videocontent
claudecodexAnalyze, search and reason over video: /videocontent skill + MCP tools.
1 skill · 1 MCP server
Claude Code and Codex plugins their authors filed under "development". All categories.
Analyze, search and reason over video: /videocontent skill + MCP tools.
1 skill · 1 MCP server
Write idiomatic code against the Waystone.Net packages — composing Option<T> and Result<TOk, TErr>, the traps that defeat them, and the WM analyzer diagnostics that catch those traps.
2 skills
Map the codebase first: symbols, callers, impact/blast radius, hotspots over a pre-indexed knowledge graph. Skill + MCP server.
1 skill · 1 MCP server
Your coding assistant plans, sandboxed workers build, and nomArmy checks every change before it counts: the tests run again in a fresh sandbox, and must fail with the change reverted. Needs `npm install -g nomarmy` and `nomarmy setup` first.
1 skill · 1 MCP server
SHELEG Design methodology: cinematic scroll-driven landing pages (single scroll clock, layered degrade-to-calm motion, WebGL particle formations), a motion doctrine that decides whether to animate before it decides how, and thirty-nine pluggable visual style packs, each with a ready-made token layer — instrument-console (near-black aerospace console; technical systems and infrastructure), editorial-luxury (cream and espresso; editorial, research, premium B2B), workbench (quiet light/dark UI; dashboards, admin, internal tools), briefing-room (dark 16:9 deck; investor and board presentations), atrium (cream daylight; consumer health and high-trust DTC), babylove (white with orange; SEO SaaS, long time-to-value, disconnected states), patchbay (black with mint-cyan; engines, buses, pipelines, OSS front doors), nameplate (cool slab with coral; press, certification and third-party trust), rimlight (white with blue light; studios, services and case studies), onionskin (white working sheet; developer and AI infrastructure), deskmate (warm beige with a dusk bleed; AI coworkers and chat-native agents), test-drive (warm paper with one coral; self-serve SaaS proven by the live product), surveyor (peach paper with teal and pink; visibility, monitoring and benchmark tools), chorus (warm paper under a crosshair grid, with a cut-corner bubble; AI-search visibility, brand monitoring and community marketing), outrank (white with violet; one brand across marketing and product), orchard (warm oat slabs; friendly biotech and wellness), field-notes (ruled green paper; auditable open-source developer tools), showroom (white gallery; product-led companies selling the app), blueprint (white technical stock; vector, storage and query infrastructure), prism (iridescent hard edge; command-first OSS infrastructure), maquette (near-black table; enterprise data infrastructure), cyclorama (looping pastel field; applied-AI consultancies), scoreboard (warm paper; growth, ads and accumulating metrics
1 skill · 1 command
Explicit Nittle review skill and MCP server.
1 skill · 1 MCP server
dm42: write, review and debug HP-42S-family RPN programs, the SwissMicros DM42n first (also DM42, Free42, Plus42). /dm42:rpn is the workflow and the verified reference — program-text rules, stack lift, flags, locals, menus, GETKEY vs GETKEY1, PIXEL/AGRAPH, the DM42 virtual variables and graphics modes — with a round-trip check for the lines the text parser drops silently. /dm42:setup builds dm42sim: SwissMicros' own Free42 core compiled as for the device, driven headless by action scripts that return JSON. No hooks, no MCP.
2 skills
Explicit Nittle review skill and MCP server.
1 skill · 1 MCP server
Connect Android ADB through Tailscale and switch the device to TCP ADB on port 5555.
2 skills
Set up Agent Guild, then see and steer its sessions from this agent: the setup-agent-guild skill and the Agent Guild MCP server.
1 skill · 1 MCP server
Write Neo plugins (neo-plugin) and change Neo itself (neo-core).
2 skills
The Juice AI guide (AGENTS.md) and every package's AI card, as a skill that triggers on any Juice code.
1 skill
Skills for driving the kkullm CLI and board
1 skill
Strict Python formatter hook
hooks
Supervise multi-agent coding work: Opus investigates, Sonnet implements, an Opus babysitter handles PR review, the main session reviews and ships
1 skill
Architecture documentation tooling for Spryker projects — arc42/C4 records, ADRs, and Solution Designs.
1 skill
Write and update project markdown (README, PR template, CONTRIBUTING, CHANGELOG, docs) that matches the project's existing tone. Picks a project-type archetype (library, cli, app, framework, side-project, showcase), reads CLAUDE.md and git context, supports animated and visually-striking showcase READMEs for profiles and portfolios, remembers style choices in .md-craft.json so later runs skip the style question, and shows a diff plan before writing.
1 skill
Read-only research agent that gathers and fact-checks information from the codebase or the public web.
1 agent
Deprecated: part of lexi 0.12.0 and later.
hooks
cmux 内蔵ブラウザを使った E2E テスト実行基盤。認証を含む UI フローを画面で見ながら検証する。
1 skill
cmux ワークスペースによる並列タスクディスパッチ。タスクごとに分離した git worktree と設定可能なエージェントセッションを起動し、親セッションがオーケストレーション。
1 skill
Claude Code の rules / CLAUDE.md を Codex が読める AGENTS.md にネスト生成する汎用プラグイン。
1 command
Expose browser-control's MCP server for controlling local browsers through CDP and WebDriver BiDi.
1 MCP server
Install and operate the RAR catalog, reversible Toasted skills, manual platform exports, external-AI callbacks, and a local RAPP Brainstem.
1 skill
Drive a running React Native or Expo dev build directly: see the screen, fill forms, press buttons, seed data, flip flags, navigate, mock the network, fake realtime messages and undo it all, in milliseconds per call.
1 skill
Evidence-first engineering protocol for AI coding agents. A bundled tool runs the checks and names the result, so the model never grades its own work.
1 skill
AWS Knowledge MCP for documentation search and recommendations
1 MCP server
gopls-lazy LSP server for Go (lazy workspace proxy for large monorepos)
LSP
golance LSP server for Go (memory-bounded LSP server for large monorepos, successor to gopls-lazy)
LSP
Use when designing or reviewing automation architecture for GitHub Actions, Argo Workflows, or Argo Events — choosing an idempotency or work-avoidance strategy, wiring GitHub App authentication, or picking an error-handling or hub-and-spoke pattern.
1 skill