Development plugins

/mcp-oauth-doctor:mcp-oauth-doctor runs the doctor against an MCP server URL and explains the first broken sign-in step (401 challenge, protected-resource metadata, authorization-server discovery, client registration), whose it is — the server, its identity provider or a known client bug — and the fix, per client.

1 skill

A grab bag of agent skills for gaps in the existing ecosystem. Install once to get every skill in the collection.

1 skill

On-demand Astro diagnostics via /astro-check:check — zero memory cost, runs astro check and exits

1 skill

Full Astro language server — real-time diagnostics, go-to-definition, references. ~400MB memory. For heavy editing sessions.

LSP

Inspect and deterministically scan live process memory on macOS, Linux, and Windows, or authorized Windows x64 minidumps

1 skill

ctrlsys routine lookup and usage guidance

1 skill

LTI systems, controller design, discretization

1 skill

Process identification and lambda tuning

1 skill

Create, instrument and package SLS HTML5 activities with verified xAPI reporting.

1 skill

Assess an app built with an AI coding tool and get a Ship, Harden, Rebuild, or Retire verdict with file-level findings.

1 skill

Reef workspaces in place of git worktrees: each worktree session and subagent gets a copy-on-write Reef workspace, held while the session runs.

hooks

Create new skills, modify and improve existing skills, and measure skill performance. Runs a guided interview to scope new skills and helps choose an orchestration architecture (inline, forked subagent, dynamic workflow, or agent team). Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

1 skill

Guidelines for building Go applications on the Blueprint framework and GoAuth authentication library

1 skill

ClickHouse practices, tunables and gotchas: schema and sorting-key design, query optimization, ingestion, materialized views, replication, operations

1 skill

Kodein's code review workflow: findings recorded in an ISSUES.adoc file, then fixed one commit at a time

1 skill

Host adapters for CodeRifts: Claude Code PreToolUse asks before Write/Edit of OpenAPI, AsyncAPI, GraphQL, protobuf, or MCP manifest files. Not the GitHub Action (coderifts/contract-gate) and not the guard library (@coderifts/agent-guard).

hooks

Architects Swift server backends as gRPC microservices behind a Hummingbird gateway, one Swift package per service, with Postgres row-level security, Valkey and Temporal workflows. Use when planning a Swift backend or splitting it into services, adding a service, endpoint, use case, repository, migration, webhook, multi-tenant table, background job or durable Temporal workflow, drawing a Swift server's module boundaries or writing its Package.swift, wiring configuration, graceful shutdown, mTLS or JWT auth, naming server types and targets, setting up a server package's tests, CI/CD or deployment, or reviewing a Swift server's architecture or code style. Not for iOS, macOS or SwiftUI apps. Applies even when the user doesn't name the architecture.

1 skill

Meta-plugin combining all Artemis City Anaconda/Claude skills; installs the anaconda-agent-studio skill and others.

1 skill

IoT and embedded work done safely: identify the board and its voltages before wiring, back up flash before flashing, MQTT and OTA with authentication and a way back, and proof on the real device before 'done'.

1 skill

PLC, industrial automation and robotics with safety first: safety functions stay with qualified engineers, programs are backed up from the PLC before editing, simulation before site, Modbus/OPC UA done right, commissioning evidence.

1 skill

Research with integrity: every reference verified to exist (DOI, Crossref, OpenAlex, PubMed, arXiv), accurate quotes and numbers, reproducible analysis, sound statistics, ethics and AI-use disclosure.

1 skill

Coding practices that apply on any host: design and clarity over expediency, security first, comment discipline, logging, and verifying what you don't know. No hooks, no forge.

1 skill

Собрать, проверить и выпустить плагин по стандарту.

1 skill

Свой ИИ-сотрудник: скилл = должностная инструкция (расширенный форк официального skill-creator).

1 skill

Expert ReduxKit to create an application using the redux architecture convention.

1 skill

Cross-provider development loop: independent plan review, delegated build, and independent final inspection across Claude Code, Codex, Kimi Code, DeepSeek Harness and qwen-code.

1 skill

Lavish extension: /lavish-ext:code-walkthrough turns a PR, branch, or diff into a plain-words, step-by-step walkthrough page (Overview, then Step 1..N with the code and why). Requires the lavish skill.

1 skill

Self-check a Codyssey AI Native final project against the official rubric

1 skill

Run the mnemonic memory MCP server, with its embedding key read from Vault at start.

1 MCP server

Skills for contributing to Enonic's own repositories, starting with documentation

1 skill