Vague software requests often lead to rework and drift. Ralph helps Claude, Codex, and Claude Code clarify requirements, create specs, and verify progress through bounded loops.

AI coding agents can start work before plans are clear, which makes errors costly. Plannotator adds a browser review step for plans, diffs, images, approvals, and structured feedback.

Complex coding tasks are hard to split, verify, and resume across multiple agents. OMC adds team, autopilot, and verify/fix workflows for Claude Code projects.

Developers need clear patterns for production AI flows, agents, RAG, and deployment. This skill provides Genkit setup, examples, commands, and deployment guidance for Firebase and Cloud Run.

Firebase teams often need safe patterns for adding Gemini features without scattered setup notes. This skill guides Firebase AI Logic setup, SDK usage, prompt handling, and basic security practices.

Growing projects often become hard to navigate when folders and names evolve without rules. This skill gives Claude, Codex, and Claude Code practical structures for cleaner codebases.

Teams need a controlled way to delegate reviewed GitHub issues to Copilot Coding Agent. This skill documents a label-based workflow that assigns Copilot, starts implementation, and tracks draft pull requests.

Complex code slows changes and raises regression risk. This skill guides behavior-preserving refactors with tests, extraction patterns, and validation steps.

Large repositories make code paths and dependencies hard to locate quickly. This skill guides Claude, Codex, and Claude Code through targeted semantic, grep, glob, and history searches.

AI-assisted projects often lose phase context and skip review checkpoints. This skill initializes BMAD workflow files, shows current status, and routes teams through phase-based planning.

Backend services fail when edge cases, auth flows, and data changes are not tested. This skill guides Claude, Codex, and Claude Code to create focused backend tests.

API teams need consistent contracts before implementation starts. This skill guides resource design, request formats, errors, versioning, and documentation.

Manual feature testing can miss edge cases and leave evidence scattered. This skill plans browser scenarios, captures results, uploads media, and creates a structured Alan report.

Pull request reviews often miss context or produce vague feedback. This skill gathers GitHub evidence and posts focused, line-specific findings through Alan MCP tools.

Teams often need a clean task file before ralph-tui can execute a PRD. This skill converts requirements into structured user stories with dependencies and quality gates.

Large PRDs are difficult to turn into executable ralph-tui work. This skill converts PRD stories into beads with dependencies and quality gates.

Stripe version changes can break API responses, webhooks, and SDK clients. This skill gives structured guidance for planning, testing, and completing upgrades.

Multi-agent coding tasks can lose ownership, status, and completion signals. This skill guides Claude, Codex, and Claude Code through Orca orchestration commands for supervised dispatch, gates, and worker completion.

Orca projects often span worktrees, terminals, automations, and embedded browser tabs. This skill gives agents a precise CLI workflow for managing those Orca surfaces.

SpecDD projects can lose clear links between specs, source files, tests, and documentation. This skill guides Claude, Codex, and Claude Code to trace those links and report gaps without editing files by default.