agentleFS
Sign inStart free
kununukununu/agent-bridge/skills/bridge-review/SKILL.md

bridge-review

Skill18 starsChanged 4 days agoMITView on GitHub

A peer agent reviews the changes via agent-bridge, then verified findings get reported to you and the easy ones fixed right away. Name the peer after the command, e.g. /bridge-review gemini

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If this skill has a references/<peer>.md, read it.

    line 16
  2. Very specific:

    Call the Skill tool with "agent-bridge" and delegate to the peer.

    line 21
  3. Distinctive:

    Ask: code quality, adherence to both layers of standards, best practices, the simplest code that reaches the goal, efficiency & performance.

    line 30
  4. Distinctive:

    Never act on a finding you have not checked against the code, or verified some other way (e.g.

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

bridge-review

A peer agent reviews the work, you decide what is real.

1. Pick the peer

The invocation names the peer: /bridge-review gemini, /bridge-review codex, /bridge-review claude. With no peer named, never make assumptions, ask the human which one to use.

If this skill has a references/<peer>.md, read it. It records that peer's quirks. No file means no quirks. gemini is bridge peer agy.

2. Send the review

Call the Skill tool with "agent-bridge" and delegate to the peer.

The brief carries the context the peer cannot see:

  • Goal. What this change is for, so it can judge whether the code is the simplest way there.
  • Gotchas. The things you discovered during implementation that the peer should be aware of. If there are none, just skip this section.
  • Scope. Which files or which diff to review, by path or commit range.
  • Standards, both layers: the coding-standards skill, and this repo's own conventions in AGENTS.md, CLAUDE.md, local project skills and any standards docs. Where the two disagree, the repo wins.
  • Ask: code quality, adherence to both layers of standards, best practices, the simplest code that reaches the goal, efficiency & performance.
  • The output shape: for each finding, file:line, what breaks, and why it matters. Ranked, worst first.
  • Review only. It reports findings and leaves the working tree as it found it.

3. Verify every finding

Never act on a finding you have not checked against the code, or verified some other way (e.g. look up current documentation). How you check depends on the finding: read the file, run the test, try the input, write and run temp script. A finding is real once you can name what breaks or what will break. If you cannot name it, it is noise.

4. Fix or ask

Fix it yourself when the change is small and obvious:

  • Cleanups that leave behavior identical: a standards violation, a code smell, the same logic written more simply.
  • A real bug whose fix is clear and local, however serious it is.

Anything else goes in the summary instead of the diff: a fix that needs huge restructuring, or a finding you are not sure about. Say what you would do and let the human decide.

Then report every finding, what you fixed, and what you left.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free