Developer Tools plugins

Production UX contracts and durable design context for frontend implementation.

2 skills

Teaches coding agents to build AppKit UI on UIFoundation: the widgets, stacks, result builders and .box helpers to reach for instead of hand-rolling, their traps, and an app settings layer on PersistentSettings.

2 skills

Write, review, and fix code in any language — complete, runnable blocks you can paste, with nothing left out. Or skip the code and have a web app or website built on B12.

1 skill

Audit and repair AI-generated n8n workflows before production

1 skill

Clone any app or website, then make it better and yours: research, measured design, clean-room build, scored gates, launch.

1 skill

Web Project MVP 1

Mine past Claude Code conversations for decisions, mistakes, patterns, and wisdom. Manage memory lifecycle: audit staleness, extract knowledge, prune waste.

4 skills · 8 commands · 5 agents

Deep codebase interrogation — multi-angle architecture review with 6 specialized agents, 5 review styles (including Paranoid Mode), and 8 add-on pressure tests. v1.3.0 ships the Codex CLI plugin layout alongside the Claude Code layout.

8 skills · 1 command · 6 agents

Comprehensive GitHub CLI search commands and troubleshooting

9 skills · 1 command · 3 agents · hooks

Skills that keep AI slop out of your plans, designs, and code. Works with Claude Code, Codex, Cursor, Gemini CLI, and any Agent Skills-compatible agent.

13 skills

AI-powered OpenStack code review toolkit

1 skill · 9 agents

Official Upstage AI bundle: Solar models, document processing (OCR, parse, classify, extract), schema generation, Studio agent workflows, multi-API builder for webapps, and BotMadang client. One install activates all 9 skills.

9 skills

Configure and run DiffPal reviews locally and in CI.

6 skills

Repo-local Codex plugin for this workspace only. Not intended for marketplace publication.

1 skill · 5 MCP servers

Package-specific skills for the dart_helper_utils Dart package: exact utility APIs (strings, maps, collections, dates, intl formatting), async timing tools (Debouncer, throttle, stream transformers), the v5-to-v6 and v6-to-v7 migrations, and version upgrades.

5 skills

Local-first AST codebase-to-user-flow mapper and 11-heuristic UX gap auditor across 7 frontend and mobile frameworks.

4 skills · 1 command

Delegate coding work across harnesses and accounts, with every run recorded.

3 skills · 1 MCP server · hooks

Plugin of Agent Skills for working with Xojo projects.

4 skills

Your coding agent shows its evidence before it edits, and its diff is verified against the plan it declared. Local, read-only MCP server with 16 tools — BM25 and regex code search, symbol resolution, references and call relationships, impact analysis, context packs, plan_change and verify_change — from a native binary and an index under .ok/. Supports Rust, TypeScript, Python, Go, Java, and JavaScript.

1 skill · 1 MCP server · hooks

Real-time session logging, command history, and auto-naming for Claude Code

2 commands · hooks

EverOS memory for Claude Code - automatic recall, capture and session seal against a local EverOS server.

2 skills · hooks

Use SurrealDB Agent Memory through the managed OAuth MCP server with optional Codex turn capture

1 skill · 1 MCP server · hooks

Official Hex-Rays IDA MCP Server.

1 MCP server · hooks

Compile repositories and documents into local, provenance-backed domain expertise for coding agents.

2 skills

在终端和Agent中管理优云智算 GPU 实例、镜像、云盘、存储和团队资源。Command-line client for managing CompShare GPU compute resources

2 skills

Search, score, and rank GitHub developers for technical recruiting. 9 tools: plan_search, search_developers, get_developer_profile, rank_candidates, score_against_jd, compare_candidates, bulk_score, generate_outreach, get_repo_contributors.

1 MCP server

Chained clarity review of a repo, plan, or work items — combines code review, plan refinement, deep-module architecture, DRY/cruft, and naming analysis. Use for clarify/defuzz/audit/harden/fresh-eyes requests.

1 skill

Use when asked to crystallize a workflow, skill, codebase, or agent runs, or to find where agents repeatedly rediscover methods, apply stable rules, or do unnecessary work. Analysis of opportunities to replace repeated agent effort with reusable procedures; not a general code cleanup or an automatic implementation run.

1 skill

Extract plain text from ebooks (EPUB, MOBI, PDF) for analysis, processing, or reading.

1 skill

MCP server bridging AI coding hosts to cursor-agent over ACP.

1 skill