
Makes the agent interview you about a plan or design, one question at a time with a recommended answer attached, until every branch of the decision tree is resolved and you both share the same understanding.

Makes the agent interview you about a plan or design, one question at a time with a recommended answer attached, until every branch of the decision tree is resolved and you both share the same understanding.

A complete software-development methodology packaged as composable skills the agent reaches for on its own: brainstorming before code, writing and executing plans, test-driven development, systematic debugging, verification before completion, requesting and receiving code review, git worktrees, subagent-driven development.

Rewrites AI-sounding text so it reads like a person wrote it, without changing what it says.

Anthropic's official code-review plugin for Claude Code: runs a structured review of a diff or pull request for correctness, standards and spec adherence and reports findings with locations and severity.

Anthropic's official frontend-design skill, shipped as a plugin in the claude-plugins-official marketplace and as a skill in anthropics/skills.

General-purpose browser automation for coding agents: the agent writes and runs custom Playwright scripts on the fly, from a single page check to a multi-step flow, with a visible browser by default so you can watch it.