Cross Review Project
技能 已验证 活跃Conduct a structured cross-project code review between two Claude Code instances via the cross-review-mcp broker. Each agent reads its own codebase, reviews the peer's code, and engages in evidence-backed dialogue — with QSG scaling laws enforcing review quality through minimum bandwidth constraints and phase-gated progression.
To enable deep, comparative code reviews between distinct projects by leveraging AI agents and a structured broker protocol for higher quality and actionable insights.
功能
- Structured cross-project code review
- Multi-agent dialogue via MCP broker
- QSG scaling laws for review quality
- Phase-gated progression
- Evidence-backed dialogue and verdicts
使用场景
- Comparing architectural concerns between two projects.
- Obtaining independent code reviews that go beyond single-reviewer perspectives.
- Facilitating cross-pollination of patterns and practices between codebases.
- Generating structured, evidence-backed findings for code improvement.
非目标
- Performing code review by a single agent.
- Replacing team code review processes entirely.
- Providing automated code refactoring or bug fixing.
- Reviewing projects that lack common architectural concerns or share no common patterns.
工作流
- Verify Prerequisites (broker status, protocol resource)
- Register agents with the broker
- Compose and send structured briefings to peers
- Wait for peer briefing, review code, produce and send structured findings (≥5)
- Wait for peer findings, respond with accept/reject/discuss verdicts and evidence
- Compile synthesis artifact, signal completion, and deregister
先决条件
- Two project paths accessible to two Claude Code instances
- `cross-review-mcp` broker running and configured as an MCP server in both instances
- Optional: Focus areas — specific directories, patterns, or concerns to prioritize
- Optional: Agent IDs — identifiers for each instance (default: project directory name)
安装
/plugin install agent-almanac@pjt222-agent-almanac质量评分
已验证类似扩展
Test A2a Interop
100Test A2A interoperability between agents by validating Agent Card conformance, exercising all task lifecycle states, and verifying streaming and error handling. Use when verifying a new A2A server implementation before deployment, validating interoperability between two or more A2A agents, running conformance tests in CI/CD for A2A services, debugging failures in multi-agent A2A workflows, or certifying that an agent meets A2A protocol requirements for a registry.
Design A2A Agent Card
100Design an A2A Agent Card (.well-known/agent.json) manifest describing agent capabilities, skills, authentication requirements, and supported content types. Use when building an agent that must be discoverable by other A2A-compliant agents, exposing capabilities for multi-agent orchestration, migrating an existing agent to the A2A protocol, defining the public contract for an agent before implementation, or integrating with agent registries that consume Agent Cards.
Review Pull Request
100Review a pull request end-to-end using GitHub CLI. Covers diff analysis, commit history review, CI/CD check verification, severity-leveled feedback (blocking/suggestion/nit/praise), and gh pr review submission. Use when a pull request is assigned for review, performing a self-review before requesting others' input, conducting a second review after feedback is addressed, or auditing a merged PR for post-merge quality assessment.
Oh My Claudecode
100Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly
ClawSweeper Skill
100Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, commit-review reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted ClawSweeper-reviewed autofix/automerge, GitHub Actions monitoring, permissions, gates, and manual backfills.
Claude Handoff
100运行 /handoff 以捕获会话数据，然后编写一个引用该数据的分阶段实施计划。创建用于跟踪的 beads。