Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 381,677 indexed, measured the same four ways as everything else here.
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct…
Guides a brand-new YNAB user through structuring their first budget — category-group pattern, right level of detail, and avoiding beginner traps. Use when a user says "I just signed up for YNAB, where do I start", "how should I set up categories", "how many categories should I have", "should I track every subscription…
UI mockups, dashboards, advanced interactivity, generative art, simulations, math visualizations, and design system rules for producing rich HTML widget output.
Creates cloud sandboxes and deploys apps with the lizard CLI. Sandboxes run untrusted or AI-generated code and give an agent its own computer: shell, files, HTTPS URLs for ports, a desktop and browser for computer use, and Claude Code or Codex in the cloud. Deploys cover apps, agents, workers and managed databases…
Manage resident peer agents: long-running monitors that live inside the pi session, tick on minute intervals, watch the main agent's work, and push findings back mid-turn. Use when the user asks to launch/stop/ask a peer, watcher, monitor, observer, sentinel, or auditor; wants standing review, drift/scope watching…
MCP server "gemini-bridge" as configured in Walkoud/gemini-browser-mcp. Runs C:/Users/volka/Desktop/gemini-pro-help-me/gemini-bridge/server.js with node.
Universal security-audit plugin and CLI engine for AI agents, built for defensive website, API, and codebase audits with professional Markdown, HTML, and PDF reports.
★not rated 4 3mo agoA
tokens not measured
originalMIT
An interactive setup skill that turns an empty Claude Code folder into an OpenClaw-style personal assistant. It asks about the assistant's identity, tone, communication channels, permissions, and memory, then creates the related instruction and memory files.
A workflow for producing AI-assisted film and video concepts with separate roles for directing, visual design, cinematography, brand review, and AI execution. It breaks a script into storyboards and develops the visual plan in stages.
Always active — coordinates with other Claude Code agents via intercom MCP. Automatically checks for messages, announces presence, and communicates to avoid conflicts. Triggers on ANY task start and periodically during work.
Build a 3D tower-defense game (creeps walk a lane, you place towers on a grid to stop them) on the Ship Shit engine, matching the FPS's neon-arena look. Use when adding a TD mode/game with an RTS-style angled or orthographic camera (NOT pointer-lock), raycast click-to-place on a grid, gold/build economy, waypoint…
Set up Microsoft.OpenTelemetry distro in a new .NET application. Use when adding observability to an agent, ASP.NET Core app, console app, or Agent Framework project. Covers package installation, exporter configuration, token resolver setup, baggage context, and instrumentation options.
Builds, fixes, styles, and composes UI with the Gravity UI design system — the React ecosystem of @gravity-ui/ packages (uikit, charts, table, navigation, date-components, icons, and more). Routes to the correct package when look-alikes exist, applies theming and required setup, and prevents invented component APIs.…
Plugin de Direito Previdenciario brasileiro para o advogado do segurado, do dependente e do beneficiario contra o INSS: RGPS, BPC/LOAS, acidentario, via administrativa (INSS e CRPS) e judicial ate o cumprimento de sentenca, com triagem de RPPS e previdencia complementar. 34 skills em 6 camadas e 7 scripts de calculo…
Darn — production-grade content gap analysis using DataForSEO MCP. Domain Mode (your site vs competitors) and Topic Mode (content plan from a seed keyword), multi-language (200+ markets).
★not rated 4 3mo agoA
tokens not measured
originalMIT
AG2 design system and brand guidelines. Applies consistent visual identity to all generated UI code, artifacts, and visual output for the AG2 multi-agent AI framework.
★not rated 4 6mo agoA
tokens not measured
originalApache-2.0
Run GitHub Actions workflow steps in parallel, replace repeated workflow configuration with YAML anchors, name every workflow, job, and step, and pin every action reference to a commit SHA on workflow edits.
Planning stage. Turn an approved concept into planning docs, but never one monolithic PRD. Produce a small overview file plus separate per-feature spec files, so that implementation reads only the spec it needs. Use when planning a build. This structure is cheaper to read, cheaper to edit, and cache-friendly compared…
★not rated 4 2mo agoA71 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: