ai-research-arm: Command for Claude Code

Generative Research

User-supplied topic: $ARGUMENTS

If the topic above is empty or just whitespace, ask the user for a topic and stop until they answer.

Step 1 — choose execution mode (always ask)

Use AskUserQuestion to ask the user how they want this run executed. DO NOT skip this prompt — the two modes have very different cost, latency, and depth profiles. Present these two options:

• Run locally (in this chat) — ~5–15 min. Deep pipeline runs in the current session using sub-agents (Task tool), evidence packets, and a verifier pass. Article lands as a local commit in research/generative/ (not pushed). Recommended for topics you want to iterate on, or when you want to read the result immediately.
• Route to GitHub workflow — ~20–45 min on the self-hosted runner. Dispatches generative-research.yml on the registry's default backend (the generative-research-default lane in data/agent-backends.json) unless the user names one. Your chat is freed instantly. The runner produces a longer article (4500–7000 words target, ≥20 cited references) and publishes it to main. Recommended for substantive topics where you want maximum depth without spending in-chat time.

After the user picks:

• Route → follow PATH A below.
• Run locally → follow PATH B below.

---

PATH A — Route to the GitHub workflow

Dispatch the workflow with the user's topic. The backend comes from data/agent-backends.json, never from memory: omit -f backend and the workflow runs the generative-research-default lane. Pass -f backend=<selector> only when the user named one, and only if it matches a selector, backend key or alias in the registry; otherwise show the list and ask.

jq -r '.lanes["generative-research-default"].backend' data/agent-backends.json
# Selectable backends: selector, backend key, display name, aliases
jq -r '.backends | to_entries[] | select(.value.generative.exposed == true)
  | [.value.generative.selector, .key, .value.display_name,
     (((.value.aliases // []) + (.value.generative.aliases // [])) | join(","))] | @tsv' \
  data/agent-backends.json

DISPATCHED_AT="$(date -u +%Y-%m-%dT%H:%M:%SZ)"; echo "$DISPATCHED_AT"
gh workflow run generative-research.yml \
  -f topic='<the exact topic the user gave>'