mcpField
E
error-debugging-multi-agent-review

error-debugging-multi-agent-review

github.com/sickn33Testing & quality48.7k325 installsUpdated today
Repository

About error-debugging-multi-agent-review

A skill that coordinates a bounded code review across relevant perspectives, including correctness, authorization, and performance. It defines an evidence-focused process for reviewing a specified diff, whether authorized reviewers work independently or perspectives are handled sequentially.

Key features

  1. 01Review a defined diff or subsystem
  2. 02Select change-relevant review perspectives
  3. 03Record findings with evidence and locations
  4. 04Reproduce and deduplicate findings
  5. 05Separate demonstrated failures from hypotheses

Use cases

  1. 01Reviewing tenant-scoped cache changes
  2. 02Checking authorization effects in a code diff
  3. 03Assessing performance and correctness in a subsystem

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/sickn33/agentic-awesome-skills --skill error-debugging-multi-agent-review

After installing, type/error-debugging-multi-agent-reviewin Claude Code to confirm it loaded.

Details

From the project README

Compatibility and maintenance

Primary editorial path for this compatibility group. The full instructions and support files remain local so existing installations continue to work offline. This is one shared procedure, not an additional capability. Preserve the callable ID when an existing manifest or client configuration uses it. Modified in AAS on 2026-09-05; original metadata and license notices are retained.

Coordinate a bounded code review

When to Use

Review a defined diff or subsystem from several relevant perspectives, such as correctness, authorization and performance. The skill describes a review procedure; it does not install an orchestration engine or prove compliance.

Inputs and execution scope

Pin repository/base/head, the changed paths, intended behavior and available tests. Use independent agents only if the user authorizes delegation and the host supports it. Otherwise conduct the perspectives sequentially. Do not spawn agents merely because this callable ID contains “multi-agent”. Read-only review is the default; fixes, external posts and deployment stay within the user's actual task authority.

Review process

  1. Read the complete diff and the directly affected call paths and tests.
  2. Choose only perspectives relevant to the change. Give each authorized reviewer a bounded question, owned paths, time/effort limit and expected evidence format.
  3. Record findings with exact locations, trigger, consequence and reproduction. Keep hypotheses separate from demonstrated failures; do not invent confidence scores.
  4. Reproduce important findings centrally. Deduplicate by root cause, not wording.
  5. Resolve disagreement through code or tests. Weighted votes and multiple agents repeating a claim are not evidence of correctness.
  6. Return blockers first, then material improvements and untested areas. Preserve the original failing result; a rerun does not erase it.

Example

For a tenant-scoped cache change, review key construction, authorization context and invalidation. Reproduce two tenants requesting the same prompt and different prompt versions within one tenant. Expected result: a finding only if an actual cross-scope hit or stale result can occur, with the smallest case showing it. A general style opinion must not be presented as a data-exposure defect.

Limitations

No agent-routing code, compliance validator or quality-score calculator is bundled. Parallel review adds cost and can duplicate blind spots. This procedure cannot prove whole-repository safety from a diff, nor authorize production load tests or messages.

Comments

Markdown supported