Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
chatmaterials/lammps-workflows
Skill Codex
Use when the task involves LAMMPS atomistic simulation workflows, including input script creation, minimize, NVT, NPT, and restart setups, force-field and data-file checks, log.lammps review, restart handling, and scheduler scripts.
taurus42119-stack/godkiller-mcp
Skill Claude CodeCodex
Run a prompt or skill in this session on a recurring or variable interval (e.g. /loop 5m /foo).
nightquill/rpgmaker-agent-skills
Skill Claude CodeCodex needs its repo
Use this skill when working with any RPG Maker MV or MZ project. Triggers: presence of a Game.rpgproject or Game.rmmzproject manifest, data/.json files named Actors.json/Skills.json/Items.json/Enemies.json/MapInfos.json, or when the user mentions RPG Maker, RPGMaker, MV, MZ, JRPG development, or narrative RPG in a…
Forgemind-git/agentic-command-center
Skill Claude CodeCodex
An advisory blueprint for planning your own AI command center — one chat or voice interface that runs your whole business by routing to internal systems you own. Guidance and architecture only; it explains the four phases (own your systems, connect your tools, expose them over MCP, unify under one command layer) but…
dingshuxin353/design-broll-animation
Skill Codex
Analyze SRT, TXT, or Markdown transcripts to identify AI concept-animation B-roll opportunities, pause for confirmation, write self-contained Vox or halftone-sticker text-to-video prompts with optional A-roll chroma-key transition handles, and optionally hand confirmed prompts to an installed Gemini Omni or MiniMax-H3…
yusenthebot/stanford-ai-agent-skill
Skill Claude CodeCodex
Use when designing, debugging, training, researching, or evaluating an AI agent and the decision concerns one of seven areas: minimum agent loop, inference-time compute allocation, verifier or LLM-judge trust, long-horizon dependency and rollback control, verified-trajectory post-training, evidence-gap research, or…
Skill Claude CodeCodex
Invoke OpenCode CLI as a sub-agent to leverage alternative AI models (GPT-5.x, Codex, local models) for code implementation, review, debugging, research, and second opinions. Use when the user asks to "use opencode", "get a second opinion from GPT/Codex", "implement with opencode", "review with opencode", "let…
Skill Claude Code
Prompt recipes for Grok image/video generation from Codex (OG images, README banners, launch clips).
Skill Claude CodeCodex
A cryptocurrency analysis guide for investigating why digital-asset prices move. It examines market, funding, macroeconomic, and technical evidence, including a method called CZSC for identifying chart structures, divergences, and possible entry patterns.
Skill Claude CodeCodex
Prevent mixed-responsibility modules and uncontrolled file growth. Use before adding behavior to a large or mixed-responsibility file, or when splitting one. Do not use for small, local edits to cohesive modules.
Agentchengfeng/paper-reading-skills
Skill Codex
A set of instructions for reading research papers, technical reports, arXiv PDFs, and related code repositories. arXiv is a public website where researchers share scientific papers, often before formal publication.
Skill Claude Code
A staged development process that takes a project from context and idea through planning, risk checks, design contracts, implementation, audit, feedback and release. Each stage produces files in docs/pipeline/ that serve as the project record.
b1rdmania/claude-premortem-skill
Skill Claude CodeCodex
Run a premortem on any plan, launch, product, hire, strategy, or decision. Imagines it failed 6 months from now, works backward to find every reason why, then produces a revised plan. Triggers include "premortem this", "premortem my", "what could kill this", "stress test this plan", "find the blind spots", "poke holes…
Skill Claude CodeCodex
A skill that researches a person or vague need, extracts a way of thinking, and turns it into a reusable advisor skill.
sonlovinbot/coachio-may-starter
Skill Claude CodeCodex
Phân tích viral + viết bài Facebook viral tiếng Việt (cho thị trường VN, target CEO/marketer mảng AI/tech) từ một link (X/IG/FB/TikTok/web) hoặc một chủ đề. Dùng khi user muốn "viết lại", "viết content", "làm bài Facebook", "viết viral", "repurpose", "dịch + viết lại" từ link hoặc topic. Khi input là link, LẤY DỮ LIỆU…
Skill Claude CodeCodex
Use for VRChat friend queries (online status, who played with whom, activity timelines, online patterns) and VRChat social actions (boop, invite, join world, friend management, group operations, image uploads) via the vrc-monitor MCP server on port 8799.
6missedcalls/personal-finance-skill
Skill Claude CodeCodex
Personal finance management skill providing 75 tools across 7 extensions for bank account aggregation (Plaid), brokerage trading (Alpaca), portfolio monitoring (IBKR), tax optimization, market intelligence (Finnhub, SEC EDGAR, FRED, BLS, Alpha Vantage), social sentiment (StockTwits, X/Twitter, Quiver), and financial…
Skill Claude CodeCodex
Foundational data-discipline skill for econometrics work in any language. Enforces the discipline that every other data, analysis, and writing skill depends on: define the unit of analysis before anything else; treat IDs as a contract; merge with explicit cardinality and validation; never silently change the unit of…
Skill Claude CodeCodex
Two-circuit backup & GitHub sync system for Home Assistant. Circuit 1 — real git inside /config with a deploy key, a pre-commit secret scanner and meaningful commits; Circuit 2 — full encrypted HA backups in GitHub Releases. Use EVERY time the task involves: backing up Home Assistant, syncing its config, git in…
Skill Codex
Build rich, scroll-controlled real-time Three.js experiences as one persistent 3D world whose camera, lighting, atmosphere, materials, objects, DOM story, and interactions evolve across authored chapters. Use for 3D scrollytelling, scroll-driven WebGL worlds, camera journeys, interactive portfolios, product stories…
Skill Claude CodeCodex needs its repo
A workflow that turns a natural-language description into an editable `.pbd` patent block diagram, renders it in the diagram editor, checks the image, and exports a PNG.
Skill Claude Code
Guides creation or update of a SKILL.md: chooses the right frontmatter fields (description vs whentouse, argument-hint, model, effort, allowed-tools, paths, disable-model-invocation, etc.), runs three pressure tests, and follows the approval flow before writing.
Impertio-Studio/Three.js-Claude-Skill-Package
Skill Claude CodeCodex
Use when optimizing 3D models for web delivery: reducing file size, compressing meshes, optimizing textures, or generating LOD. Provides a complete GLTF optimization pipeline using Draco, KTX2, mesh simplification, and gltf-transform. Keywords: optimize model, reduce file size, Draco compression, KTX2, gltf-transform…
Skill Claude Code
Walk a user through setting up Beadhive on this machine without them reading the docs: probe what is already installed, choose ONE install route (the managed nix path, or PyPI as the labelled fallback), install and verify bh, then configure it — bh config init, MCP wiring, the harness plugin, Factory HQ, and a first…
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: