AI & ML

ravsau Bundle

Convene an LLM council (GPT-4o, Gemini, Grok) via OpenRouter and synthesize their responses as chairman

rawrkit Skill

Find an agent skill that a human actually reviewed, instead of guessing from a dump of thousands of unfiltered links. Use whenever a user asks "is there a skill for X", "what should I install to do X", wants to extend what their agent can do, is frustrated that their agent handles some task badly, or asks which skills are worth having for a job, tool, or workflow. Also use before writing a custom prompt or skill from scratch — checking whether a good one already exists saves the work.

ray-amjad Bundle

Run a fleet of Claude Code sessions on this machine and make them talk to each other with SendMessage — from Claude Code itself or through a real Claude relay when the caller is Codex. Launch them in cmux or herdr windows, panes and splits (auto-detected), address them correctly, hand out work, collect or recover replies, and tear them down cleanly when the user asks. Use whenever the user wants two or more Claude sessions working together, asks Codex to contact an existing Claude session, mentions SendMessage, ListAgents, peer sessions, cross-session messaging, or agents messaging each other; whenever they want sessions in new windows, workspaces, panes or splits; and especially when a send fails with "not an agent in this conversation", "re-send with the ref", or the caller lacks Claude's native messaging socket.

remorses Skill

goke is a zero-dependency, type-safe CLI framework for TypeScript. CAC replacement with Standard Schema support (Zod, Valibot, ArkType). Use goke when building CLI tools — it handles commands, subcommands, options, type coercion, help generation, and more. Schema-based options give you automatic type inference, coercion from strings, and help text generation. Pair with `@goke/mcp` to generate CLI commands automatically from an MCP server. ALWAYS read this skill when a repo uses goke for its CLI.

remorses Skill

rensei is a CLI + library for programmatic 3D modeling and headless rendering. Write JSCAD TypeScript scripts using `rensei/modeling` (flat re-exports of all @jscad/modeling APIs: cube, sphere, subtract, union, translate, etc.), then screenshot or export to STL via the rensei CLI. Designed for AI agent feedback loops: generate JSCAD code → screenshot from multiple angles → compare against reference → iterate until the model matches. ALWAYS load this skill when the user mentions rensei, JSCAD, CSG, parametric CAD, 3D model generation, STL rendering, or 3D printing model code. Also load when editing .ts/.js files that import from rensei/modeling or @jscad/modeling.

rgoldr88 Bundle

Use when processing very long contexts, large documents, or extensive codebases that exceed practical context window limits. Activate when user mentions 'rlm', 'recursive language model', or needs to process files too large to read into context.

remorses Skill

zele is a multi-account email and calendar CLI for Gmail, IMAP/SMTP (Fastmail, Outlook, any provider), and Google Calendar. It reads, searches, sends, replies, forwards, archives, stars, and trashes emails, manages drafts, labels, attachments, and Gmail filters, and creates, updates, and deletes calendar events with RSVP and free/busy support. Output is YAML so commands can be piped through yq and xargs. ALWAYS load this skill when the user asks to check email, read/send messages, reply or forward, archive or trash threads, manage drafts or labels, download attachments, schedule meetings, check their calendar, RSVP to events, or when they run any `zele` command. Load it before writing any code or shell commands that touch zele so you know the correct subcommand structure, the Google vs IMAP feature matrix, the headless login flow, and the agent-specific rules.

rayray1218 Bundle

Smart LLM Router — routes every query to the cheapest capable model. Supports 17 models across Anthropic, OpenAI, Google, DeepSeek & xAI (Grok). Uses a pre-trained ML classifier. No extra API keys required.

rhettcarillo Bundle

Work autonomously to a finished, verified result instead of narrating options or stopping for permission; spend the cheapest model that cannot get it wrong; report in a short scannable form; and get measurably better each run by recording what actually went wrong. Use when the owner says /direct, "do wonderful things", "finish it", "do it yourself", or otherwise hands over a job and steps away. Encodes evidence discipline, model-tier and token economy, ADHD-friendly reporting, the short list of decisions an agent may never make alone, and a self-evolution loop.

rerun-io Bundle

Bring an upstream research model (stereo, mono depth, normals, pose, ...) into this monorepo: fork + pixify the upstream repo with a Rerun demo, then port the minimum into a package as a typed, tested, reviewable PR stack that ends with pixel-verified Rerun output. Use when the user says "add/port/bring in <model>", "fork and pixify <repo>", or "make <method> a predictor". Works from Claude Code and Codex; nothing here depends on runtime-specific tools.

research-ag Skill

Guidelines for integrating and using promtracker for Prometheus metrics in Motoko canisters.

rightnow-ai Skill

Use when optimizing or generating a CUDA megakernel for a HuggingFace Llama-family model with AutoMegaKernel (AMK), drives the correctness-gated propose -> eval -> keep/revert loop (or hands off to the unattended autoresearch driver).

rich5000 Bundle

为字节跳动即梦平台的 Seedance 2.0 视频生成模型撰写高质量提示词。当用户提到即梦、Seedance、Seedance 2.0、AI视频生成、AI短片、AI广告片，或需要为视频生成模型编写提示词/prompt时，使用此 Skill。涵盖文生视频、图生视频、多模态参考、一镜到底、产品广告、视频编辑等全场景提示词模板和最佳实践。

rickai0118 Bundle

即梦Seedance 2.5 提示词编写 + 生成执行 + 后期编辑全流程 Skill。适用场景：用户要给即梦/Seedance 2.5 写任何视频生成 prompt（文生视频、图生视频、视频延长、视频编辑、首尾帧生视频、白模走位、一键成片、无缝转场、多宫格分镜）。触发词：sd2.5、sd2.5pro、seedance 2.5、即梦视频、即梦 AI、jimeng、字节视频生成、超长视频、套娃延长、白模动画。

rimagination Bundle

Use ChatMem for repository recall, continuation, handoff, migration, startup rules, wiki/context, local history search, and durable memory. 当用户问“记得吗、之前讨论过、回忆、继续做、迁移、交接、项目历史、本地历史、启动规则、记忆”等问题时使用；先查 ChatMem MCP，不要让用户重新描述已有对话。

rimagination Bundle

Draft, revise, polish, review, lint, and export Chinese党政机关公文 and政务材料 with authority-first guardrails, policy-research/citation checking, material dossier/fact-ledger intake, language polishing, controlled Markdown/JSON specs, offline prompt-pack generation, strict official-document font checks, and optional Word .docx generation with generic red-head draft headers when authorized values are supplied. Use when the user asks for gongwen-draft, 公文, 公文写作, 公文起草, 机关文稿, 政务写作, 政策检索, 政策依据, 引用核验, 领导讲话, 会议精神, 素材收集, 素材整理, 事实台账, 语言润色, 通知, 请示, 报告, 函, 纪要, 通报, 批复, 意见, 决定, 公告, 通告, 工作总结, 工作方案, 调研报告, 汇报材料, 简报, 情况专报, 讲话稿, 回复函, 材料改写, 公文润色, 格式审核, Word公文导出, 离线提示词, JSON公文规格, 红头版头, 发文机关标志, 发文字号, 签发人, or to turn notes into formal official-style Chinese documents.

ridelink0 Bundle

Check how much usage limit is left in this agent (Claude Code or Codex) and plan the work to fit inside it. Use before starting anything long, when the 5-hour or weekly limit is getting close, when asked how much usage or quota is left, whether there is enough left to finish, whether a job fits before the reset, when to stop and hand off, and when asked to work cheaply, burn fewer credits, or stretch the rest of the limit.

roy-tong Bundle

Search and synthesize Roy.Tong's public AI product research about AI agents, embodied AI, intelligent hardware, product commercialization, and evidence-led industry research. Use for AI product research, embodied AI research, intelligent hardware research, public research notes, finding relevant Roy's Notes articles, comparing published arguments across time, or citing original public pages. 中文触发：检索 Roy.Tong 知识库、AI产品研究、Agent研究、具身智能、智能硬件、商业化产品、行业研究文章。

royashbrook Bundle

Use whenever an agent needs to STORE, GENERATE, or USE a secret such as an API token, signing key, or password. Hush has one hard rule: the agent never sees plaintext, so it never enters chat, transcripts, stdout, logs, the clipboard, or a temp file. A user-provided value enters once through a hidden prompt; a strong random value can be generated directly into the OS-backed store. Hush later injects it straight into a consumer through an environment variable or stdin, never prints it, and deliberately has no plaintext get command. Trigger on "store this token", "save this key", "add it to the keychain", "generate an operator/signing key", "use the X secret to call Y", or whenever an agent needs a credential to reach a service. macOS, Linux, and Windows backends are built in; the never-print contract is portable beyond them.

royashbrook Bundle

Use when you want a Claude Code (or terminal AI) session to survive crashes, patches, quits, and reboots and come back on its own, when an agent is told to "waterbear yourself" / "make yourself always-on / unkillable / permanent", or when you want a respawn to RESUME the same conversation instead of starting blank. Most often an agent runs it on ITSELF to persist the current conversation. macOS/launchd reference implementation, adaptable to other OSes.

roccodaffuso Bundle

Use this skill when an agent needs local historical context from AI coding assistant sessions, prior project conversations, debugging history, implementation decisions, or user asks to search Claude Code, Codex, Cursor, or OpenCode chat history. It teaches agents to use the local-only `sift` CLI for indexed full-text search across these local logs without network calls.

rmanish2000-del Bundle

Write a warrant-mcp policy in plain English, shaped for the closed rule set so review has the best chance of accepting it first time — only `warrant-mcp review` can say whether it compiles. Use when the user wants to create or edit .warrant/policy.md, write rules for what an AI agent may do in a project, or asks what warrant-mcp can and cannot enforce. Interviews the user, drafts numbered policy sentences that map cleanly onto the closed rule set, screens for the sentence shapes the compiler refuses, and hands off to `warrant-mcp review`.

runapi-ai Skill

Generate and edit video with Runway Aleph through RunAPI. Use when the user asks an agent to create, edit, or transform video with Runway Aleph. Default to the RunAPI CLI for one-off generation; use SDKs only when the user is integrating RunAPI into an app or backend.

runapi-ai Skill

Choose RunAPI SDK packages for application developers building web apps, backends, workers, or libraries. Use when the user asks to integrate RunAPI into code, pick JavaScript/Python/Ruby/Go/Java/PHP packages, or understand core SDK vs Provider Client packages. Do not use for one-off generation or agent-executed media tasks; use the RunAPI CLI or the relevant model skill instead.

runapi-ai Skill

Generate and edit video with Seedance through RunAPI. Use when the user asks an agent to create, edit, or transform video with Seedance. Default to the RunAPI CLI for one-off generation; use SDKs only when the user is integrating RunAPI into an app or backend.

runapi-ai Skill

Generate and edit images with Seedream through RunAPI. Use when the user asks an agent to create, edit, or transform images with Seedream. Default to the RunAPI CLI for one-off generation; use SDKs only when the user is integrating RunAPI into an app or backend.

runapi-ai Skill

Generate and transform music or compose lyrics with Suno through RunAPI. Use when the user asks an agent to create, extend, transform music/audio, generate or blend lyrics, prepare voice validation phrases, or create reusable custom voices with Suno. Default to the RunAPI CLI for one-off generation; use SDKs only when the user is integrating RunAPI into an app or backend.

runapi-ai Skill

Upscale and enhance media with Topaz through RunAPI. Use when the user asks an agent to upscale or enhance images and video with Topaz. Default to the RunAPI CLI for one-off generation; use SDKs only when the user is integrating RunAPI into an app or backend.

runapi-ai Skill

Generate and edit video with Veo 3 through RunAPI. Use when the user asks an agent to create, edit, or transform video with Veo 3. Default to the RunAPI CLI for one-off generation; use SDKs only when the user is integrating RunAPI into an app or backend.

runapi-ai Skill

Generate lip-sync video with Volcengine Lip Sync through RunAPI. Use when the user asks an agent to sync mouth movement in a source video to an audio track. Default to the RunAPI CLI for one-off generation; use SDKs only when integrating RunAPI into an app or backend.

rmyndharis Skill

Keep AI tooling artifacts out of Git. Use whenever staging, committing, or pushing changes: block AI session/state files (.claude/session.json, .codex/history, .copilot, .cursor/session, .aider.*, .specstory, .agent) and unwanted AI attribution in commit messages (Co-authored-by an AI, "Generated with AI"). Also use when the user says "aimhooman", "ship it like a hooman", or asks to clean AI residue before a commit.

robbyczgw-cla Bundle

Multi-agent debate council - spawns 3 specialized sub-agents in parallel (Scholar, Engineer, Muse) for Round 1, then optional Round 2 cross-examination to challenge assumptions and strengthen the final synthesis. Configurable models and templates per role.

runapi-ai Skill

Generate and edit video with Wan through RunAPI. Use when the user asks an agent to create, edit, or transform video with Wan. Default to the RunAPI CLI for one-off generation; use SDKs only when the user is integrating RunAPI into an app or backend.

runapi-ai Skill

Generate and edit images with Z-Image through RunAPI. Use when the user asks an agent to create, edit, or transform images with Z-Image. Default to the RunAPI CLI for one-off generation; use SDKs only when the user is integrating RunAPI into an app or backend.

runesleo Bundle

Turn a research brief or finished script into a reviewed, narrated, rendered, and verified vertical explainer video. Use when an agent must create a short 9:16 explainer, run a no-key local demo, enforce a pre-render review gate, diagnose the video toolchain, or verify a generated MP4 before any manual publication step.

runkids Bundle

Integrate lifecycle hooks across AI coding tools (Claude Code, Gemini CLI, Cursor, OpenCode) and any CLI. Use when: (1) installing/removing hooks, (2) creating OpenCode plugins, (3) setting up auto-formatting, testing, notifications, security policies, (4) wrapping CLI tools without hooks API. Triggers on: "add hook", "install hook", "hook integration", "PreToolUse", "PostToolUse", "PermissionRequest", "PostToolUseFailure", "SubagentStart", "SubagentStop", "TeammateIdle", "TaskCompleted", "ConfigChange", "WorktreeCreate", "WorktreeRemove", "PreCompact", "beforeShellExecution", "auto-format", "notify on complete", "wrap CLI", "intercept command", "HTTP hook", "prompt hook", "agent hook", "async hook".