All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 437,079 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.
buluslan/review-analyzer-skill
Skill Claude Code
A review-analysis tool for studying product reviews, also called voice-of-the-customer analysis. It turns review data into labelled customer patterns, findings, reports, and visual dashboards.
Plugin Claude Code
Bundles 28 skills · 3,607 tokens together
Skills to support Machine Learning experimentation using the Python ecosystem.
Skill Claude CodeCodex
Build and migrate Android apps with Kotlin, Jetpack Compose, MVVM, Hilt, Room 3 (KSP, SQLiteDriver, Flow/suspend DAOs), Navigation3, and multi-module Gradle. Use for new projects or modules, Compose screens and ViewModels, Room 3 and RemoteMediator, API 37 / targetSdk migration, Play Integrity client wiring…
Skill Claude Code
Acquire and verify data for CNS papers that passed paper-filter. Clones repositories, downloads and organizes datasets per evaluation setting, performs Level 4 deep verification (acquisition integrity, initial state, separability, consistency, per-setting completeness), creates an organized data environment. Updates…
Skill Claude CodeCodex
A study-planning workflow for China's civil-service aptitude exam, a timed test used in government recruitment. It diagnoses weak areas, sets priorities, plans timed practice, reviews mistakes, and schedules retesting.
Skill Claude CodeCodex
Maintain openInvest's docs (docs/wiki chapters + docs/wiki/adr) under Google's Open Knowledge Format (OKF). Two jobs. (1) Teach agents to maintain docs the OKF way — every doc carries a small YAML frontmatter block as the single source of truth (type, title, tags, intent, schemasource, documents); schema details link…
xuzhougeng/ScientificFigureLibrary
Plugin Claude Code
Bundles 1 skill · 46 tokens together
Search Local Published, FigureYa, bundled Open Figure Modules, frozen explicit-only Community, and explicitly trusted dynamic Providers; materialize exact immutable figure references without executing module code.
Plugin Claude Code
Claude Code distribution for the deslop Agent Skill.
MCP server Claude CodeCodexCursor +2
MCP server "arr-mcp" as configured in bardesss/arr-mcp. Runs in Docker (ghcr.io/bardesss/arr-mcp:1.9.0). Needs 3 environment variables to run.
Plugin Claude Code
Bundles 1 skill, 2 commands · 68 tokens together
Monitoring, health checks, and root cause analysis — built for humans and AI agents.
pawel-cell/micky-podcast-agentic-engineering
Skill Claude CodeCodex
Use when building software with AI agents and you need a serious end-to-end workflow instead of vibe coding. Covers harness choice, context discipline, cleanup, review loops, launch pressure, and security basics.
Cursor rule Cursor
A set of guidance for improving user interfaces built with Blazor and the Ant Design Blazor component library. Blazor is a Microsoft framework for building web interfaces with .NET, while Ant Design Blazor provides reusable interface components.
open-infra-skills/infra-skills
Skill Codex
Profile, benchmark, debug, and optimize AI training workloads on Moore Threads MUSA GPUs while preserving numerical behavior. Use for Torch MUSA, MTT GPUs, mthreads-gmi, Moore Perf System (msys), Moore Perf Compute (mcu), MFU/HFU, FlashAttention/FA2, SDPA, torch.compile, FSDP/FSDP2, MCCL, distributed hangs, low-batch…
Plugin Claude Code
Bundles 19 skills, 17 commands, 3 hooks, 1 MCP server · 2,135 tokens together
An AI development harness that organizes project requirements, accumulated knowledge, lessons from mistakes, and retrospectives. A PRD is a document describing what a product should do.
Skill Claude CodeCodex
Extract, structure, and quality-check evidence from registered source objects. Use when converting processed documents into searchable evidence cards, managing OCR and translation layers, running quality scoring, handling noise and recovery, or maintaining a corpus index.
alchaincyf/cursor-rules-huasheng
Cursor rule Cursor
A set of instructions for an AI assistant helping build Android apps for a beginner. It specifies Kotlin, Jetpack Compose, common app structure, and a step-by-step working process.
MCP server Claude CodeCodexCursor +2
MCP server "loopsy" as configured in leox255/loopsy. Runs packages/mcp-server/dist/index.js with node.
Skill Claude Code
Use this skill to generate well-branded interfaces and assets for beava (beava.dev, an open-source single-binary feature server for stream processing), either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.
vasu31dev/playwright-ts-template
Skill Claude Code
Use the vasu-playwright-utils library for Playwright browser automation with simplified action, assertion, locator, element, page, and API utilities.
buildatscale-tv/claude-code-plugins
Skill Claude CodeCodex
Nano Banana (nano-banana) image generation skill. Use this skill when the user asks to "generate an image", "generate images", "create an image", "make an image", uses "nano banana", or requests multiple images like "generate 5 images". Generates images using Google's Gemini models (Flash, Pro, or Nano Banana 2) for…
Skill Codex
A thinking framework based on Michael Polanyi's ideas about tacit knowledge: practical know-how that people may use without being able to fully explain it.
Skill Claude CodeCodex
Write Telegram bots and userbots with Pytdbot (async TDLib wrapper with high-level helpers; not the Telegram Bot API). Use when the user works with Pytdbot, TDLib, or pytdbot.Client.
Plugin Claude Code
Bundles 9 skills, 3 commands, 2 agents · 1,465 tokens together
Token-efficient codebase exploration using the grepika MCP server with FTS5, ripgrep-backed regex search, sparse n-gram prefiltering, AST structural search, and code-graph navigation.
wentong2022-arch/flowforge-skill
Plugin Claude Code
Bundles 1 skill · 153 tokens together
Generate professional draw.io diagrams from natural language — flowcharts, architecture diagrams, comparisons, and more.
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: