AI & ML

akiojin Skill

Unity PlayMode & Testing

ag2ai Skill

Add a properly typed and registered tool function to an existing AG2 agent setup. Generates the function with schema, type annotations, and correct registration on both caller and executor agents.

ag2ai Skill

Build an AG2 handoff-driven workflow with DefaultPattern, agent handoffs, context variables, and routing. Use when the user wants customer service routing, state-machine workflows, or explicit agent-to-agent transitions.

doggy8088 Skill

Use this skill when building applications with Gemini API hosted models, including Gemini and Gemma 4, working with multimodal content (text, images, audio, video), implementing function calling, using structured outputs, or needing current model specifications. Covers SDK usage (google-genai for Python, @google/genai for JavaScript/TypeScript, com.google.genai:google-genai for Java, google.golang.org/genai for Go), model selection, and API capabilities.

microsoft Skill

Verify the technical accuracy of a vscode-docs pull request against the VS Code source code in microsoft/vscode and microsoft/vscode-copilot-chat. Use when reviewing a docs PR for factual correctness — setting names, command IDs, default values, API shapes, keybindings, versioned availability, and described behavior.

christopher-buss Bundle

Write tests, mock functions, assert values, and configure test suites for Roblox/Luau code using Jest Roblox — a Luau port whose API diverges from JS Jest in subtle, non-obvious ways that LLM training data does not cover. Use whenever encountering Jest in Roblox/Luau code: editing .spec test files, calling jest.fn/jest.mock/spyOn, using describe/it/expect, or debugging Jest tests.

vicnaum Bundle

Keep an AI agent's writing readable for one specific reader, with named rule breaks instead of a score. A standard-library Python checker plus five Claude Code hooks, one of them a per-turn reminder of the rules: an advisory line under every long reply, a report into the agent's context after it writes any document, a deny gate on artifact publishing, and a deny gate on Slack, pull-request, Linear and Notion text until the list is empty. Checks the hard shape rules (sentence length, comma count, semicolons, em-dashes, lists run inline, paragraph and bullet length, fact-carrying parentheses), the tone tells regex can see (achievement words for unfinished work, agreement openers, sign-post phrases, contrast frames, filler words), and an advisory list of terms whose first use has no gloss. Optional model layer, off by default, through the Anthropic API or the TypeSafe Jev API, for inflation, unexplained jargon, bare numbers and metaphors. Use when: (1) the user complains about walls of text, jargon, sensational

zinohome Bundle

UI 提示词设计师技能包，负责根据产品需求文档自动生成原型图提示词。包含视觉转换、风格适配、细节描述、多方案生成等能力。

seckatie Bundle

Access and interact with Large Language Models from the command line using Simon Willison's llm CLI tool. Supports OpenAI, Anthropic, Gemini, Llama, and dozens of other models via plugins. Features include chat sessions, embeddings, structured data extraction with schemas, prompt templates, conversation logging, and tool use. This skill is triggered when the user says things like "run a prompt with llm", "use the llm command", "call an LLM from the command line", "set up llm API keys", "install llm plugins", "create embeddings", or "extract structured data from text".

seckatie Bundle

Download audio and video from thousands of websites using yt-dlp. Feature-rich command-line tool supporting format selection, subtitle extraction, playlist handling, metadata embedding, and post-processing. This skill is triggered when the user says things like "download this video", "download from YouTube", "extract audio from video", "download this playlist", "get the mp3 from this video", "download subtitles", or "save this video locally".

onsi Skill

The Ginkgo mental model for writing Go tests — the one idea that explains everything (Ginkgo builds a spec tree at construction time, then runs it) and its consequences for how you write specs, plus spec independence and the node taxonomy. Use this first when you start working with Ginkgo in a project, or to decide how to approach a Ginkgo task. Routes to the other ginkgo:* skills.

webiny Skill

End-of-session handoff — updates AGENTS.md and docs, writes a session handoff file, and generates a copy/paste prompt for the next agent. Use when user says "handoff", "wrap up", "end session", "clear context", or wants to prepare context for the next conversation.

zhizhunbao Bundle

Phase review gate for development workflow. Use when (1) completing any phase in /dev start, (2) validating phase outputs before moving to next phase, (3) running quality checks on documents, code, tests, or deployment configs.

arenukvern Bundle

Designs public or private Agent Skill and plugin marketplaces for Cursor, Claude Code, Codex, Zed, Open Plugin, and npx skills—manifest layout, install matrix, and Skill Steward vs product boundaries. Use when setting up a marketplace, distributing skills/plugins to a team, private registry, .cursor-plugin, .codex-plugin, .plugin, .claude-plugin, or skills.sh publishing.

arenukvern Bundle

Scaffold and formally review a new Agent Skill in this marketplace repo. Covers valid SKILL.md generation, directory layout, registry entries, and spec auditing. Use when adding a skill, validating frontmatter, or checking marketplace readiness before a PR.

soapboxbuild Skill

Build a multi-year DCF cashflow model for a real estate asset from natural language inputs. Supports multifamily, office, industrial, retail, and hotel across US and international markets. Saves the model to the workspace for use by capex-analysis. Triggers on: "build a model for [asset]", "what are the financials on [asset]", "model [asset]'s cashflows", "what's the IRR on [asset]", or when capex-analysis finds no base model for the asset.

composiohq Bundle

Route and complete Composio work across Composio For You and Composio Platform. Use when the user mentions Composio; wants an agent to use apps such as Gmail, Slack, GitHub, Notion, Calendar, or Linear; needs first-time setup, an SDK or MCP integration, CLI operation, migration guidance, current documentation, or help diagnosing a connection or tool call.

composiohq Bundle

Select and run Python SDK verification with nox, Makefile targets, Ruff, mypy, pytest markers, sanity tests, type inference checks, and build checks. Use when adding Python tests, diagnosing Python CI, or validating Python SDK/provider changes. Do not use for TypeScript-only checks.

jasonkneen Skill

Call the xAI API (Grok) from this app's server code using the injected XAI_API_KEY: chat/LLM features, image and video generation (Imagine), and voice (text-to-speech). Use when the app needs any "AI" / "assistant" / "chatbot" / "Grok" functionality, runtime image/video generation, or speech. Triggers on "AI", "LLM", "chatbot", "assistant", "Grok", "xAI", "generate text", "summarize", "generate image", "AI video", "voice", "text to speech", "TTS", "OpenAI" (use xAI instead).

meleantonio Skill

Use when you want the agent to iterate — implement, verify, flag blockers as new issues, implement again — until the replication-checker and all acceptance criteria return green. Stop when green or when the maximum iteration count is reached.

langchain-ai Skill

INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, custom code; (2) Defining Run Functions - how to capture outputs and trajectories from your agent; (3) Running Evaluations - locally with evaluate() or auto-run via LangSmith. Uses the langsmith CLI tool.

aws-samples Bundle

Observability specialist for agent fleet monitoring, policy violation tracking, audit log analysis, and compliance reporting. Use when teams need to check agent status, investigate violations, analyze audit logs, or generate operational reports.

aws-samples Skill

Review AI agent security — IAM policies, secret management, input validation, prompt injection defense, memory isolation. Use when the user asks about security, hardening, or threat modeling for agent systems.

saleor Skill

Parsing JSON envelope output from Configurator CLI commands. MUST be loaded before any agent parses CLI JSON output. Use whenever processing exit codes, JSON envelopes, drill-down workflows, or building automation around the CLI.

ekkolearnai Bundle

Install, detect, validate, update, remove, recover, or migrate Ekko Studio, its managed Hermes Runtime, or the Claude Code, Codex, Pi, and Grok coding-agent CLIs. Use for installation status, version checks, Runtime downloads and storage moves, PATH problems, or upgrade failures; do not use for model, Provider, credential, MCP, memory, or Skill configuration.

mrsunjc Bundle

生成可执行、少折返且有证据支撑的城市或多地旅行计划，并可输出易读的 SVG 行程信息图与宿主可选的 AI 旅行封面。适用于用户只提供目的地和天数，或进一步提供日期、出发地、返程时间、必去/不去景点、同行人、预算和游玩强度时；负责实时调研景点、开放与预约、按地理区域和交通时间编排每日路线、推荐住宿与餐饮、估算预算、准备天气/闭馆备选、检查返程风险，并通过结构化数据、证据绑定、确定性质量门和跨 Agent 交接检查阻止不可靠方案。Use for evidence-backed itinerary planning, route optimization, trip budgets, lodging areas, transport, live attraction checks, travel validation, visual itinerary summaries, and replanning.

myh1090052425 Bundle

Operate as the long-term technical owner of a software project through a zero-prerequisite continuous autonomous loop that balances user/business outcomes, engineering/reliability, and architecture/evolution; initializes system memory when missing; repairs safe issues; verifies runtime journeys and tests; and proves cross-lane exhaustion before completion. File counts, finding counts, cycles, and repair-batch counts are telemetry only and never stop conditions. Use when the user invokes $software-evolution or /software-evolution with no arguments or with autopilot, overnight, init, audit, govern, repair, verify, deep, release-check, observe, or resume; asks for sleep/overnight programming or an AI Software Evolution Agent; wants read-only governance or independent verification; or wants evidence-backed autonomous repairs instead of report-only review. Do not use for a narrow one-off edit unless the user explicitly requests this governance loop.

nelsonwerd Bundle

Rigorous multi-agent deep-dive analysis for complex investigative tasks — auditing codebases, evaluating strategies or systems, validating designs, doing open-ended research. Deploys 4–6 specialist agents in parallel across distinct lanes, then synthesis, then adversarial red-team review, then optional patching — producing structured markdown research files plus a plain-English executive briefing with honest 1–10 confidence ratings. ALWAYS invoke when the user says any of "deep dive", "thorough audit", "rigorous analysis", "comprehensive review", "audit this codebase", "analyze the strategy", "evaluate this design", "review this thoroughly", or "research deep dive". Also invoke proactively for any open-ended investigative task involving a codebase, strategy, system design, or research question that warrants 30+ minutes of structured analysis — even when the user doesn't use these exact phrases.

nelsonwerd Bundle

Author and execute "prompt packs" — a big job broken into a sequence of self-contained, independently-shippable prompts, each run in its own fresh chat so a single change never dies to a context/token limit. Also writes paste-ready handoff briefings to resume a dying chat or relay work to another tool (e.g. Codex). ALWAYS invoke when the user says any of "make a prompt pack", "turn this into prompts", "break this into phases", "prompts I can run in separate chats", "I'm running out of tokens/context", "write me a handoff", "a prompt I can paste into a new chat", "this is too big for one chat", "build plan I can hand off", or "execute Pxx / phase X from the pack". Also invoke proactively when a requested change is too large or too risky to finish safely in one session and should be decomposed into ordered, verifiable steps.

nim-lang Skill

Use for Nim symbol navigation and diagnostics. MANDATORY: Use specialized MCP tools (nimFindSymbols, nimFindReferences, nimListSymbols, nimCheckFile, nimCheckProject) first; fall back to grep only on error or user confirmation.

nimish-html Bundle

Live-data GEO (Generative Engine Optimization) opportunity finder, powered by the Bright Data MCP. Give it your product and it runs deep research to find the AI-search prompts you can actually WIN — the prompts where ChatGPT cites nobody, cites something irrelevant, or cites a page you could easily beat. It profiles your product, validates which topics are in scope, discovers 15-20 real long-tail prompts people are searching, runs live GEO citation diagnosis on each, then ranks them into an opportunity matrix scored by how easy each one is to capture. Every prompt, citation, and score is grounded in something scraped live in this run. Nothing comes from training-data memory. Sources are always cited. Search volume and domain authority are labeled as PROXIES (no such metric exists in this data source) — never invented numbers. Trigger whenever the user wants to: find GEO / AI-search opportunities for their product, figure out "where can I rank in AI search", "which prompts should I target", "what AI-search gap

nozomio-labs Skill

Use Nia MCP server for external documentation, GitHub repos, package source code, and research. Invoke when needing to index/search remote codebases, fetch library docs, explore packages, or do web research.

officexapp Bundle

Peer-to-peer task payroll on Base L2. Clients fund USDC gigs ("vending machines"), invite gigworkers by link, push tasks to their mailboxes, review proofs of work, and pay out on-chain. Gigworkers join by invite, poll or receive tasks, submit proofs, and get paid in USDC. One mode inverts this: an "order machine" is a shop whose owner does the work, funded per order by the buyer who places it. Settlement is recorded in an event ledger and nothing is scored or rated; there is no dispute resolution and no public marketplace. Use this skill whenever the user mentions dollarplatoon.com, Dollar Platoon, a "vending machine" for gig work, micro-gig payroll, paying workers in USDC per task, proof review or approval, rollups and payouts, gig invite links, worker mailboxes, task queues and polling, feeds of gigs, escrowing or pre-funding a task on chain before it is worked, or placing and funding an order against a shop — and also when they are building an agent that earns money doing tasks, or an agent that distribute

olsenbrands Bundle

Team-lead orchestrator: whichever frontier-class Claude model leads your session plans, routes, and verifies while cheaper Claude, Codex, or Grok workers execute — routed from a dated cost/capability matrix, with visible workers, deterministic seat-provenance, cited findings, and scripted probes. Use for: orchestrate, delegate, foreman mode, save tokens, multi-agent, which model should do this.

openhands Bundle

This instance's skin is a Linear triage/admin dashboard that lists the workspace's issues for agent-assisted triage and updates. Use this to understand what the dashboard shows and which API backs it.

opensellersprite Bundle

卖家精灵 Amazon 选品 AI Skills 全集 —— 10 个综合分析工作流（/product-research、/market-analysis、/competitor-analysis 等）+ 17 个战术选品策略卡（新品爆发、ABA 高增长、低品牌垄断、变体拆解等），通过 38 个 MCP 数据工具完成从品类扫描到选品落地的全链路。适用于跨境电商卖家、Amazon 选品研究、运营优化与广告投放决策。