Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 375,099 indexed, measured the same four ways as everything else here.
Agent Claude Code
Use this agent when reviewing PRs that add server-side code (routes, server functions, Inngest functions, scripts, infra), code on a non-inspectable execution surface (agent sandbox, container readiness gate, cron worker), or code under plugins/ that executes on a customer's self-hosted CLI (observability layer 7), to…
ThomasVitale/agents-skills-oci-artifacts-spec
Skill Claude CodeCodex
A skill for managing pull requests in Forgejo repositories using the forgejo-cli. Supports creating, listing, viewing, merging, closing, and commenting on PRs.
Skill Claude CodeCodex
A Chinese-language editing workflow for writing or revising social-media scripts and spoken content. It gives structured, highly direct feedback using a small set of defined editorial voices.
Skill Claude CodeCodex
A scheduled, pre-market investment briefing for Hong Kong and United States stocks. A deterministic preparation step gathers data and an agent adds judgment, while a later step validates and publishes the result.
datumbrain/claude-code-privacy-guard
Plugin Claude Code
Privacy guard plugin for Claude Code - prevents PII and secrets from leaking into AI prompts.
Plugin Claude Code
Bundles 31 skills, 17 agents · 2,420 tokens together
Tells your coding agent when it is about to build something that already exists.
Skill Claude CodeCodex
Author an IMPL-BLIND spec-conformance oracle for an acceptance criterion the policy worklist (clad oracle --required) demands — an empty worklist means don't author unless the user explicitly asks. YOU spawn a blind sub-agent from a spec-only brief, then record it. Activate only when the connected project contains…
Plugin Claude Code
Use the Plonk macOS toolbox from Claude Code. Needs the app installed: brew install --cask ostapondo/plonk/plonk.
Skill Claude Code needs its repo
Help users add icons to their projects using the Unicon icon library. Unicon provides 19,000+ icons from Lucide, Phosphor, Hugeicons, Heroicons, Tabler, Feather, Remix, and Simple Icons. Use when adding icons to React, Vue, Svelte, or any web project; using the unicon CLI to search, get, or bundle icons; setting up…
MCP server Claude CodeCodexCursor +2
MCP server for managing Proxmox VE clusters through AI assistants. Runs locally from the mcp-proxmox Python package.
MCP server Claude CodeCodexCursor +2
Agent-first MCP server for WeChat Mini Program debugging & automation via WeChat DevTools. Runs locally from the @chaixueyuan/weapp-agent-mcp npm package. Needs 15 environment variables to run.
Skill Claude CodeCodex
Triage ABAP short dumps (ST22) — list recent dumps, group by root cause, read the dump chapters, pull the source at the termination point, and produce a prioritized report with a concrete fix suggestion per dump family. Use whenever the user mentions dumps, ST22, runtime errors, CX exceptions, "production crashed"…
Skill Claude CodeCodex
Review local code changes for concrete correctness, regression, security, and test gaps before shipping.
Skill Claude CodeCodex
Comprehensive, extraction-verified reference for Portfolio123 (P123), the systematic equity research platform: factor investing, stock screening, ranking systems, backtesting, and the REST API with the p123api Python wrapper. Use this skill whenever the user mentions Portfolio123, P123, p123api, P123 screens or screen…
PramodDutta/AdvancePlaywrightFramework1x
Skill Claude CodeCodex
Generate a Playwright Page Object (POM) class for the TTACart demo app (app.thetestingacademy.com/playwright/ttacart) by driving the live page and reading its real selectors. Use this whenever the user gives a TTACart page URL plus a flow to reach it and asks to "create a page object", "build the POM", "scaffold a…
Plugin Claude Code
Bundles 1 skill · 172 tokens together
Expert guidance for performance testing: planning, scripting, executing, and analyzing load/stress/soak/spike tests using JMeter, k6, Gatling, Locust, Artillery, NeoLoad, LoadRunner, OctoPerf, plus LLM inference benchmarking and SLO/capacity planning.
sponticelli/gamedev-claude-plugins
Plugin Claude Code
Bundles 6 commands, 6 agents · 211 tokens together
CI/CD pipelines, automated testing, build systems, deployment, and infrastructure for game development.
jbalbu01/sales-enablement-plugin
Plugin Claude Code
Bundles 18 skills, 7 commands, 10 MCP servers · 2,241 tokens together
A compounding GTM enablement engine with full MCP integration across all 21 skills, bundled with a custom Sales Intelligence MCP server (16 tools for Gong, ZoomInfo, Clay, LinkedIn). Pre-configured .mcp.json includes 9 remote connectors (HubSpot, Slack, MS365, Notion, Fireflies, Clay, ZoomInfo, Atlassian, Close) plus…
Plugin Claude Code
Bundles 39 skills, 1 hook · 3,013 tokens together
A Claude Code plugin for academic research — an opinionated set of role-based slash commands that walk a paper from idea to archive. Inspired by gstack.
raphysicst-create/korean-secondary-learning-map-mcp
MCP server Claude CodeCodexCursor +2
A locally run MCP server containing a Korean learning graph for the revised 2022 secondary-school curriculum, including achievement standards and transitions from middle to high school.
Plugin Claude Code
Plugin marketplace listing 14 plugins: prompt-engineering-skills, km, tofu-at, skills-2.0-upgrade, qwen3-tts-claude-skill.
MCP server Claude CodeCodexCursor +2
MCP server "waveform-mcp" as configured in ynivin/waveform-mcp. Runs locally from the waveform-mcp Python package.
Plugin Claude Code
Bundles 4 skills · 430 tokens together
GPU kernel knowledge-base, benchmarking, profiling, and optimization-loop skills for CUDA, Triton, CuTe DSL, CUTLASS, PyTorch, and Nsight Compute workflows.
Plugin Claude Code
Bundles 38 skills, 7 agents · 4,052 tokens together
New in 2.0.1: harness-doctor cadence promoted from prose to a SessionStart hook (30-day overdue check no longer silent); portability lint (BSD/GNU, zsh/bash pattern denylist) wired into pre-commit as the shell-layer sibling of the existing lints; branchclaim.sh gains an explicit warning that live-claim count is not a.
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: