Cross review

Skill corticalstack/flow/.claude/skills/cross-review

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.From its SKILL.md

Install

npx -y skills add corticalstack/flow --skill cross-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
runs commandsInstructs the agent to run 1 command, including `bash ${CLAUDE_SKILL_DIR}/scripts/review.sh "$1" 2>&1`.

SKILL.md

1.9 KB, 367 tokens by cl100k_base, as published. Nobody here has run it

Cross-vendor review

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.

Run the review

!bash ${CLAUDE_SKILL_DIR}/scripts/review.sh "$1" 2>&1

Present the result

The script printed the findings above and saved a markdown copy under flow/reviews/. In your reply:

Surface the findings clearly to the user, with the saved file path so they can re-read it.
Do NOT modify any code based on what the reviewer said. The reviewer is a second opinion, not an instruction.
If the user asks you to act on a specific finding, treat it as a separate task and apply your own judgement; the reviewer may be wrong.

If the script errored

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.
Authentication: az login (Foundry), gh auth login (GitHub Models), copilot auth login (Copilot CLI).
Tool not installed: az, gh, copilot, jq, or curl missing.
No diff vs 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.

What ships with it: 2 files

11.6 KB alongside SKILL.md, 1 of them executable

scripts/

review.shruns9.9 KB

profiles.example.json1.8 KB

Gives 0 of the 12 instructions most review quality skills give in 367 tokens

Counted across 1,273 of the 2,403 authors here whose files we hold, read 2026-09-06

Ask one question at a timein 63 of 1273, across 62 files
Provide a recommended answer for each questionin 47 of 1273, across 45 files
Rank findings by severityin 44 of 1273
Use parameterized queries for database accessin 38 of 1273, across 20 files
Validate all user input with schemasin 33 of 1273, across 15 files
Store secrets in environment variablesin 32 of 1273, across 14 files
Explore the codebase to answer questionsin 31 of 1273, across 29 files
Store tokens in httpOnly cookiesin 30 of 1273, across 12 files
Implement rate limiting on API endpointsin 30 of 1273, across 12 files
Sanitize user-provided HTMLin 29 of 1273, across 11 files
Return generic error messages to usersin 28 of 1273, across 10 files
Cite file and line for every findingin 28 of 1273, across 25 files

Said here and by no other author read

Surface findings clearly to the user
Provide saved file path to the user
Report script errors and suggested fixes

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.