Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
Create slash commands (reusable prompt templates). Use when building /commands, defining workflows users invoke explicitly, or setting up repeatable prompts with arguments.
Create and use Claude Code slash commands - quick prompts, bash execution, file references
Create and use Claude Code slash commands - quick prompts, bash execution, file references
Query and manage Linear issues, projects, and team workflows.
Automatically cherry-picks a specified commit (or the latest commit from the current branch) to multiple target branches, pushes them to the remote, and creates Pull Requests. Also includes...
Rollback failed deployments, restore previous versions, and handle deployment emergencies. Use when deployments fail, critical bugs are discovered in production, performance degrades after...
Set up AI tool symlinks in a repository for multi-agent compatibility. Use when the user wants to set up skills for Gemini, Claude, or other AI tools, or when they mention "setup skills",...
Use when analyzing fix commits to create postmortems, checking code changes against known issues before release, or updating postmortem knowledge base after release. Triggers on /postmortem...
Enables AI agents to report status to the central AI Command Center via GitHub API.
|
Automated code review workflow using OpenAI Codex CLI. Implements iterative fix-and-review cycles until code passes validation or reaches iteration limit. Use when building features requiring...
|
|
Systematic debugging cycle - reproduce, isolate, hypothesize, fix.
Use when errors occur deep in execution and you need to trace back to
Professional code review skill for Claude Code. Automatically collects file changes and task status. Triggers when working directory has uncommitted changes, or reviews latest commit when clean....
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to...