Coding standards, frameworks, refactoring, and code review (15.8K skills)
Prepare a selected batch of pull requests, or proposed code changes, by reviewing overlaps, diagnosing conflicts, and preserving contributor credit. Check the exact version and required authorization before each merge, then report completed work and remaining holds.
Find agent skills on GitHub, score their relevance using rule-based checks, scan for malware and embedded secrets, and import them into supported agent directories, including Hermes, Claude Code, Gemini CLI, and OpenCode.
Find agent skills for installed coding tools such as Claude Code and Codex. Use OmniRoute to detect available tools, review relevant GitHub matches, and guide installation into each tool’s skill directory.
Use the command line to send tasks to OmniRoute's A2A server, which supports communication between agents. Inspect execution history and logs, monitor or cancel tasks, and interactively test the JSON-RPC 2.0 communication protocol.
Prepare a selected batch of pull requests, or proposed code changes, by reviewing overlaps, diagnosing conflicts, and preserving contributor credit. Check the exact version and required authorization before each merge, then report completed work and remaining holds.
Set up OmniRoute and manage its command-line configuration. Inspect and validate tool settings, manage environment variables, check for updates, and control automatic startup using commands that support both interactive and unattended setup.
Set up and check OmniRoute authentication for API access and dashboard sessions. Use Bearer credentials for remote requests, manage login cookies, inspect authentication status, and configure OIDC, a standard for signing in through an identity provider.
Keep coding changes small by questioning unnecessary work and reusing existing code, standard libraries, and native platform features. Apply this approach to implementation, bug fixes, reviews, and dependency choices while preserving validation, security, and accessibility.
Manage Omni Skills, plugins, and persistent memory from the command line. Find and install skills, run them with supplied input, inspect execution history, and maintain saved information alongside plugin installations.
Configure Codex CLI to connect through OmniRoute on Linux, macOS, or Windows. The workflow detects the operating system and shell, creates configuration files and seven profiles, sets environment variables, and verifies the setup.
Prepare selected pull requests for maintainer review by comparing failures with their current base, fixing authorized defects, and preserving contributor credit. Report complete or partial validation with evidence and outstanding checks before any separately authorized merge.
Register and manage webhook endpoints, which receive event notifications from OmniRoute. Choose events such as completed requests or exceeded quotas, test delivery, inspect delivery history, and manage retries when notifications need another attempt.
Find agent skills on GitHub, score their relevance using rule-based checks, scan for malware and embedded secrets, and import them into supported agent directories, including Hermes, Claude Code, Gemini CLI, and OpenCode.
Use the command line to send tasks to OmniRoute's A2A server, which supports communication between agents. Inspect execution history and logs, monitor or cancel tasks, and interactively test the JSON-RPC 2.0 communication protocol.
Find agent skills for installed coding tools such as Claude Code and Codex. Use OmniRoute to detect available tools, review relevant GitHub matches, and guide installation into each tool’s skill directory.
Connect AI agents to OmniRoute through MCP, a protocol for accessing tools. Use tools for request routing, memory, cache, providers, and audits, with three connection methods and permission scopes that control which operations are available.
Manage command-line tools connected to OmniRoute through its API. Inspect tool status, read or change settings, manage Codex profiles and backups, and invoke tool plugins for automation tasks.
Carry out reviewed pull request plans, apply approved fixes, and preserve contributor credit. Validate the exact changes being merged, merge only explicitly authorized groups, and keep items on hold when required checks fail or remain unknown.
Review code for security flaws, bugs, performance problems, maintainability, and test quality. Produce structured feedback with issue locations, likely impact, suggested fixes, positive observations, and a recommendation on whether changes are ready to merge.
Build MCP servers, which let Claude call external tools and read data through a shared protocol. Follow Python or TypeScript examples to implement tools, connect services, configure Claude, and test server behavior.
Coordinate named agent teams on Grok Build using Ruflo MCP tools or a command-line message bus. Organize design, coding, testing, and review into ordered steps, with team-specific messages, status tracking, and shutdown.
Manage GitHub pull requests, which are proposals to merge code changes, from creation through review, testing, conflict resolution, and merging. Coordinate multiple agents to divide review work and track progress across the process.
Help design quorum management for distributed systems, where multiple nodes must agree on decisions. Covers adapting participation thresholds and voting weights to network conditions, performance, and failures, plus membership changes, validation, and rollback.
Implement and manage Raft, a method for keeping distributed servers in agreement. Covers leader election, log replication, node membership changes, and recovery after network disruptions to maintain consistent state across the cluster.