Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 377,998 indexed, measured the same four ways as everything else here.
Core conventions and rules for Playwright E2E testing with TypeScript. Covers project structure, naming conventions, selector strategy, authentication, navigation, environment configuration, test independence, and parallelism. Automatically loaded when writing or modifying E2E tests. Use when: generating E2E tests…
End-to-end FeatBit experimentation workflow with Bayesian A/B/n analysis. Use when shaping product intent, writing a hypothesis, defining feature flags and rollout strategy, designing metrics and instrumentation, creating or analyzing experiment runs, deciding continue/pause/rollback/inconclusive, or capturing…
Move fast AND rigorously through the full AI/ML research loop: framing a testable hypothesis, reviewing the literature, reproducing a baseline, designing leak-free experiments, tracking runs, analyzing results honestly, and writing up. Use this whenever the user is doing machine-learning or AI research — reading or…
Use this skill for static malware analysis and reverse engineering of suspicious binaries, Android APKs, Office documents, web payloads, scripts, source-code droppers, and multi-stage chains across Linux, macOS, and Windows. It guides Codex through safe lab workflow, tool discovery with per-install authorization…
Provides ProcessWire CLI and migration workflows for sites using the AgentTools module. Use when querying the ProcessWire API, making repeatable site changes, or transferring changes across environments.
Search Google's Knowledge Graph for structured information about real-world entities. Runs locally from the @houtini/google-knowledge-graph-mcp npm package. Needs 1 environment variable to run.
★not rated 12▲
+1 2d agoA
tokens not measured
originalMIT
A learning tool for people who build products with AI. It explains a project’s architecture and principles, creates reports and quizzes, and tracks what the builder has learned.
Lightweight Claude Code harness: 5 security hooks + a discover -> spec -> craft -> vet/exercise pipeline. Zero dependencies; runs on vanilla Claude Code.
★not rated 12 1mo agoA
tokens not measured
originalMIT
A workflow for creating Agent Skills that work with tools such as Claude Code, Codex, and Cursor. It creates SKILL.md files, supporting references, trigger examples, validation checks, and installation files.
Run a single prompt across multiple LLMs in parallel via OpenRouter, then synthesize their responses into one answer with a judge model. Use when the user wants multi-model fusion, ensemble LLM queries, parallel model comparison, or a second opinion across providers.
Interact with the TitanClip control plane API to manage tasks, coordinate with other agents, and follow company governance. Use when you need to check assignments, update task status, delegate work, post comments, set up or manage routines (recurring scheduled tasks), or call any TitanClip API endpoint. Do NOT use for…
Find academic papers and read them — searches real scholarly databases for prior work on a topic, then resolves and deep-reads the open-access PDF of any paper you pick. Use this skill WHENEVER the user wants to discover literature or read a study: "find recent papers on X", "what does the research say about Y", "find…
MCP server "claude-code-explorer" as configured in jiangyurong609/claude-code-any. Runs mcp-server/dist/index.js with node. Needs 1 environment variable to run.
Use Marlin-2B as eyes on a video — describe what's in a clip (caption) or locate when something happens (find). Use whenever the user asks what's in a video, to describe or summarize a clip, to find when/where an event occurs, or to get a timestamp for a moment. Runs locally on Apple Silicon (MLX), free, no API key…
Find duplicate functions and eliminate them so they stay gone. Triage tl dupes output by tier, apply the right consolidation pattern, and lock the win with a duplication-ratchet test. Use when asked to dedupe, remove duplication, consolidate copy-paste, clean up repeated helpers, or act on tl dupes output.
README-ROAST — Your README is lying. 8 savage personas roast your project's README with a Honesty Score, 3-5 punchy observations, a tweet-ready one-liner, and a shareable badge. Short. Funny. Accurate. Invoke with /readme-roast on any repo. Screenshot the output. Share it. Let the badge spread.
A Chinese-language writing workflow made up of six specialist roles for planning, research, drafting, review, style, and fact-checking. It covers many types of content, including articles, reports, speeches, and social-media posts.
AI-powered visual collaboration with Excalidraw for Claude Code.
★not rated 12 7mo agoA
tokens not measured
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: