am-will/codex-skills

Use this skill to complete the RED phase of TDD: define behavior with tests first, verify they fail for the right reason, then hand off implementation with objective pass criteria.

Spawn autonomous subagents to offload context-heavy work. Subagents burn their own tokens, return only final results.

Retrieve current library documentation via Context7 API.

Source details, install context, and public review data are available on the full page.

Use agents.planners to define any number of planning agents, and optionally agents.judge to override the judge. If agents.judge is omitted, the first planner config is reused as the judge. If agents is omitted in the task spec, the CLI will use the user config file when present, otherwise it falls back to the default...

Source details, install context, and public review data are available on the full page.

Use the OpenAI developer documentation MCP server from the shell to search and fetch authoritative docs. Always do this for OpenAI platform work instead of relying on memory or non-official sources.

Source details, install context, and public review data are available on the full page.

Source details, install context, and public review data are available on the full page.

Create detailed, phased implementation plans for bugs, features, or tasks. You make phased implementation plans with sprints and atomic tasks.

Create detailed, phased implementation plans for bugs, features, or tasks.

Access GitHub repository documentation and code via the gitmcp.io MCP service.

Use this skill when the user wants to create, update, or troubleshoot custom subagent roles backed by [agents. ] and a role config_file .

Source details, install context, and public review data are available on the full page.

Create implementation plans with explicit task dependencies optimized for parallel agent execution. This skill can be ran inside or outside of Plan Mode.

Rule: Mobile-first development with consistent breakpoints, fluid layouts, relative units, and touch-friendly targets.