All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 435,959 of them, each with its token cost per session, a security scan with the line that triggered it, and whether it is the original or one of the copies.
Norman-bury/research-writing-skill
Plugin Claude Code
Bundles 20 skills, 1 hook · 499 tokens together
A Chinese-language academic writing assistant for planning and drafting research papers, theses, and literature reviews.
Skill Claude CodeCodex
Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.
sanjeed5/awesome-cursor-rules-mdc
Cursor rule Cursor
This guide provides definitive best practices for Android SDK development in Java, focusing on modern architecture, Jetpack libraries, performance, security, and testing.
Skill Claude CodeCodex
A Xiaohongshu assistant for checking accounts, finding posts, publishing images or videos, and interacting with content on Xiaohongshu, a Chinese social-media platform.
Skill Claude CodeCodex
A pipeline for turning generated 2D game-character images into transparent sprite sheets, which store animation frames for a game.
Cursor rule Cursor
Use when performing browser-based testing, visual verification, accessibility checks, or performance profiling using the browser MCP.
AIScientists-Dev/academic-humanizer
Skill Claude Code
Improve the clarity and voice of AI-assisted academic writing (papers, theses, rebuttals) and funding proposals (NSF Project Summary/Description, NIH Specific Aims): preserve scholarly conventions, match claims to evidence (and, for proposals, claims to feasibility), and match the author's own voice. It never changes…
wesammustafa/Claude-Code-Everything-You-Need-to-Know
Skill Claude Code
Finds the root cause of a bug, failure or recurring problem by asking "why" until the answer is a cause you can fix. Use when the user asks why something keeps happening, or wants the root cause rather than a quick fix.
Skill Claude CodeCodex
Use tuicr's review CLI to read and add comments in active TUI review sessions, and launch tuicr in cmux, Rex, tmux, Zellij, or Herdr when a user needs an interactive review pane.
Command Claude Code
Generate a targeted test plan for the current task.
Skill Claude Code needs its repo ✓ vendor
Render a pre-extracted paper's structured 9-section spec (paperspec.md) into a single-page HTML academic poster, fit the layout to the page via an iterative measured-fill loop, and export it to print-ready PDF + PNG thumbnail. Requires the upstream paper2assets skill to have produced an output bundle with…
bergside/awesome-design-skills
Skill Claude CodeCodex
Conversational AI-first interface with minimal controls, clear outcomes, and delegated task flows for agentic workflows.
Plugin Claude Code
Bundles 1 skill · 0 tokens together
Find qualified B2B leads from inside Claude Code — drives the OpenOutreach CLI, reads the CSV it prints, and hands the rows to whatever you send with.
Skill Claude Code
A sample personal profile and memory record for a fictional 25-year-old product manager in Shanghai. It describes the person’s background, values, habits, and life events.
Plugin Claude Code
Bundles 26 skills, 1 agent, 2 hooks · 1,522 tokens together
Conversational derivation engine — generate agent-native memory architecture from natural conversation. 15 kernel primitives, 26 commands, 17 feature blocks, 3 presets.
Skill Claude CodeCodex ✓ vendor
Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for "are we spending too…
Skill Claude CodeCodex
Use the host-side agent-browser CLI for local browser smoke tests, screenshots, snapshots, and simple UI validation against forwarded localhost URLs.
Skill Claude CodeCodex
Create, improve, and evaluate agent skills (SKILL.md plus reference files). Use this skill whenever the user wants to build, scaffold, or design a new skill, improve or fix an existing skill that isn't working well, score or benchmark a skill's quality or run evals on it, or turn a repeated manual workflow into a…
Cursor rule Cursor
Git and PR guardrails for AI agents.
Skill Claude CodeCodex
How to use the @autoform/ packages with React Hook Form or TanStack Form to automatically generate React forms from Zod, Yup, or Joi schemas with any UI library (shadcn/ui, MUI, Mantine, Ant Design, Chakra UI). Use this skill whenever the user wants to create a form from a schema, select a form adapter, build forms…
Skill Claude Code needs its repo
Deep dive on Harbor trial results for tasks that use SWE-Bench-style F2P (FAILTOPASS) and P2P (PASSTOPASS) reference tests. Diagnoses why an agent failed and audits whether a failing task is genuinely hard or unfair (instruction-vs-verifier mismatch). Use when the user asks to analyze, debug, investigate, or deep dive…
Skill Claude CodeCodex
Build large HTML files in chunks when a single writefile exceeds stream limits.
Skill Claude CodeCodex
Guidance for installing and using Fli correctly as a CLI and MCP server. Use when: setting up Fli with pipx, running fli flight searches, configuring Claude Desktop with fli-mcp, using the HTTP MCP server, or troubleshooting Fli command availability and common usage mistakes.
taylorwilsdon/google_workspace_mcp
Plugin Claude Code
Bundles 1 skill · 117 tokens together
Complete Google Workspace integration -- Gmail, Drive, Calendar, Docs, Sheets, Slides, Forms, Tasks, Contacts, Chat, Apps Script, and Custom Search via MCP with workflow guidance.
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: