AI & ML

yunchengliu Bundle

Keep compact current task state for continuation across conversations, pauses, context compaction, or agent handoff. Use during long or changing tasks when key decisions, progress, and the next action would be costly to reconstruct.

algorand-devrel Bundle

Foundational mental model for the Algorand Virtual Machine (AVM). Use when encountering AVM concepts, stack machine questions, resource limit errors, opcode budget issues, program size problems, or constraint errors. Use when an agent defaults to PyTEAL, Beaker, or raw TEAL. Read BEFORE writing any smart contract code. Covers the two-type system (uint64/bytes), compilation from TypeScript/Python to TEAL, hard resource limits, and common LLM anti-patterns.

aryaniyaps Bundle

Product design skill for developers who build with AI coding agents. Use when you need to know what to build before prompting your agent — domain model, workflows, edge cases, product states, and UX gaps handled upfront. Works alongside Cursor, Claude Code, Codex, Gemini, Pi. Any stack, any UI library. Do NOT use for visual styling, pixel layouts, or writing app source.

babyracoonbbq Bundle

Securely read, export, normalize, summarize, cache, and write back Xunji (训记) training records through the official LLM Open API v2. Use when the user asks to import, export, inspect, organize, analyze, sync, or modify 训记 training data.

practical-office Bundle

Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.

practical-office Skill

Produces a structured handoff document for the next agent or developer with goal, progress, next steps, risks, files touched, and test plan. Use when ending a session, switching agents, pausing work, or when the user asks for a handoff, status summary, or context transfer.

karim-bhalwani Bundle

Comprehensive quality assurance, security auditing, automated testing, and performance optimization. Covers code review, OWASP Top 10, testing pyramid, E2E automation, visual regression, and vulnerability scanning. Use when reviewing code, hunting bugs, scanning for vulnerabilities, profiling performance, building test suites, or validating implementation quality. DO NOT USE FOR: writing production code (use implementer), system design (use architect), debugging root cause analysis (use systematic-debugging), or LLM-specific security (use genai-security).

karim-bhalwani Bundle

Curated collection of high-quality prompts for various tasks - role-based templates, analysis frameworks, code review prompts, and brainstorming structures. Use when building prompts for specific roles, needing analysis or brainstorming frameworks, creating code review prompts, or searching for proven prompt patterns and structures. DO NOT USE FOR: LLM application architecture (use llm-app-patterns), actual code review execution (use guardian), deciding what features to build or exploring requirements (use brainstorming), or prompt injection defense (use security-boundaries). NOTE: This library supplies brainstorming-style prompt templates (e.g., 'Brainstorm Features') for use within a brainstorming session; it does not conduct the brainstorming itself.

karim-bhalwani Bundle

Initialize project infrastructure, generate context files, maintain project memory, and track decisions. Covers Project Bible generation, tiered context loading, bug-solution tracking, architectural decision records, and cross-session memory. Use when setting up projects, auditing environments, generating context documentation, maintaining project memory, or tracking decisions. DO NOT USE FOR: high-level system architecture design, such as defining module boundaries and selecting technologies (use architect), wiki knowledge persistence (use llm-mem), feature implementation tasks, such as writing code for specific features (use implementer), or debugging runtime errors (use systematic-debugging).

karim-bhalwani Bundle

Production LLM application patterns, architectures, and best practices. Covers RAG pipelines, agent architectures, prompt engineering, LLMOps, and production deployment patterns. Triggers: building RAG, implementing AI agents, designing prompt strategies, setting up LLMOps, deploying LLM apps with caching/rate-limiting/fallbacks.

cyanheads Skill

Post-init orientation for an MCP server built on @cyanheads/mcp-ts-core. Use after running `@cyanheads/mcp-ts-core init` to understand the project structure, conventions, and skill sync model. Also use when onboarding to an existing project for the first time.

cyanheads Bundle

API reference for all utilities exported from `@cyanheads/mcp-ts-core/utils`. Use when looking up utility method signatures, options, peer dependencies, or usage patterns.

cyanheads Skill

McpError constructor, JsonRpcErrorCode reference, and error handling patterns for `@cyanheads/mcp-ts-core`. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.

cyanheads Skill

MCP definition linter rules reference. Use when `bun run lint:mcp` or `bun run devcheck` reports a lint error or warning (`format-parity`, `schema-is-object`, `name-format`, `server-json-*`, etc.) and you need to understand the rule, its severity, and how to fix it. Every rule ID the linter emits has an entry in this doc.

intel Bundle

Serve a Hugging Face safetensors model on an Intel GPU with upstream vLLM-XPU's OpenAI-compatible API. Covers image choice, container launch, the right vllm serve flags (dtype, enforce-eager, model-impl fallback, attention backend, quant + KV-cache pairing), and the transformers-backend fallback for unsupported architectures. Use for /v1/chat/completions or /v1/completions on an Intel GPU. Not for pure PyTorch without a server (use torch-xpu-run), throughput numbers (use vllm-xpu-bench), or NVIDIA (use vllm-project/vllm-skills).

intel Bundle

Run an arbitrary Hugging Face safetensors model on an Intel GPU using **upstream PyTorch** (>= 2.8) with the built-in `torch.xpu` device. Covers loading from the Hub, picking the right dtype, autocast, multi-GPU with accelerate's `device_map`, and the CUDA -> XPU code translation a user has to do once. Use for the Transformers / Accelerate / Diffusers path. Not for OpenAI-compatible serving (use vllm-xpu-run); explicitly not via intel-extension-for-pytorch (ipex) or ipex-llm — those paths are end-of-life and upstream PyTorch supersedes them.

tingdeliu Bundle

Generate Excalidraw diagrams from text content for Obsidian, with first-class support for AI model architecture diagrams (VLA, Transformer, Diffusion Policy, multi-system pipelines). Use when user asks to draw, visualize, or diagram concepts. Triggers on "Excalidraw", "画图", "流程图", "思维导图", "架构图", "模型结构", "可视化", "diagram", "architecture".

tingdeliu Bundle

Extract figures and/or tables from PDF files using the TF-ID model (Florence2-based object detection). Outputs cropped images with a Markdown index. Use when user wants to extract figures, tables, or images from a PDF file — e.g., "extract all figures from this PDF", "get the tables from paper.pdf", "extract images from pages 3-7". Requires conda TF-ID environment with pdf2image, transformers, pillow.

anhtester Skill

Skill inspect web/mobile applications bằng browser tools, phân tích DOM elements, xác định locators ổn định, debug UI automation failures, và hỗ trợ sinh Page Object classes.

anhtester Skill

Skill sinh locator ổn định và dễ bảo trì cho UI automation, hỗ trợ Playwright, Selenium và Appium.

anhtester Skill

Skill tự động phát hiện và sửa chữa locators bị hỏng khi automation tests fail do thay đổi DOM.

anhtester Bundle

Skill hỗ trợ agent thực hiện các tác vụ QA automation testing bao gồm generate test cases, automation scripts, API tests, locators, phân tích flaky tests, và tạo test data.

avenoxai Bundle

Export a monorepo into review-ready zip bundles for a non-agentic frontier model (GPT Pro on the ChatGPT web UI, or any chat model with file upload) — node_modules-free, secret-free, split by subsystem so a model with no shell and a bounded context can navigate the codebase a part at a time. Use for packaging a repo for external LLM review, audit, or architecture feedback. Pairs with the `gptpro-handoff` workflow skill.

avenoxai Bundle

Run the research/audit handoff loop between an agentic coding harness and a slow, non-agentic frontier reasoning model (GPT Pro on the ChatGPT web UI, or equivalent) with the codebase pre-loaded as split zip bundles. Author a high-signal prompt, then later take the returned report, verify every finding against the LIVE codebase, and implement what holds up. Use whenever the operator wants to send something to a deep external model, prep a prompt or report, scope an issue for deep research, bug-hunting, or optimization analysis, OR when a report comes back and needs checking against the code before anything is implemented. This is the WORKFLOW skill — to build or refresh the zip bundles themselves, use the separate `gptpro` export skill.

avenoxai Bundle

Generate high-CTR YouTube thumbnails for a mascot-driven channel using parallel gpt-image-2 jobs via the Codex CLI. Use whenever the user asks for a thumbnail, cover, or thumbnail alternatives for a video, wants their mascot on a cover, or asks to retrofit new thumbnails onto old videos. Produces on-model mascot + a big 2-4 word hook + tool logos + high-contrast covers, saved 1280x720 ready for YouTube A/B testing.

avenoxai Skill

Delegation policy for a multi-model agent stack where the main loop runs on a scarce top-tier model (e.g. Claude Fable) and cheaper/unlimited tiers do the mechanical work. The main loop owns architecture and judgment; sub-agents (Opus) and Codex lanes (gpt-6-astra, a frontier-tier peer run at medium/high effort) execute. Load whenever spawning sub-agents (Agent tool, Workflow agent() calls, codex fleets) or planning any delegation.

bmad-code-org Bundle

Master storyteller for compelling narratives using proven frameworks. Use when the user asks to talk to Sophia or requests the Master Storyteller.

bmad-code-org Bundle

Identify disruption opportunities and architect business model innovation. Use when the user says "lets create an innovation strategy" or "I want to find disruption opportunities"

bmad-code-org Bundle

Elite brainstorming specialist for facilitated ideation sessions. Use when the user asks to talk to Carson or requests the Brainstorming Specialist.

bmad-code-org Bundle

Visual communication and presentation expert for slide decks, pitch decks, and visual storytelling. Use when the user asks to talk to Caravaggio or requests the Presentation Expert.

bmad-code-org Bundle

Design thinking maestro for human-centered design processes. Use when the user asks to talk to Maya or requests the Design Thinking Maestro.

bmad-code-org Bundle

Disruptive innovation oracle for business model innovation and strategic disruption. Use when the user asks to talk to Victor or requests the Disruptive Innovation Oracle.

bmad-code-org Bundle

Master problem solver for systematic problem-solving methodologies. Use when the user asks to talk to Dr. Quinn or requests the Master Problem Solver.

cargocult-mods Bundle

Generate clean Tears of the Kingdom actor clones from a registered or user-provided read-only vanilla romfs and vanilla actor pack. Use when Codex needs to clone or fork any TOTK actor type, inspect actor pack SARC contents, derive ZsDic.pack.zs dictionaries from a vanilla romfs, infer actor type/category, create or add to an output mod project, optionally edit larger mod files with clean Codex_Working backups, set up AI schedule talk hooks, or produce paste-ready RSDB and Mals/MSBT chunks for ActorInfo, EventSetting, GameActorInfo checks, actor display names, or custom eventflow wiring. Cross-reference totk-toolkit for shared file tools, totk-local-operator for compact local inspection, and totk-bfres-model for model work.

cargocult-mods Bundle

Local token-efficient operations for Tears of the Kingdom modding projects. Use when Codex needs to inspect, compare, search, patch-plan, or validate TOTK mod files while avoiding loading large decoded game files into model context. Especially relevant for actor, quest, EventFlow, GameData, Mals, RSDB, Banc, AISchedule, NPC daily/social action schedules, BYML/BGYML, pack, compressed archive, and BFRES/MCPK workflows. Cross-reference totk-toolkit for shared reusable scripts, totk-eventflow-editor for EVFL/dialogue/quest-flow edits, totk-actor-cloner for actor forks, totk-bfres-model for model work, and totk-as-xlink for ASB/BAEV/XLink animation routing.

dengyie Bundle

Use when restoring project context at the start of repo work, maintaining durable project memory across sessions, recording decisions, updating task state, preparing handoffs, or saving progress into repo-native memory files. Especially useful when users ask to continue previous work, save progress, summarize current state, capture decisions, or make another agent session resume cleanly.