Browse Skills

OpenSpec Explore enters a thinking-partner mode for exploring ideas, investigating problems, and clarifying requirements before or during a change. It reads code, maps architecture, and compares options without implementing.

Review Chorus guides the Admin Agent through the AI-DLC review stage: approving or rejecting proposals, verifying completed tasks, and managing project governance.

Yolo Chorus drives a single prompt from Idea through Proposal, Execution, Verification, and Code Review to Done without human-in-the-loop. Use it when you want an agent to autonomously plan, build, review, and ship a software change in Chorus.

Research gathers external knowledge and logs it as source-cited §R rows so builds ground in facts instead of hallucinating library behavior. Use it when a spec decision hinges on a library, API, or best practice you are unsure of.

Spec Mutator creates, amends, and backprops bugs into SPEC.md at the repo root, serving as the sole mutator of the project spec. Use it when writing a new spec, distilling from existing code, adding invariants, amending sections, or recording a bug via backprop.

Ask Questions If Underspecified asks the minimum clarifying questions needed before work starts when a request lacks key details. Use it to avoid implementing the wrong scope, behavior, or constraints.

Best Practices transforms vague prompts into stronger Claude Code prompts with added context, constraints, phases, and verification. Use it when you want to improve a task prompt before execution or evaluate prompt quality.

Curate A Team Library helps build a managed skills library for a team’s stack. It maps work to shelves, checks existing skills before adding new ones, and creates a starter pack once the first pass is stable.

LLM Application Development covers prompt engineering, API integration, and RAG patterns for building AI-powered features. Use it for chatbots, LLM-based automation, and apps that generate or retrieve text.

Check Prompt evaluates and improves AI prompt quality by analyzing prompts against best practices for structure, executability, prohibited items, quality assurance, roles, and continuous improvement. Use it to score, deep-analyze, or automatically fix prompts for AI agents.

Context7 searches technical documentation using the Context7 MCP, triggered by requests like "check the docs" or "how to use this library?". Use it to look up API references and solutions from official docs within Claude Code.

Explain Code provides detailed explanations of code behavior, logic, patterns, performance issues, and security concerns. Use it when asked to explain this code or understand how a function, algorithm, or project works.