Create a specialized agent by analyzing documentation URLs

You will create a new specialized agent by analyzing documentation from the provided URLs, guided by a specific intent or purpose.

Create a new Claude Code skill from a description

Load Ultracite rules for JS/TS development

Create well-formatted commit: $ARGUMENTS

Understand the current state of the git repository

Load context for a new agent session by analyzing codebase structure, documentation and README

Run security scans on project files (Python/Go/JS/TS)

Generate session report capturing learnings, tools, pitfalls, and extension recommendations

Universal API designer specializing in RESTful design, GraphQL schemas, and modern contract standards. **MUST BE USED** proactively whenever a project needs a new or revised API contract. Produces clear resource models, OpenAPI/GraphQL specs, and guidance on auth, versioning, pagination, and error formats—without prescribing any specific backend technology.

MUST BE USED whenever server‑side code must be written, extended, or refactored and no framework‑specific sub‑agent exists. Use PROACTIVELY to ship production‑ready features across any language or stack, automatically detecting project tech and following best‑practice patterns.

MUST BE USED to explore and document unfamiliar, legacy, or complex codebases. Use PROACTIVELY before refactors, onboarding, audits, or risk reviews. Produces a full-length report—architecture, metrics, risks, and a prioritised action plan—that other sub-agents can act on.

MUST BE USED to run a rigorous, security-aware review after every feature, bug‑fix, or pull‑request. Use PROACTIVELY before merging to main. Delivers a full, severity‑tagged report and routes security, performance, or heavy‑refactor issues to specialist sub‑agents.

MUST BE USED to craft or update project documentation. Use PROACTIVELY after major features, API changes, or when onboarding developers. Produces READMEs, API specs, architecture guides, and user manuals; delegates to other agents for deep tech details.

MUST BE USED to validate outputs from other agents to prevent hallucinations and ensure accuracy. Use PROACTIVELY to verify research tasks, documentation, code explanations, and any AI-generated content. Cross-references claims against codebase, web sources, and documentation while providing confidence scores and corrective actions.

MUST BE USED to deliver responsive, accessible, high‑performance UIs. Use PROACTIVELY whenever user‑facing code is required and no framework‑specific sub‑agent exists. Capable of working with vanilla JS/TS, React, Vue, Angular, Svelte, or Web Components.

Generates a new, complete Claude Code sub-agent configuration file from a user's description. Use this to create new agents. Use this Proactively when the user asks you to create a new sub agent.

MUST BE USED whenever users report slowness, high cloud costs, or scaling concerns. Use PROACTIVELY before traffic spikes. Identifies bottlenecks, profiles workloads, and applies optimisations for blazingly fast systems.

MUST BE USED to analyse any new or unfamiliar codebase. Use PROACTIVELY to detect frameworks, tech stacks, and architecture so specialists can be routed correctly.

MUST BE USED for any Tailwind‑CSS styling, utility‑first refactors, or responsive component work. Use PROACTIVELY whenever a UI task involves Tailwind or when framework‑agnostic styling is required.

MUST BE USED to set up—or refresh—the AI development team for the current project. Use PROACTIVELY on new repos or after major tech‑stack changes or when user asks to configure the AI team. Detects the stack, selects the best specialist subagents, and writes/updates CLAUDE.md with an “AI Team Configuration” section.

Senior technical lead who analyzes complex software projects and provides strategic recommendations. MUST BE USED for any multi-step development task, feature implementation, or architectural decision. Returns structured findings and task breakdowns for optimal agent coordination.

Review code for best practices, security issues, and potential bugs. Use when reviewing code changes, checking PRs, analyzing code quality, or performing security audits.

Generate clear, conventional commit messages from git diffs. Use when writing commit messages, reviewing staged changes, or preparing commits.

11 hooks across 8 events