All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 433,751 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.
CYC2002tommy/Deep-Research-Agent
Skill Claude CodeCodex
Scientific literature pipeline on Scopus, Exa, OpenAlex, Semantic Scholar and AnySearch: map a field (themes, foundational papers, research groups, gaps), find verbatim gap quotes and draft a positioning narrative for an Introduction or proposal, build a course reading list from a syllabus, or run the full manuscript…
Skill Claude Code
Implements an approved spec. Validates that the state means "Approved" (in any language), creates a git branch named after the spec, switches to it, and starts the implementation step by step with pauses to review diffs.
Agent Claude Code needs its repo
Game artist. Generates and processes visual assets, registers them in manifest.json.
Plugin Claude Code
Bundles 3 skills, 1 hook · 189 tokens together
Produce triager-grade YesWeHack reports instead of AI slop: always-on drafting discipline plus three on-demand skills (write, triage, gotchas).
Plugin Claude Code
Bundles 25 skills · 2,164 tokens together
25 marketing skills for technical marketers and founders: CRO, copywriting, SEO, paid ads, pricing strategy, referral programs, and more.
Skill Claude CodeCodex
Use when Python code must turn files, folders, URLs, zip archives or GitHub repos (PDF, Word, Excel, PowerPoint, CSV, HTML, notebooks, images, audio) into text and images for a language model, with the attachments library (from attachments import att). Covers installing 1.0 (not the old 0.25 API that models remember)…
Skill Claude CodeCodex
Use when building, extending or upgrading an agent on the yoagent Rust crate. Maps each job (tools, policies, verifiers, budgets, sub-agents, plugins from other ecosystems, retries, structured output, tests) to the yoagent feature for it, with tips, pitfalls and what changed per version.
Cursor rule Cursor
Auth architecture, middleware chain, and auth-specific coding standards.
tachikomared/character-animation-creator-skill
Skill Codex
Create game-ready fixed-cell pixel-art character spritesheets from text concepts, reference images, or existing character art. Use when Codex needs to design, generate, clean up, validate, and package 2D game characters with native 32x32, 64x64, or 128x128 cells; 4-way or 8-way directions; idle, walk/run, jump…
hassancs91/claude-youtube-editor
Skill Claude Code
Step 1 of the AI Video Editor pipeline — turn raw talking-head footage into a clean master cut. Use when the user wants to "clean cut", "cut the raw footage", "remove filler / dead air / bad takes", "tighten the pacing", produce cuts.json, run the cut editor, or render a cleaned preview/master for a video-N project in…
Skill Codex
Discover, compare, audit, and safely install reusable AI Agent Skills with OpenAgentSkill. Use whenever an agent needs a capability it does not already have, must compare Skill alternatives, or needs evidence before installing third-party instructions.
Skill Claude CodeCodex
Tool choices, workflows, and MAXScript pitfalls for controlling 3ds Max via MCP.
Skill Claude CodeCodex
Use Kuri's HTTP server as a session-based browser skill. Prefer X-Kuri-Session with /tab/new, /tab/current, /page/info, /snapshot?filter=interactive&format=compact, and /action for low-token agent loops. Use when an agent needs to browse, read, click, or fill through Kuri without managing raw CDP details.
Plugin Claude Code
Bundles 24 skills · 2,458 tokens together
A Claude Code plugin for Japanese tax filing. It supports employees with side businesses, including business-income, blue-return, income-tax, and consumption-tax filings.
MCP server Claude CodeCodexCursor +2
Geospatial intelligence with Mapbox APIs like geocoding, POI search, directions, isochrones, etc. Runs locally from the @mapbox/mcp-server npm package. Needs 1 environment variable to run.
Skill Claude CodeCodex
Run dev servers and terminal commands that AI agents can read, wait on, and type into. Wrap any command in a named background session. Humans get auto-attached; agents get a session they can inspect with read, snapshot, wait, and type.
giuseppe-trisciuoglio/developer-kit
Plugin Claude Code
Bundles 52 skills, 11 commands, 9 agents · 4,655 tokens together
Comprehensive Java development toolkit with Spring Boot, testing, LangChain4J, and AWS integration.
Skill Claude CodeCodex
Run a full empirical / causal analysis in Python with StatsPAI (import statspai as sp) — applied-economics style (DID / RD / IV / synthetic control / DML / matching with estimating equation, identifying assumption, Table 1, main table, event-study figure, robustness gauntlet, Word / Excel / LaTeX export), epidemiology…
CosmoBlk/email-marketing-bible
Plugin Claude Code
Bundles 1 skill · 195 tokens together
Email marketing operating manual for AI agents, with hard send-safety gates: campaigns, newsletters and flows, deliverability and DNS, switching ESPs, compliance, anti-slop copy, email design and benchmarks, with any ESP through MCP or an API.
MCP server Claude CodeCodexCursor +2
MCP server "depyler" as configured in paiml/depyler. Launched with depyler agent start --foreground --port 3000. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server "chainlink-safe-fetch" as configured in dollspace-gay/chainlink. Runs .claude/mcp/safe-fetch-server.py with python.
Skill Claude CodeCodex
Use for HarmonyOS NEXT development help and local DevEco automation. Covers ArkTS/ArkUI/NDK API lookup, offline guide navigation, DevEco Studio and HarmonyOS Emulator tasks, hdc/uitest/aa/bm/hilog/hidumper diagnostics, ArkWeb/WebView DevTools and CDP evidence, and private DevEco interfaces such as CodeGenie, MCP…
Skill Claude CodeCodex needs its repo
Multi-dimensional LLM council review of an open PR (default) or a local feature branch (§ 8 branch mode, invoked via /gflow:branch-review). Five baseline dimensions (correctness, quality, security, tests, memory-hygiene) plus adaptive dimensions per surface (transports / data / CLI / docs / auth / BDD / scripts /…
Skill Claude CodeCodex
MemMesh TypeScript SDK reference (@thinkfleet/memory-sdk) for the hosted platform at app.memmesh.ai. Covers the ThinkFleetMemory client — observe / search / list, the predict + lattice prediction surface, closed-loop learning (recordDecision / recordOutcome), emergent behavior discovery, and the health / financial…
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: