pilot-code-review-pipeline-setup

Deploy an automated code review pipeline with 3 agents. Use this skill when: 1. User wants to set up an automated code review or PR analysis pipeline 2. User is configuring an agent as part of a code review workflow 3. User asks about scanning PRs, reviewing code quality, or reporting review results across agents Do NOT use this skill when: - User wants a single static analysis run (use pilot-task-router instead) - User wants to send a one-off alert (use pilot-alert instead)

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "pilot-code-review-pipeline-setup" with this command: npx skills add vulture-labs/pilot-code-review-pipeline-setup

Code Review Pipeline Setup

Deploy 3 agents that scan PRs, analyze code quality, and report review results.

Roles

RoleHostnameSkillsPurpose
scanner<prefix>-scannerpilot-github-bridge, pilot-task-router, pilot-metricsRuns static analysis and security scans on PRs
reviewer<prefix>-reviewerpilot-event-filter, pilot-alert, pilot-audit-logAnalyzes scan results, suggests improvements
reporter<prefix>-reporterpilot-webhook-bridge, pilot-slack-bridge, pilot-receiptPosts PR comments, sends notifications

Setup Procedure

Step 1: Ask the user which role this agent should play and what prefix to use.

Step 2: Install the skills for the chosen role:

# For scanner:
clawhub install pilot-github-bridge pilot-task-router pilot-metrics

# For reviewer:
clawhub install pilot-event-filter pilot-alert pilot-audit-log

# For reporter:
clawhub install pilot-webhook-bridge pilot-slack-bridge pilot-receipt

Step 3: Set the hostname:

pilotctl --json set-hostname <prefix>-<role>

Step 4: Write the setup manifest:

mkdir -p ~/.pilot/setups
cat > ~/.pilot/setups/code-review-pipeline.json << 'MANIFEST'
{
  "setup": "code-review-pipeline",
  "setup_name": "Code Review Pipeline",
  "role": "<ROLE_ID>",
  "role_name": "<ROLE_NAME>",
  "hostname": "<prefix>-<role>",
  "description": "<ROLE_DESCRIPTION>",
  "skills": { "<skill>": "<contextual description>" },
  "peers": [ { "role": "...", "hostname": "...", "description": "..." } ],
  "data_flows": [ { "direction": "send|receive", "peer": "...", "port": 1002, "topic": "...", "description": "..." } ],
  "handshakes_needed": [ "<peer-hostname>" ]
}
MANIFEST

Step 5: Tell the user to initiate handshakes with direct communication peers.

Manifest Templates Per Role

scanner

{
  "setup": "code-review-pipeline", "setup_name": "Code Review Pipeline",
  "role": "scanner", "role_name": "Code Scanner",
  "hostname": "<prefix>-scanner",
  "description": "Runs static analysis, linting, and security scans on PRs.",
  "skills": {
    "pilot-github-bridge": "Watch for new PRs, fetch diffs and changed files for scanning.",
    "pilot-task-router": "Route scan tasks across analysis tools and collect results.",
    "pilot-metrics": "Track scan counts, finding severity distribution, and scan duration."
  },
  "peers": [
    { "role": "reviewer", "hostname": "<prefix>-reviewer", "description": "Receives scan results for code analysis" },
    { "role": "reporter", "hostname": "<prefix>-reporter", "description": "Final stage — does not communicate directly" }
  ],
  "data_flows": [
    { "direction": "send", "peer": "<prefix>-reviewer", "port": 1002, "topic": "scan-result", "description": "Scan results with findings and severity" }
  ],
  "handshakes_needed": ["<prefix>-reviewer"]
}

reviewer

{
  "setup": "code-review-pipeline", "setup_name": "Code Review Pipeline",
  "role": "reviewer", "role_name": "Code Reviewer",
  "hostname": "<prefix>-reviewer",
  "description": "Analyzes scan results, checks code patterns, suggests improvements.",
  "skills": {
    "pilot-event-filter": "Filter scan results by severity and relevance before analysis.",
    "pilot-alert": "Flag critical findings that need immediate attention.",
    "pilot-audit-log": "Log all review decisions for compliance and traceability."
  },
  "peers": [
    { "role": "scanner", "hostname": "<prefix>-scanner", "description": "Sends scan results from PR analysis" },
    { "role": "reporter", "hostname": "<prefix>-reporter", "description": "Receives review verdicts for reporting" }
  ],
  "data_flows": [
    { "direction": "receive", "peer": "<prefix>-scanner", "port": 1002, "topic": "scan-result", "description": "Scan results with findings and severity" },
    { "direction": "send", "peer": "<prefix>-reporter", "port": 1002, "topic": "review-verdict", "description": "Review verdict with suggestions and approval status" }
  ],
  "handshakes_needed": ["<prefix>-scanner", "<prefix>-reporter"]
}

reporter

{
  "setup": "code-review-pipeline", "setup_name": "Code Review Pipeline",
  "role": "reporter", "role_name": "Review Reporter",
  "hostname": "<prefix>-reporter",
  "description": "Formats review results, posts PR comments, tracks metrics.",
  "skills": {
    "pilot-webhook-bridge": "Post review comments to GitHub PRs via webhook.",
    "pilot-slack-bridge": "Send review summaries to Slack channels.",
    "pilot-receipt": "Confirm delivery of review notifications to external systems."
  },
  "peers": [
    { "role": "scanner", "hostname": "<prefix>-scanner", "description": "First stage — does not communicate directly" },
    { "role": "reviewer", "hostname": "<prefix>-reviewer", "description": "Sends review verdicts for reporting" }
  ],
  "data_flows": [
    { "direction": "receive", "peer": "<prefix>-reviewer", "port": 1002, "topic": "review-verdict", "description": "Review verdict with suggestions and approval status" },
    { "direction": "send", "peer": "external", "port": 443, "topic": "review-notification", "description": "Review notification posted to PR and Slack" }
  ],
  "handshakes_needed": ["<prefix>-reviewer"]
}

Data Flows

  • scanner -> reviewer : scan-result events (port 1002)
  • reviewer -> reporter : review-verdict events (port 1002)
  • reporter -> external : review-notification via webhook (port 443)

Handshakes

# scanner and reviewer handshake with each other:
pilotctl --json handshake <prefix>-reviewer "setup: code-review-pipeline"
pilotctl --json handshake <prefix>-scanner "setup: code-review-pipeline"

# reviewer and reporter handshake with each other:
pilotctl --json handshake <prefix>-reporter "setup: code-review-pipeline"
pilotctl --json handshake <prefix>-reviewer "setup: code-review-pipeline"

Workflow Example

# On reviewer — subscribe to scan results:
pilotctl --json subscribe <prefix>-scanner scan-result

# On reporter — subscribe to review verdicts:
pilotctl --json subscribe <prefix>-reviewer review-verdict

# On scanner — publish a scan result:
pilotctl --json publish <prefix>-reviewer scan-result '{"pr":142,"repo":"acme/api","findings":[{"file":"auth.go","line":58,"severity":"high","rule":"sql-injection"}]}'

# On reviewer — publish a review verdict:
pilotctl --json publish <prefix>-reporter review-verdict '{"pr":142,"status":"changes_requested","comments":1}'

Dependencies

Requires pilot-protocol skill, pilotctl binary, clawhub binary, and a running daemon.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Security

xfire Security PR Review

Multi-agent adversarial security review — 3 AI agents debate every finding, only real vulnerabilities survive

Registry Source
3500Profile unavailable
Coding

FreeGuard VPN Setup Guide

Use when a user wants to set up, use, or troubleshoot FreeGuard VPN - guides non-technical users through installation, login, connection, and daily usage wit...

Registry SourceRecently Updated
3240Profile unavailable
Coding

Claude Code Controller

控制和管理 Claude Code 编码助手,支持项目感知编码、代码审查、重构和功能实现。使用 ACP 运行时在隔离会话中执行 Claude Code 任务,或在主会话中管理配置和项目上下文。

Registry SourceRecently Updated
4931Profile unavailable
Coding

QA Reviewer

提供代码审查、单元测试、覆盖率分析和问题追踪,支持C++/Python/JavaScript,确保项目质量和文档完整度。

Registry SourceRecently Updated
4683Profile unavailable