How do I install the Review Agent Orchestration skill?

Run npx skillmds@latest add diagrid-labs/review-agent-orchestration in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Review Agent Orchestration safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Review Agent Orchestration?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Review Agent Orchestration free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Review Agent Orchestration?

diagrid-labs (@diagrid-labs) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Review Agent Orchestration by diagrid-labs

Name: Review Agent Orchestration
Rating: 4.666666666666667 (3 reviews)
Author: diagrid-labs

Review Agent Orchestration

This skill reviews multi-agent orchestration for pub/sub topic conventions, loop safety, and handoff correctness. Use this skill when the user asks to "review agent orchestration", "check multi-agent handoffs", "audit agent pub/sub", or similar.

diagrid-labs Updated Sep 10, 2026

File contents

Review Agents — Orchestration

Overview

Scans multi-agent projects (coordinator + specialists) for pub/sub topic naming conventions, loop safety (max_iterations), agent-registry wiring, port collisions in dapr.yaml, and cross-agent shared-state hazards. Read-only. Single-agent projects receive zero findings.

Execution Order

You MUST follow these phases in strict order.

Resolve scope — Read ../shared/review-scope-prompt.md and follow it to set scope_root.
Detect target — Read ../shared/review-detect-target-agent.md. If topology == single-agent, emit No issues found. and stop.
Load checklist — Based on language, read exactly one of:
- python → ../shared/review-agent-orchestration-python.md
- dotnet → ../shared/review-agent-orchestration-dotnet.md
Scan — Apply every rule. Port-collision rules require parsing dapr.yaml; topic-routing rules require grepping for publish_topic= / subscribe_topic= / DaprClient.PublishEventAsync(.
Report — Format findings using ../shared/review-report-format.md.
Show final message — Emit the report from step 5 with a ## Next steps block.

Prerequisites

Read access to the project directory.

Allowed tools

Read, Grep, Glob only.

Rules

Python rules — DAG-ORCH-001 … DAG-ORCH-009
.NET rules — shared subset of DAG-ORCH-* (see the rule-id map in the Python file)

Show final message

The last thing you emit MUST be the report from step 5. ## Next steps should suggest:

Run review-agent-tools and review-agent-memory next if not yet run.
Run review-agent-observability for native dapr-agents projects.
Re-run this skill after fixing critical findings.

Do not add any text after the report.

---name: review-agent-orchestrationdescription: This skill reviews multi-agent orchestration for pub/sub topic conventions, loop safety, and handoff correctness. Use this skill when the user asks to "review agent orchestration", "check multi-agent handoffs", "audit agent pub/sub", or similar.---# Review Agents — Orchestration## OverviewScans multi-agent projects (coordinator + specialists) for pub/sub topic naming conventions, loop safety (`max_iterations`), agent-registry wiring, port collisions in `dapr.yaml`, and cross-agent shared-state hazards. Read-only. Single-agent projects receive zero findings.## Execution OrderYou MUST follow these phases in strict order.1. **Resolve scope** — Read [`../shared/review-scope-prompt.md`](../shared/review-scope-prompt.md) and follow it to set `scope_root`.2. **Detect target** — Read [`../shared/review-detect-target-agent.md`](../shared/review-detect-target-agent.md). If `topology == single-agent`, emit `No issues found.` and stop.3. **Load checklist** — Based on `language`, read exactly one of: - `python` → [`../shared/review-agent-orchestration-python.md`](../shared/review-agent-orchestration-python.md) - `dotnet` → [`../shared/review-agent-orchestration-dotnet.md`](../shared/review-agent-orchestration-dotnet.md)4. **Scan** — Apply every rule. Port-collision rules require parsing `dapr.yaml`; topic-routing rules require grepping for `publish_topic=` / `subscribe_topic=` / `DaprClient.PublishEventAsync(`.5. **Report** — Format findings using [`../shared/review-report-format.md`](../shared/review-report-format.md).6. **Show final message** — Emit the report from step 5 with a `## Next steps` block.## Prerequisites- Read access to the project directory.## Allowed tools`Read`, `Grep`, `Glob` only.## Rules- [Python rules](../shared/review-agent-orchestration-python.md) — `DAG-ORCH-001` … `DAG-ORCH-009`- [.NET rules](../shared/review-agent-orchestration-dotnet.md) — shared subset of `DAG-ORCH-*` (see the rule-id map in the Python file)## Show final messageThe last thing you emit MUST be the report from step 5. `## Next steps` should suggest:- Run `review-agent-tools` and `review-agent-memory` next if not yet run.- Run `review-agent-observability` for native `dapr-agents` projects.- Re-run this skill after fixing critical findings.Do not add any text after the report.

Frequently asked questions