A pre-check for calling external coding agents such as Codex or Gemini. It checks that the command-line tool is installed, credentials exist, the network works, rate limits allow a call, and the request is usable.
A task-intent classifier for the ce:work coding workflow. It distinguishes implementation, bug fixing, refactoring, exploration, configuration or documentation, and mixed tasks, then selects a matching approach.
A review step for code changes produced as a patch or diff, meaning a text description of file changes. Codex produces the patch in an isolated copy, Claude reviews it, and the user confirms before it is written.
A review policy that divides code reviewers into three levels: blocking issues, analytical concerns, and optional advice. It adds rules for how certain reviewers must be and how findings should be classified.
A document structure for tracking coding tasks in docs/tasks/. Each task has a plan.md for goals and acceptance rules, a state.md for progress and blockers, and a review.md for findings and conclusions.
Multi-agent collaboration overlay for ce:plan/work/review. ce:brainstorm structured convergence is built-in to [P] mode, not via [T]. Enables contract-gated execution with single writer principle, real Agent Teams verifier, and deterministic patch gate.
This skill should be used when designing user interfaces with a "worst user first" philosophy. It applies when creating forms, pages, flows, or any user-facing interface where usability and emotional comfort are priorities. Generates structured UI design proposals with interaction flows, layouts, copy guidelines, and…
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.
This skill should be used when writing Ruby gems following Andrew Kane's proven patterns and philosophy. It applies when creating new Ruby gems, refactoring existing gems, designing gem APIs, or when clean, minimal, production-ready Ruby library code is needed. Triggers on requests like "create a gem", "write a Ruby…
A collaborative workflow for exploring a feature or improvement before writing code. It produces a requirements document that records the intended behavior, scope, and measures of success.
A workflow for committing code, sending it to a remote Git repository, and opening or updating a pull request—a request for others to review proposed changes.
A coding workflow that reviews your current Git changes and creates one commit with a clear message. Git is a tool that records versions of files and commits are saved change sets.
A workflow for reviewing experience documents in a project's docs/solutions/ folder. It checks whether those documents are outdated, duplicated, or no longer match the codebase.
A workflow for turning a feature request into a lasting technical implementation plan. It explains how to build the feature but does not implement code, run tests, or use execution results.
A command that creates a GitHub Pull Request (PR), which asks to merge changes from one branch into another, and can optionally merge it into the main branch.