Loading...
Loading...
Found 1,029 Skills
Persistent markdown files as working memory for complex tasks: plan, track progress, store findings. Use when tasks have 3+ phases, require research, span many tool calls, or risk context drift. Use for "plan", "break down", "track progress", "multi-step", or complex tasks. Do NOT use for simple lookups, single-file edits, or questions answerable in one response.
VRChat World SDK 3 scene setup and optimization guide. Use this skill when configuring VRChat world scenes, placing SDK components, setting up layers, optimizing performance, or uploading worlds. Covers VRC_SceneDescriptor, spawn points, VRC_Pickup, VRC_Station, VRC_Mirror, VRC_ObjectSync, VRC_CameraDolly, layer/collision matrix, baked lighting, Quest/Android limits, and upload workflow. SDK 3.7.1 - 3.10.2 coverage. Triggers on: VRChat world, VRC SDK, scene setup, VRC_SceneDescriptor, spawn point, VRC_Pickup, VRC_Station, VRC_ObjectSync, layer setup, optimization, Quest support, light baking, upload, FPS improvement. Related: Use unity-vrc-udon-sharp for UdonSharp C# coding.
Community registry of agent configurations for the AIBTC platform — browse reference configs for arc0btc, spark0btc, iris0btc, loom0btc, and forge0btc, or copy the template to bootstrap a new agent.
Audits a React SPA project against architecture rules. Use when asked to "review components", "check architecture", "audit this react project", "does this follow react rules", or "review my frontend structure".
Lavarage Protocol — leveraged trading on Solana for any SPL token. Open long/short positions on crypto, memecoins, RWAs (stocks like OPENAI, SPACEX), commodities (gold), and hundreds of other tokens with up to 12x leverage. Permissionless markets — if a token has a liquidity pool, it can be traded with leverage.
Orchestrates end-to-end software development using the addyosmani/agent-skills framework. Guides the user through define → plan → build → verify → review → ship phases, spawns subagents for each step, tracks state persistently, and never loses focus on workflow completion. Use when the user says "let's build X", "help me implement X", "walk me through X", or wants structured multi-phase dev guidance. Also triggers when a task is clearly non-trivial and would benefit from phased execution.
Philip Tetlock's Superforecasting framework applied to a business decision, investment thesis, or strategic question. Spawns a team of specialist agents — Calibrator, Decomposer, Updater, Devil's Advocate, Scorekeeper — who each apply a different piece of the superforecasting methodology. The lead synthesizes into a calibrated probability estimate with Brier-scoreable predictions, explicit base rates, and an accountability structure for keeping score over time. Use when the user says "tetlock this", "what's the probability", "how confident should I be", "forecast this", "calibrate this", proposes a business thesis and wants probabilistic stress-testing, or wants to apply superforecasting to a decision. Works standalone or after /munger.
Peter Thiel's Monopoly Creation framework applied to a business idea. Spawns a team of specialist agents — Monopoly Anatomist, Secret Hunter, Market Framer, Last Mover Analyst, Girardian — who each apply a distinct lens from Thiel's framework to evaluate whether a venture has genuine monopoly potential. The lead synthesizes into a verdict: does this company have a secret, a 10x advantage, a tiny domination-ready market, and a path to becoming the last mover in its category? Use when the user says "thiel this", "monopoly test", "zero to one analysis", "does this have monopoly potential", or proposes a venture and wants Thiel-style evaluation. Works standalone or after /office-hours and /munger.
Implement end-to-end Medallion Architecture (Bronze/Silver/Gold) lakehouse patterns in Microsoft Fabric using PySpark, Delta Lake, and Fabric Pipelines. Use when the user wants to: (1) design a Bronze/Silver/Gold data lakehouse, (2) set up multi-layer workspace with lakehouses for each tier, (3) build ingestion-to-analytics pipelines with data quality enforcement, (4) optimize Spark configurations per medallion layer, (5) orchestrate Bronze-to-Silver-to-Gold flows via notebooks. Triggers: "medallion architecture", "bronze silver gold", "lakehouse layers", "e2e data pipeline", "end-to-end lakehouse", "data lakehouse pattern", "multi-layer lakehouse", "build medallion", "setup medallion".
On task completion, pair "what failed first" with "what finally worked" and codify the should-have-known-it insight as an ast-grep rule, skill, or CLAUDE.md rule. Use after trial-and-error solutions to spare future-you (or another agent) the same trap. Trigger phrases: "codify today's lessons," "make it a skill," "drop it into lint."
Use when the user is doing AI/ML work in a scientific domain — biology, chemistry, physics, astronomy, climate, genomics, materials science, medicine, ecology, energy, conservation, engineering, mathematics, scientific reasoning, drug discovery, protein design, weather modeling, theorem proving, single-cell, PDE solving, or anything similar. Hugging Science (huggingscience.co) is a curated catalog of scientific datasets, models, blog posts, and interactive Spaces; the `hugging-science` org on Hugging Face hosts community datasets, models, and demo Spaces. This skill helps you discover the right resource AND actually use it — loading datasets via `datasets`, running models via `transformers` or the HF Inference API, calling Spaces like BoltzGen via `gradio_client`, and citing blog posts for methodology. Trigger this skill whenever a user mentions a scientific ML task, asks for "a dataset/model for X" where X is a scientific topic, wants to fine-tune on scientific data, asks about protein / molecule / genome / climate / materials / astronomy / pathology / weather ML, or needs AI tools for research — even if they never say "Hugging Science" explicitly. The catalog is purpose-built for LLM agents (it ships an `llms-full.txt`); prefer it over generic web search for these tasks.
Use when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` / `cuda.tile.tune` in code, `autotune` in filenames, or correctness/performance issues in autotuned CuTile kernels. Covers: tune-once/cache/launch pattern, per-architecture configs (sm80–sm120), parameter space design (tile sizes, occupancy, num_ctas), and 7 common pitfalls with solutions.