AI & ML

drunkcoding Bundle

Poll TickTick for coding tasks and dispatch them to remote machines via SSH + OpenCode Serve. Includes full TickTick CLI, intelligent agent routing (build/plan/deep), stuck/loop detection, plan verification gate, session knowledge management (DAG/forest), and LLM-powered session relevance matching with Haiku/GPT-5.1/GPT-4o fallback chain.

drunkcoding Skill

Step-by-step tutorial for adding new CUDA kernels to FlashInfer

drunkcoding Bundle

Provides guidance for writing and benchmarking optimized CUDA kernels for NVIDIA GPUs (H100, A100, T4) targeting HuggingFace diffusers and transformers libraries. Supports models like LTX-Video, Stable Diffusion, LLaMA, Mistral, and Qwen. Includes integration with HuggingFace Kernels Hub (get_kernel) for loading pre-compiled kernels. Includes benchmarking scripts to compare kernel performance against baseline implementations. Use for kernel types: attention, rmsnorm, rope, adaln, geglu, benchmark, transformers, diffusers, huggingface-kernels, get_kernel.

shashank-yadav Skill

Operate this repo (SkillUp) -- a framework for distilling agent experience into a portable SKILL.md and evaluating whether it measurably improves the same frozen model on unseen tasks. Use this skill when asked to train a skill for an environment, evaluate a trained skill, add a new environment or training algorithm to this repo, or install a trained skill into another harness (Claude Code, Codex, OpenCode, ...).

j5ik2o Bundle

Use when evaluating whether CQRS is worth adopting, especially tradeoffs among consistency, availability, scalability, operational complexity, and event sourcing. Trigger for read/write separation decisions, eventual consistency concerns, CQRS architecture review, or choosing between a unified model and CQRS.

paulieb89 Bundle

Compare up to 3 UK properties side by side — comparable sales, EPC ratings, rental yields, stamp duty, and a relative ranking. Use when someone shares 2 or 3 addresses, postcodes, or Rightmove URLs and asks "which is the better investment?", "compare these properties", "rank these for me", or "which should I buy?". Produces a structured 3-column report with a clear winner. Requires the Property MCP server (property-shared) to be connected.

paulieb89 Skill

Find motivated sellers in a UK postcode. Pulls reduced Rightmove listings, benchmarks against Land Registry comps, and assesses motivation signals. Use when someone asks about reduced properties, motivated sellers, price drops, bargains, or who has been on the market longest. Requires the Property MCP server (property-shared) to be connected.

paulieb89 Skill

Look up a Pine Script v6 function and get its signature, parameters, and a usage example. Use when someone asks "how do I use [function] in Pine Script?" or "what are the parameters for [function]?". Requires the PineScript MCP server to be connected.

paulieb89 Skill

Get comparable sales data for a UK postcode. Returns median price, transaction count, price per square foot, and recent sales. Quick lookup — one tool call. Use when someone asks "what are houses going for in [postcode]?" or "comps for [area]". Requires the Property MCP server (property-shared) to be connected.

paulieb89 Skill

Take a trading idea described in plain English and produce a working Pine Script v6 strategy. Looks up correct v6 syntax via the PineScript MCP server, validates functions, lints the output, and explains every section. Use when someone says "write a strategy for X", "build a Pine Script for Y", "code up this trading idea", "how do I implement Z in Pine Script", or pastes a trading concept they want to test. Requires the PineScript MCP server (pinescript-mcp) to be connected.

fabioc-aloha Bundle

Use when the user wants to humanize, de-AI, de-slop, or un-ChatGPT a piece of text — strip AI-isms and add real voice — or wants a copywriter pass that reviews existing copy for a named audience (e.g., non-native English readers) using an idiom/tone/register/ambiguity/grammar taxonomy and an approval-gated before/after table workflow. Scans for 29 documented AI-writing patterns (Wikipedia's "Signs of AI writing") and produces a draft → self-audit → final rewrite. Optional voice-calibration from a user-provided writing sample. Adapted from Hermes Agent / blader/humanizer.

fabioc-aloha Skill

The 10 canonical tenets of Artificial Critical Thinking (ACT) with rationale for each — I Hypothesis Primacy, II Disconfirmation Over Confirmation, III Multiple Working Hypotheses, IV System-Prompt Skepticism, V Calibration Over Confidence, VI Materiality Gating, VII Frame Before Solve, VIII Adversarial Self-Probe, IX Visible Markers, X The Discipline Applies to Itself. Use when a decision cites "a tenet", when running act-pass, when authoring a critical thinking rule, or when looking up the ACT canon.

fabioc-aloha Skill

Author Flint charts in Scout from data, intent, and audience context. Use when creating, selecting, rendering, or refining charts with the Flint MCP tools; pairs with chart-big-idea, chart-vocabulary, and render-verify.

fabioc-aloha Skill

Use for any feature, bug fix, refactor, or behavior change — enforces RED-GREEN-REFACTOR. Write the failing test first, watch it fail, write minimal code to pass, refactor. Carve out only throwaway prototypes, generated code, configuration files. Adapted from Hermes Agent / obra/superpowers.

green-pt Skill

Write less code and say less about it: YAGNI, stdlib-first, terse prose. Cuts agent token cost on every coding and writing task.

hyhyxyx Bundle

按分诊状态机核验、分类并整理外部问题或PR，生成可供智能体执行的任务说明。 English: Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.

hyhyxyx Bundle

生成人机协作的交互式配置向导；适用于必须由用户完成的账号、凭据、控制台或迁移步骤。 English: Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.

hyhyxyx Bundle

把当前对话压缩成可供另一个智能体或新会话继续执行的交接文档。 English: Compact the current conversation into a handoff document for another agent to pick up.

hyhyxyx Bundle

基于官方文档、源码和规范等一手资料开展调研并形成带引用的Markdown报告。 English: Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

hyhyxyx Bundle

制作一次性逻辑或界面原型来回答设计问题；适用于需要先看效果或验证状态模型时。 English: Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

hyhyxyx Bundle

把超出单次会话的大型模糊工作规划为决策任务地图，并逐步消除关键不确定性。 English: Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

hyhyxyx Bundle

建立并校准项目领域语言、CONTEXT文档和架构决策记录；适用于术语、概念关系和关键决策。 English: Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.

xianyu110 Bundle

使用ModelScope Z-Image-Turbo模型生成图片。支持通过Prompt描述生成图片。

xianyu110 Bundle

Unified search skill with Intelligent Auto-Routing. Uses multi-signal analysis to automatically select between Serper (Google), Tavily (Research), Exa (Neural), Perplexity (AI Answers), You.com (RAG/Real-time), and SearXNG (Privacy/Self-hosted) with confidence scoring.

kelvinchenof Bundle

Teach the user a new skill or concept, within this workspace.

kelvinchenof Bundle

Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.

kelvinchenof Bundle

Generate an interactive bash wizard that walks a human through a manual procedure — third-party setup, a one-off migration, an A→B state transition — opening URLs, capturing values, confirming each step, and writing .env files and GitHub Actions secrets.

kelvinchenof Bundle

Compact the current conversation into a handoff document for another agent to pick up.

kelvinchenof Bundle

Grill me about specs for the workflows I want to build, within this workspace.

kelvinchenof Bundle

Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

kelvinchenof Bundle

Ask which skill or flow fits your situation. A router over the skills in this repo.

kelvinchenof Bundle

Implement a piece of work based on a spec or set of tickets.

kelvinchenof Bundle

Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

kelvinchenof Bundle

Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in one file per ticket locally, or native blocking links on a real tracker.

kelvinchenof Bundle

Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.

kelvinchenof Bundle

Writing, exploit — assemble raw material into a journey of beats, grounding each term before a beat leans on it.