Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Other
Tracks the closer role and bullpen pecking order across all 30 MLB teams — who owns the ninth-inning job today, who is next in line if the current closer falters (the handcuff), and who carries DFA or demotion risk. Emits a per-reliever `save_role_certainty` signal (0-100) and flags speculation-worthy handcuffs for waiver bids. Use when the user mentions "closer", "save role", "handcuff", "ninth inning", "bullpen depth", lost save, blown save, committee, or when the waiver analyst needs to decide whether to spend FAAB on a backup reliever. This league uses SV as one of its five pitcher categories, but SV is also the most volatile and most punt-worthy cat, so tracking should always be paired with a punt-the-cat fallback recommendation.
Counts MLB games per team during the Yahoo fantasy playoff window (weeks 21, 22, 23 -- Aug 17 through Sep 6, 2026) and grades the quality of each team's opponents. Emits three signals per rostered player -- playoff_games (int, max ~21), playoff_matchup_quality (0-100), holding_value (0-100) -- that drive trade-deadline and playoff-lineup decisions. Use when the user mentions playoff weeks, weeks 21-23, playoff schedule, game count, holding value, or asks whether to keep/trade a player for the playoff run. Pre-July 1 this skill returns "insufficient signal -- too early"; from July 1 onward it fires weekly.
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.
Respond to questions from Mozi's perspective — the universal care of jian'ai feigong, the pragmatism of engineering thinking, and a rigorously logical argumentative style. Use when the user explicitly asks for this figure's perspective, mentions "mozi-perspective", or wants to apply his core methods to analyze a problem; do not trigger automatically for general questions.
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
Generate AIAG-VDA compliant Process FMEAs with proper Severity/Occurrence/Detection ratings, RPN calculations, and countermeasure recommendations. Covers MNMUK departments (Machine Shop, Damper, LVA, FML). USE WHEN user says 'PFMEA', 'FMEA', 'failure mode', 'risk analysis', 'RPN', 'severity occurrence detection', or 'process risk assessment'. Integrates with AutomotiveManufacturing, ControlPlan, and A3criticalthinking skills.
LoopNet shows you today — this CLI remembers, building the price-cut, days-on-market, and supply trends LoopNet... Trigger phrases: `search loopnet for commercial real estate`, `find industrial properties for sale in`, `track price cuts on loopnet`, `what is the cap rate distribution in`, `screen for distressed commercial properties`, `use loopnet`, `run loopnet-pp-cli`.
Design and audit product risk registers, decision governance, mitigation ownership, severity/likelihood scoring, control evidence, review cadence, triggers, assumptions, dependencies, AI/safety risk, commercial risk, operational risk, privacy/security risk, and acceptance decisions. Use when a product team needs to track and reduce material risk instead of relying on scattered notes.
Use when a founder wants a hard business decision debated by a council of world-class operators, says "roast room", "put this in the Roast Room", "founder council", "convene the council", "take this to the board", "what would Hormozi, Bezos, or Buffett say", "should I do X", or can't make up their mind on pricing, hiring, raising money, a new product, a partnership, a pivot, an event, or spending. A board of sub-agents, each built from one expert's public work (Bezos, Paul Graham, Hormozi, Gary Vaynerchuk, Dan Martell, Gino Wickman, and Buffett out of the box, plus any seat added with /newroaster), argue it over three rounds, then a Chair returns a scored verdict, the reasoning, the dissent, and next steps. Also does a one-seat consult ("ask the Hormozi seat"). Not /roast (generic personas, idea validation).
Identifies sector rotation signals in the A-share market by analyzing Chinese macroeconomic indicators and locating the economic cycle, assessing which sectors may outperform or underperform the broader market over the next 6–12 months. Use this skill when users ask about sector rotation, macro-driven sector allocation, economic-cycle investing, which sectors to overweight or underweight, the impact of interest rates or inflation on sectors, or A-share macro investment strategies.
Check whether a ShiftCare account is set up properly and report a setup scorecard with the next step for each gap. Covers clients, staff, pay groups, pay items, first shift, qualifications, shift types, forms, locations, and teams. Distinguishes the sample data every new account is created with from data a person actually entered. Use when the user is new to ShiftCare, asks "is my account set up", "what is left to set up", or wants an onboarding checklist. Read-only.
Sweep staff credentials and certifications in ShiftCare and report what has expired, is expiring, is missing, or is unverified — for one staff member or a whole account. Optionally checks against an advisory NDIS or Australian aged-care worker checklist. Use when the user asks about compliance, expiring certifications, police checks, worker screening, audit readiness, or staff documents.
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.
Generates images with Stable Diffusion models (SD 1.5, SDXL, SD 3.0, Flux) through the HuggingFace Diffusers library, covering text-to-image, image-to-image, inpainting, outpainting, ControlNet conditioning, LoRA adapters, scheduler swapping, and GPU memory optimization. Use when generating images from text prompts, transforming or restyling an existing image, filling masked regions of an image, adding spatial control from edges, poses, or depth maps, loading LoRA style adapters, or fixing out-of-memory and black-image errors in a Diffusers pipeline. Not for API-only generation without a GPU, where DALL-E 3 fits better.
Generate a structured tax planning checklist and review framework for any individual or business context. Use when asked to review tax planning, prepare for year-end tax, check tax efficiency, or identify tax-saving opportunities. Produces a checklist of considerations, common reliefs, and a review framework. Not a substitute for qualified tax advice.
Expert in token economics - distribution models, vesting schedules, incentive mechanisms, emission curves, and sustainable protocol design. Use when "tokenomics, token economics, vesting, token distribution, emission, inflation, token utility, governance token, token supply, tokenomics, token-economics, vesting, emission, incentives, governance, defi, crypto" mentioned.
Use this skill alongside the primary implementation, review, or workflow skill when the user wants code review, repo scanning, maintainability or architecture feedback, implementation planning, documentation cleanup, readable comparisons, or a clearer structured answer. Apply it when shared formatting, alignment, and response-structure rules must be enforced across touched code or documents. Do not use it as the primary owner of language, framework, runtime, or workflow decisions.
Transcribes and translates audio with OpenAI's Whisper (openai-whisper Python package and whisper CLI), covering model sizes from tiny to large plus turbo, language specification, initial prompts, word and segment timestamps, temperature fallback, batch processing, and subtitle generation. Use when transcribing speech, podcasts, meetings, or video audio to text. Use when translating non-English speech to English. Use when working with noisy or multilingual audio in any of 99 languages. Use when choosing a Whisper model size for available VRAM. Use when generating subtitles from audio. Not for speaker diarization or live captioning; use AssemblyAI or Deepgram instead.
Comprehensive Windows workstation operations — diagnose slow boot, failing drives, BSOD crashes, startup bloat, runaway processes, and event logs. Use for: Windows is slow, slow bootup, won't boot, blue screen, BSOD, kernel crash, drive failing, SMART errors, disk errors, Event 41, Event 129, storahci reset, BugCheck, CRITICAL_PROCESS_DIED, crash dump, MEMORY.DMP, minidump, msconfig, services.msc, registry Run keys, StartupApproved, scheduled tasks at logon, slow login, high CPU at boot, disable startup app, unexplained UAC prompt, what asked for admin, prefetch forensics, BAM, process attribution, Security 4688, high CPU, runaway process, spinning process, process eating CPU, memory commit exhausted, out of memory, too many processes, what is using my RAM, orphaned process, stale processes, zombie process, kill a process tree, machine is hot, fans are loud. A drive letter alone does not name the skill: mapped network drive, SMB, UNC, NAS route to net-ops.
A dedicated balcony renovation guide to help avoid common pitfalls. Covers the full process, including laundry and drying areas, opening up balconies and window enclosures, balcony storage and cabinets, leisure and functional renovations, waterproofing, insulation and construction, homes without balconies and remedies, and general balcony renovation. Curates the essential content of the Xi'an Home Renovation Classroom member edition knowledge base in reverse order to help users renovate with less hassle and fewer pitfalls.
Execute on-chain trading actions via the Zerion CLI: swap, bridge, and send tokens across 14 EVM chains and Solana. Use whenever the user asks to swap / trade / convert tokens, bridge across chains, or transfer tokens to an address. Always uses an API key + agent token (no pay-per-call). Pair with `zerion-agent-management` to set up tokens/policies first, and `zerion-analyze` to check positions before trading.
A dedicated skill for saving money on home renovations. Covers the full process, including what is and isn't worth spending on, negotiating and quotes, money-saving tips, and budget planning and allocation. Curates the essential content of the Xi'an Home Renovation Classroom member edition knowledge base in reverse order, helping users save money on renovations with less hassle and fewer pitfalls.
A dedicated guide to choosing renovation hardware. Covers the full process, including floor drains and drainage, faucets, showers and sinks, hinges, drawer slides and furniture hardware, door locks and fittings, selection principles and pitfalls to avoid, and general hardware. Curates the essential content of the Xi'an Home Renovation Classroom member edition knowledge base in reverse order to help users choose renovation hardware with less hassle and fewer pitfalls.
Read and reason about Altium Designer projects and schematics using structured data from .PrjPcb and .SchDoc files. Use when the user asks an AI to understand, explain, review, debug, summarize, inspect, or query an Altium circuit design, including components, nets, pin-level connectivity, BOMs, variants, sheet hierarchy, power rails, or questions like what is connected to a pin.
Build natural-language crypto agents, web3 assistants, and trading bots that read and write EVM chain state. Aomi turns prompts ("swap 1 ETH for USDC", "open a 3x GMX long", "bet $100 on Polymarket") into wallet-signed transactions on Ethereum, Base, Arbitrum, Optimism, Polygon, Linea — non-custodial, fork-simulated. Use when the user wants a crypto/DeFi agent, AI trading/wallet assistant, or on-chain execution against Uniswap, Aave, Lido, GMX, Hyperliquid, Polymarket, Binance, OKX, or 40+ other protocols. Trigger with prompts about swaps, lending, bridging, staking, perps, prediction markets, or any DeFi/CEX action needing a wallet signature. Account-abstraction aware with EIP-7702/4337 in the backend lane; local CLI signing is EOA. MUST NOT fabricate or echo credentials; values reach the CLI only when the user explicitly supplied them.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.