From Flow
Run an OPTIONAL, advisory cross-vendor code review of the current branch's diff vs main using a configurable second-opinion backend (Azure Foundry next-gen, GitHub Models, or Copilot CLI - all OAuth, all keyless). Explicit-only; run only when invoked via /cross-review or when the user explicitly asks for a cross-vendor review, never autonomously.
How this skill is triggered — by the user, by Claude, or both
Slash command
/flow:cross-reviewThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are running a cross-vendor code review on the current branch's diff vs `main`, using the reviewer profile the user named (or the default from `profiles.json`). This is a **second opinion** from a model in a different vendor lineage. It is **advisory only**: surface findings, do not apply changes.
You are running a cross-vendor code review on the current branch's diff vs main, using the reviewer profile the user named (or the default from profiles.json). This is a second opinion from a model in a different vendor lineage. It is advisory only: surface findings, do not apply changes.
!bash ${CLAUDE_SKILL_DIR}/scripts/review.sh "$1" 2>&1
The script printed the findings above and saved a markdown copy under flow/reviews/. In your reply:
Common causes (the printed error points at one of these):
profiles.json missing: copy .claude/skills/cross-review/profiles.example.json to profiles.json and edit endpoints/models.az login (Foundry), gh auth login (GitHub Models), copilot auth login (Copilot CLI).az, gh, copilot, jq, or curl missing.main: the branch has no changes to review.Tell the user the specific error from the script output and the fix; full setup is in docs/cross-vendor-review.md.
npx claudepluginhub corticalstack/flow --plugin flowGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.