, or any enabled service), interview the scientist for that service's inputs, show the assembled request, and dispatch it. Use for "use a service", "invoke X", "which tool fits this", or naming a service by id.
Command Claude Code
Start a Wheeler research session or pick the right /wh: command for your task.
Command Claude Code
Use when the user asks about Wheeler investigation progress in .plans/ or what research task to tackle next.
Command Claude Code
Use when the user wants to triage GitHub issues against Wheeler research plans in .plans/.
Command Claude Code
Check for Wheeler updates and upgrade if available.
Command Claude Code
Use when the user wants to draft scientific text with Wheeler citation enforcement from knowledge-graph findings.
Hook Claude Code
Runs after a tool call finishes for ^(Read, Write)$, ^(Write and Edit)$ tool calls, running python3 -m wheeler.hooks.track_file_access (2 commands). From maxwellsdm1867/wheeler.
Hook Claude Code
Runs before the agent uses a tool for mcp__wheeler_mutations__(ensure_artifact, add_plan, add_document, add_script, add_dataset and update_node) tool calls, running python3 -m wheeler.hooks.read_before_mutate. From maxwellsdm1867/wheeler.
Settings file Claude Code
Agent settings declaring 2 hook events (PostToolUse, PreToolUse).
Skill Claude CodeCodex
Render a self-contained, scientist-friendly HTML research brief (a "game plan" decision aid) for a Wheeler investigation plan or execution. It leads with the question and sub-questions, then figure mockups (wireframe or synthetic-data PNG) showing what will be plotted and how competing hypotheses would differ, then…