Development plugins

SOTA Rust tooling - refactoring, profiling, benchmarking, testing, SIMD, dependency audit

2 skills · hooks

MagicDocs system — skills for bootstrapping, creating, and maintaining terse architectural documentation

3 skills

Debug and analyze Undo recordings using AI-powered queries

1 skill · 1 MCP server · hooks

Agent skills for PyXLL that ensure AI always consults the live documentation — not outdated training data — when writing, configuring, or debugging PyXLL code.

3 skills

Scaffold a multi-agent Claude Code development system for any project from its vision and tech stack.

1 skill · 1 agent · hooks

Guitar Alchemist DSL — in-process music theory tools (chord analysis, interval lookup, key inference, tab search) exposed as MCP tools, plus the /ga slash command for quick theory queries.

1 skill · 1 command · 1 MCP server

Operate eth2-quickstart through Claude Code using the canonical wrapper and MCP server.

2 skills · 1 MCP server

Code-quality rule engine: guard codebase health against vibe-coded bloat

2 skills · hooks

Android development skills vendored from Google's Android Skills (Apache 2.0): R8 analyzer, edge-to-edge migration, and Android CLI orchestration

3 skills

The owner's technology-selection knowledge base: decision frameworks with their reasons, one skill per domain.

3 skills

Biome linter and formatter MCP server with post-edit hooks for Claude Code

1 command · 1 MCP server · hooks

Bun test runner MCP server with post-edit hooks for Claude Code

1 command · 1 MCP server · hooks

MicroPython device interaction patterns via mpremote: connecting, file transfer, and persistent PTY sessions

3 skills

MicroPython project rules, multi-agent review skill, and documentation style guide for any MicroPython repo

2 skills · hooks

Code quality analysis, review, and cleanup commands

3 commands

General-purpose KubeRocketCI development utilities including commit message generation and code review

2 commands · 1 agent

Shepherd a whole GitHub Epic (issue with sub-issues) end-to-end. Phase 1 snapshots open sub-issue topology + blocked_by edges into a tier-ordered sequence JSON. Phase 2 (/loop /epic-shepherd:shepherd) is the autonomous tick loop — dispatches an implementer for each ready issue, polls for the opened PR, hands it off to pr-shepherd to drain reviews + merge, regenerates the snapshot so closed issues advance the frontier. Phase 3 (v0.3.0) autonomously closes out the epic when the sequence empties: composes a close-out report, opens a PR that squash-closes the epic via 'Closes #N', shepherds that PR via pr-shepherd, exits the loop. Hard stops (human CHANGES_REQUESTED, branch protection, conflict, ping-pong cap, implementer failure, sub-issue reopened mid-closeout) pause and surface.

1 skill · 2 commands

Research and verify IETF RFC claims from authoritative source text.

2 skills · 1 MCP server

Run Claude in a while-true loop with the same prompt until task completion

2 commands · hooks

Canonical rooms, tasks, context, receipts, and agent lifecycle integration for Claude, Codex, Gemini, and LLM Caret

1 skill · 1 MCP server · hooks

Stack-aware clean-code best practices. Detects the project's framework and version, then loads only the matching guidance across frontend, backend, and shared core standards.

3 skills

IDE-grade code intelligence for agents — Serena (LSP symbol nav/refactor) and ast-grep (AST search/rewrite) with usage cheatsheets, setup helpers, and a context-isolated explorer agent

2 skills · 1 agent

Java/JVM tooling — Maven Central intelligence, class search/decompilation (MCP via Docker), plus jar-explore for raw JAR content inspection

3 skills

Gives Claude a deterministic semantic graph of your codebase instead of flat text. Exact callers, real blast radius, and scoped context in a few hundred tokens rather than whole files.

2 skills · 1 MCP server

Build sanitized, classified SQL context through the managed local service.

1 skill · 1 MCP server · hooks

Your agents, learning together. Connect your AI agent client (Claude Code, Grok (preview, not GA) and other MCP-capable clients) to Dharma Agent Fabric to inspect and operate your organization's authorized agents, tasks, evidence and shared skills.

2 skills · 1 MCP server

Proactive LSP context injection for Claude Code — symbols, diagnostics, and structural context via hooks + persistent daemon

2 skills · hooks

A Claude Code plugin that reads papers from Zotero and generates structured study notes into Obsidian.

2 skills · hooks

unit-check skill, Cynicχl reviewer (agent and skill), and scidata-mcp server for scientific software work.

2 skills · 1 MCP server

High-signal software engineering skills for AI coding agents: interactive assisted PR reviews, code architecture, and engineering workflows

3 skills