Diagnose the ResearchForge environment
researchforge doctor --json
Each entry has name, ok, required, detail, and an optional hint.
- All required checks pass → say the environment is ready and continue.
- A required check fails → explain the failure in plain language, show the
hint, and stop: later commands will refuse to run. Do not try to work around a failed required check. - An optional check fails (e.g. Docker) → note the limitation: experiments
fall back to
.venvmode, which is dependency isolation, not a security sandbox — only trusted repositories should be run there.
If skills seem out of date or missing, researchforge claude status --json
reports the installed/modified/missing state of each skill and
researchforge claude install refreshes unmodified ones.
Rules
- The Python engine is the boundary: never work around a validation error, a protected path, or an approval gate — fix the artifact or ask the user.
- Approvals belong to the user: never pass
--yesor type a confirmation unless the user explicitly approved that step in this conversation. - Ground every summary in stored data: quote only numbers returned by
--jsonoutput or files under.researchforge/— never invent metrics.