Skills covering MVUX, navigation, toolkit, themes (Material, Simple, shared semantic), authentication, Kiota API clients, and testing workflows for Uno Platform. The Uno documentation MCP is provided by the Uno tooling, not bundled in the plugin.
Four universal, opinionated skills for writing software: writing-code (API-consultation gate, dependency shape, orphaned-symbol sweep, footgun check, two-tier comment policy with a code-comment consistency gate), writing-tests (classicist behavior-first workflow with a dead-code stop that reports to the caller), writing-docs (single-owner surfaces, pointer-file discipline, anti-slop validation via the human-author:ai-slop-writing-fixer subagent), and sweeping-dead-code (a report-only sweep for unused code across a path, the repository, or a branch: a definition ledger, read-only runs of installed dead-code tools, reachability classification, and independent refutation subagents). Each skill is extendable at every step via Pre-Step-N / Post-Step-N positions and via recognized named configuration values; the plugin ships hooks that deliver a project's extension files (.claude/extensions/software-writer/) wrapped in a structural envelope.
Linux kernel mailing-list workflow: reading and monitoring threads on lore.kernel.org, checking patch state in patchwork, replying to review inline, submitting patch series with git send-email, and the communication rules that keep a submission alive — recipients, timing, tone, and prose that passes maintainer review
Consult OpenAI Codex for fresh analytical perspective — auto-escalation when stuck, on-demand second opinions, and web research. Uses the official codex-mcp-server with session management and GPT-5.2-codex.
Documentation skills following the Diataxis framework for organizing and generating docs into tutorials, how-to guides, reference, and explanation sections
Audit a URL for modern web quality and hill-climb guidance-backed fixes. The model is the auditor: it gathers raw-CDP evidence, judges 17 declarative principles against Modern Web Guidance, and writes fixes itself. Adds the /web-audit skill.
Bidirectional bridge between Claude Code and external AI coding agents. Exposes Claude Code as an A2A server (Gemini CLI, any A2A client) and as an ACP agent (OpenClaw, Zed, VS Code); routes outbound tool calls to Codex, OpenClaw, and Hermes adapters through a shared daemon with per-room task logs and verification-artifact support.
Debug Java programs interactively: launch under jdb or attach to a running JVM (JDWP), set breakpoints, step, and inspect variables, threads, and exceptions. Stateful background sessions, structured text/JSON output, native on Windows.
Dispatch one Conductor workspace per issue and supervise their PRs to merge: keep them current with the base branch, resolve conflicts, rerun transient CI failures, tell green PRs to merge, and archive each workspace once its PR lands
Dispatch one Paradev workspace per issue and supervise their PRs to merge: keep them current with the base branch, resolve conflicts, rerun transient CI failures, tell green PRs to merge, and archive each workspace once its PR lands
Opinionated, batteries-included spec for adding an SEO-first, i18n-ready blog to a Next.js + Sanity site. 40-question intake, one-page plan, 20-section spec, pass/fail checklist. Includes AI hero images via Gemini 3 Pro Image (Nano Banana Pro).
Core Swift language features, concurrency, API design guidelines, testing, SwiftData, Core Data, Charts, Codable, FormatStyle, and architecture patterns