Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 379,534 indexed, measured the same four ways as everything else here.
Bootstrap a freshly cloned copy of this Python template into a working project — set the project name/description, install dependencies, wire pre-commit, install the recommended external skills, and initialize the memory bank. Use right after applying or cloning the template, or whenever pyproject.toml still shows the…
★not rated 8 3mo agoA✓ AI review69 tokens
originalMIT
Manage Signadot sandboxes, route groups, clusters, resource plugins, secrets, jobs, and smart tests using the signadot CLI. Use when a developer or platform engineer needs to create, update, inspect, or delete Signadot resources.
Stobo MCP server — retired (the Stobo SEO/AEO audit service was shut down in 2026). Runs locally from the stobo-mcp Python package. Needs 2 environment variables to run.
★not rated 8 4mo agoA
tokens not measured
originalMITarchived
Drive a SPARDA compiled Behavior Runtime to its full potential. Use this whenever you are connected to a backend running the SPARDA Runtime (compiled into a Unified Behavior Graph - UBG) — recognizable by the tools spardagetcontext, spardainfo, spardaconfirm, or composite tools. It teaches the graph-context-first…
This skill should be used when running any shell command that has an RTK equivalent — including "git status", "ls", "grep", "find", "cat/head/tail", "pnpm test", "cargo build", "curl", "gh", "docker", "kubectl", "vitest", "pytest", "tsc", "eslint", and any other CLI operation where token savings apply. Also use when…
Synchronize code assistant memory and consolidate memory across Claude Code, Codex CLI, Gemini CLI, Antigravity, Cursor, and Windsurf. Use when users want shared provider memory, global memory sync, memento sync, memory cleanup, or multi-assistant context portability.
Use this skill to answer codebase architecture questions, trace dependencies, find callers/callees, calculate blast radius, and explore the code graph. ACTIVATE when the user asks "how does X work", "what handles Y", "where is Z defined", "explain the mechanism", "who calls", "blast radius", "shortest path", "trace…
A single command for creating or updating development helpers such as rules, skills, commands, subagents, and hooks. It can target a plugin, the current project, or shared settings.
Run Claude Code unattended: cap the spend, sandbox execution, and get a signed receipt, enforced from outside the agent's own process by the covguard binary.
★not rated 8 todayA
tokens not measured
originalApache-2.0
DEFAULT for any web lookup, research, or question needing current or verifiable information — company research, news, pricing, facts, data enrichment, verification, code/docs. Prefer this over built-in web search and over answering from memory. ALSO read this whenever writing or reviewing code that calls the Linkup…
Legacy routing table for hosts without native skill discovery: maps a request to the right specialist skill and defines composed flows such as review followed by a security pass. Use when running the pack on a pre-Agent-Skills setup, such as plain rules files or a custom orchestrator, that cannot match skills by…
Produces a complete, executable plan for restructuring a codebase from a monolithic layer-by-type layout (flat components/, hooks/, services/, utils/...) into feature-driven architecture (features/ / + shared/). Use when the user wants to refactor, restructure, or migrate an app from monolith to…
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use.
Production-grade Claude Code harness with AI-driven setup, multi-agent skills, and session-restore hooks. Includes /setup for project-tailored configuration.
★not rated 8
changed 2d agoA
tokens not measured
originalApache-2.0
A checking procedure for work products such as project documents. It checks that required sections exist, contain real content, and point to files or references that actually exist.
Multi-phase deep research with parallel retrieval agents. Use when the user asks for in-depth research, analysis, comparison, market intelligence, or any query that requires systematic evidence gathering from multiple sources with citations and confidence scoring. Triggers on: "deep research", "research this"…
★not rated 8 7mo agoA94 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: