All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 419,049 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.
Skill Claude CodeCodex
Persistent cross-session memory via Honcho — recall what you know about the user before working, and save durable insights after.
Skill Claude CodeCodex
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Skill Claude CodeCodex
An investment-analysis perspective based on Zettaranc’s published trading experience, mental models, heuristics, and communication style. It is intended to analyse markets and trading decisions from that stated viewpoint.
Skill Claude CodeCodex
Build a two-tier conversation benchmark for a fastWorkflow workflow: short single-errand conversations that act as unit tests and reusable blocks, then long real-world tasks of 20-100 steps composed from those blocks. Covers turn and conversation structure, seeding objects with enough structure to sustain a chain…
Skill Claude CodeCodex
Deep, critical paper-reading workflow that produces a structured reading note. Use when the user wants to read, understand, summarize, break down, or take notes on a single research paper. English triggers: "read this paper", "read the paper", "paper reading", "paper notes", "deeply read", "critically read"…
Cursor rule Cursor needs its repo
🚨 ABSOLUTELY FORBIDDEN: Direct python/python3 execution.
Plugin Claude Code
Bundles 23 skills, 18 commands, 1 hook, 1 MCP server · 1,014 tokens together
Compound engineering with persistent memory and multi-agent workflows based on beads. 30 specialized agents, 28 commands, 15 skills, and automatic knowledge capture/recall.
Plugin Claude Code
Bundles 6 skills, 3 agents · 213 tokens together
Neuroscience-inspired long-term memory for Claude Code — auto-captures and recalls cross-session context.
Plugin Claude Code
Bundles 18 skills, 1 MCP server · 3,947 tokens together
Public JoomPulse agent skills for product research and marketplace workflows.
EmbrasureAI/spark-observability-skills
Skill Claude CodeCodex
Diagnose slow, expensive, or regressed Apache Spark and PySpark applications by comparing runtime evidence against a healthy run. Use for long stages, stragglers, skew, shuffle, spill, garbage collection, poor parallelism, small files, slow scans, scheduler delay, executor imbalance, and unexplained compute-cost…
Skill Claude CodeCodex
Use this skill to start or resume the VeriFlow RTL hardware design pipeline (architect to synth). Trigger this when the user asks to "run the RTL flow", "design hardware", or "start the pipeline". Pass the project directory path as the argument. Optional: append --benchmark to auto-generate a benchmark report after…
Skill Claude Code
Create Book note with knowledge compounding through spawned Concept/Pattern/Theme nodes.
Skill Claude CodeCodex
Prepare Solana/Rust projects for a security audit — test coverage analysis, Rust doc-comment checks, code hygiene sweeps, dependency health verification, compute-unit optimization tips, and best-practice enforcement. Supports both Anchor-based and native solanaprogram Rust programs. Generates a scored Audit Readiness…
Skill Claude CodeCodex
A tool for creating browser-based presentations as single HTML files, or converting PowerPoint files into them. It includes bilingual English and Chinese support and a library of visual styles.
lake121380-source/lakejobai-job-radar
Skill Claude CodeCodex
A command-line job-search tool for BOSS Zhipin, a Chinese recruitment website, with an interface designed for AI agents.
xyzxyq/docx-course-report-writer
Skill Codex
Use when Codex handles Chinese coursework/report DOCX deliverables, including experiment reports, course papers, literature reviews, reading reports, report conversion, report repair, figure-heavy Word reports, and submission-ready report packages.
Hook Claude Code
One of 5 in settings.json
Runs when you submit a prompt, before the agent sees it, running an inline shell check. From bashiraziz/llm-wiki-template.
Cursor rule Cursor
When the user types /discovery or requests quality analysis, code audit, or issue detection.
Plugin Claude Code
Bundles 1 skill, 1 hook · 74 tokens together
Ecommerce data analytics toolkit for D2C stores.
Skill Claude Code
Local SEO audit and optimization for Google Business Profile, Google Maps, and Gemini Ask Maps. Covers GBP completeness, NAP consistency, review strategy, local schema, competitor benchmarking, GeoGrid visibility, multi-location, AI Local Pack readiness, and GBP suspension prevention. Use when user says "local SEO"…
Skill Claude Code
Generate a related-work section, find prior literature, or rank candidate citations for an academic paper. Uses LLM-driven debate ranking over Semantic Scholar / arXiv / OpenAlex search, with optional citation-graph BFS expansion (deep research). Use when the user provides a paper (PDF or markdown) and asks for…
Plugin Claude Code
Bundles 8 skills, 18 commands, 2 agents · 952 tokens together
Evidence-based presentation creation with Slidev, enforced design guardrails, and multi-platform diagrams.
Skill Codex
Create, update, list, and safely maintain evidence-bounded graduate-advisor Skills from comments, meeting notes, chat logs, documents, and user corrections. Use when the user asks to create or evolve a supervisor/advisor Skill, distill a mentor's working style, run /create-supervisor, /update-supervisor…
Skill Claude CodeCodex
Three.js performance optimization and best practices guidelines. Use when writing, reviewing, or optimizing Three.js code. Triggers on tasks involving 3D scenes, WebGL/WebGPU rendering, geometries, materials, textures, lighting, shaders, or TSL.
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: