Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about Claude Code…
Perform thorough code reviews with security, performance, and maintainability analysis. Use when user asks to review code, check for bugs, or audit a codebase.
Build MCP (Model Context Protocol) servers that give Claude new capabilities. Use when user wants to create an MCP server, add tools to Claude, or integrate external services.
Install, share, sync, and create AI agent skills across coding tools (Claude Code, Cursor, Codex, OpenCode, Copilot, Pi) using the agr CLI. Use whenever the user mentions agr, agr.toml, agr.lock, agrx, or asks to: add a skill ("install the pdf skill", "agr add ..."), sync agent resources across tools, share skills…
Release process for the agr package. Handles version bumping (major/minor/patch/beta), changelog updates, pre-release quality checks, git tagging, and monitoring the GitHub Actions publish pipeline. Use this skill whenever the user wants to cut a release, bump the version, publish to PyPI, or asks about the release…
Debrief an AI agent skill (SKILL.md) after using it — capture session feedback or a retrospective and fold it back into the skill. Use whenever the user says: "debrief the X skill", "let's debrief X", "retrospective on X", "feedback on X skill", "improve the X skill", "update the X skill", "let's revise X based on…
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
Audit iOS port parity against the Android app. Compares ViewModels, Views, Settings, and Navigation at the code level, verifies features from docs/videos/ TOML project files, and optionally captures side-by-side screenshots. Use when the user asks to compare iOS vs Android, check iOS parity, find missing iOS features…
Group open GitHub issues into cohesive sets, each landable as a single PR, with a merge order and a parallelism verdict. Use when the user asks which issues can be fixed in one PR, how to batch issues into PRs, how to plan the work for a release, or how to split a set of issues across sessions. Accepts a priority/area…
Unified release for both Android and iOS from a single version tag. Runs quality gates, bumps both platform versions in one commit, tags, builds both platforms, uploads Android to Play Store, and opens iOS archive for App Store upload. Use when the user asks to release, ship, cut a release, or make a new version.
Use when a user wants to bootstrap an experiment-orchestration skill for their own simulation framework. Captures their framework profile via 17 questions, then emits a tailored paper-to-experiment skill (templates, schema, registry, validator) into their .claude/skills/.
Use when reproducing a physics paper (or part of one) in this MD framework. Walks a paper PDF through the design template + registry, validates against the schema, registers any new force/analyzer/visualizer in the framework's forwarding station, and emits a runnable configs/plan.json. Used at the start of any new…