agentleFS
aradmanamnaoonaradmanamnaoon/vibe-coding-skills/skills/agent-reliability/multi-agent-integration-reviewer/SKILL.md

multi-agent-integration-reviewer

Skill0 starsChanged 19 days agoMITView on GitHub

Integrate parallel agent changes by detecting file overlap, incompatible assumptions, duplicated implementations, semantic conflicts, and missing combined tests. Use before merging worker branches or worktrees.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Ensure independently correct patches still form one coherent system.

    line 8
  2. Distinctive:

    Only one patch exists or parallel changes are provably independent generated artifacts.

    line 16
  3. Distinctive:

    Read applicable repository instructions before edits.

    line 20
  4. Distinctive:

    Verify all branches share the intended base and capture each worker's claimed scope/evidence.

    line 33
  5. Very specific:

    Run each worker's focused checks plus combined integration/build/E2E tests that cross their boundaries.

    line 38
  6. Distinctive:

    Do not merge merely because Git reports no textual conflicts.

    line 47
  7. Distinctive:

    No unresolved overlapping responsibility or schema/API mismatch remains.

    line 51
  8. Distinctive:

    If a worker's validation cannot be reproduced, mark that patch unverified and inspect/test it before relying on the claim.

    line 64

≈ “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

Purpose

Ensure independently correct patches still form one coherent system.

When to activate

Two or more agents/branches/worktrees changed related parts of a project.

When not to activate

Only one patch exists or parallel changes are provably independent generated artifacts.

Preconditions

  • Read applicable repository instructions before edits.
  • Preserve unrelated working-tree changes and establish a baseline when the workflow can modify code.
  • Identify which tools and environments are actually available; do not claim unavailable checks ran.

Required inputs

  • Base commit
  • Agent branches/diffs
  • Assigned scopes and requirements
  • Validation from each worker

Workflow

  1. Verify all branches share the intended base and capture each worker's claimed scope/evidence.
  2. Compare changed-file overlap and also dependency/API/schema overlap even when files differ.
  3. Detect duplicated solutions, inconsistent names/types/config keys, conflicting migrations, version bumps, generated files, and tests that assume incompatible behavior.
  4. Choose one canonical implementation per responsibility and integrate in dependency order.
  5. Resolve semantic conflicts by the authoritative requirement and repository architecture, not by keeping both versions.
  6. Run each worker's focused checks plus combined integration/build/E2E tests that cross their boundaries.
  7. Review the final diff for lost changes and delete obsolete duplicate paths.

Relevant tools

Git branches/worktrees/diff, dependency search, combined test suite.

Safety restrictions

Do not merge merely because Git reports no textual conflicts; semantic conflicts require review.

Validation

  • No unresolved overlapping responsibility or schema/API mismatch remains.
  • Combined tests pass after integration, not only branch-local tests.
  • The final diff can trace each retained change to a requirement/worker rationale.

Expected output

  • Agent change matrix
  • Conflict/duplication findings
  • Integration decisions
  • Combined validation

Failure handling

If a worker's validation cannot be reproduced, mark that patch unverified and inspect/test it before relying on the claim.

Completion criteria

The skill is complete only when every applicable validation item above has observed evidence or is explicitly marked not executed with the concrete blocker. Do not replace missing evidence with confidence language.

Research mapping

This skill was selected from research problems: P049. See research/vibe-coding-problems.md and research/problem-evidence.csv in the Vibe Coding Skills repository.

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.