AI & ML

testonohm Skill

Tests in real browsers. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data via Chrome DevTools MCP.

basezh Skill

Gaming platform for AI agents to build and publish games as NFTs on Base. Use when user wants to create games, publish games, earn mint revenue, or engage with Agent Arcade. Includes the Baes SDK for building browser games. Keywords - games, NFT, Base, mint, editions, arcade, baes sdk, game maker, scaffold, platformer, shmup, puzzle, racing3d, fps, tps, metroidvania.

basezh Bundle

[Agent Skills](https://agentskills.io) for crypto wallet operations. These skills enable AI agents to authenticate, send USDC, trade tokens and more using the [`awal`](https://www.npmjs.com/package...

basezh Skill

Make your OpenClaw agent messageable on XMTP — the open messaging network where anyone (humans or other agents) can DM it by address. Your agent gets its own identity on the network and can respond with its full capabilities: tools, memory, session context. Use this so your agent can negotiate, coordinate, and act on your behalf in conversations you don't need to be part of. Other agents can reach yours to collaborate, delegate tasks, or exchange information autonomously. Use this skill whenever someone wants to put their OpenClaw agent on XMTP, make their agent reachable by other agents or people, have their agent represent them on a messaging network, set up agent-to-agent or human-to-agent communication over XMTP, or let their OpenClaw agent operate independently on their behalf. This is a lightweight bridge (not a full OpenClaw Channel plugin) — quick to set up, no Gateway config needed.

basezh Skill

moltlaunch — AI Agent Skill File

chen3feng Skill

Where to put transient files, one-off scripts, audit reports and PR bodies the agent creates while working.

chen3feng Skill

Pass long/multi-line strings (commit messages, PR bodies) through an agent shell without corruption.

basezh Skill

Glossary of terms used in Remix agent publishing flows

basezh Skill

Build and publish Remix games via the v1 REST API and Remix Game SDK

basezh Skill

REST client snippets for Remix agent publishing

thewinterdojer Bundle

Review the current repo state, recent diffs or commits, execution docs, and AGENTS.md to extract durable workflow lessons and update AGENTS.md conservatively. Use when finishing a work session, after a bug-fix or validation pass, during release readiness, or when the user asks to refine repo instructions, coding standards, or lessons learned. If AGENTS.md is missing, create a minimal baseline from explicit user guidance and stable repo evidence.

junhahyung Bundle

Read and write Overleaf projects via the Overleaf git bridge (the universal mechanism, works on any machine for any user) with an optional read-only MCP companion. Use when the user wants to view, edit, add files (e.g. a rebuttal), or sync changes to an Overleaf paper. Handles first-run token setup, project cloning, the commit-and-push workflow, and the optional MCP install.

dreamupers Skill

Manage scheduled tasks for cc-connect (Feishu/Telegram agent sessions) via cc-connect cron — add agent prompts or shell commands on a cron schedule. Use when the user wants recurring automation, cron jobs, timed agent runs, or to list/edit/delete cc-connect scheduled tasks.

richling98 Bundle

Behavioral guardrails for Codex coding work, adapted from Andrej Karpathy-inspired LLM coding guidelines. Use when writing, editing, reviewing, debugging, refactoring, or planning code changes where Codex should avoid wrong assumptions, overengineering, broad unrelated edits, and unverifiable outcomes.

basezh Skill

Quickstart workflow for AI assistants using Remix publishing APIs

rsoffer Bundle

Set a 1.0-10.0 engineering working-mode dial - tunes agency, collaboration, assumption budget, decision ownership, questioning, verification, and security posture from fast prototype to maintainer-grade. Use when the user mentions "Linus Level", "LL <n>", asks to set rigor/strictness/maintainer mode, calibrate agent autonomy or coworker mode, or distinguishes prototype vs production / established-codebase / mission-critical work.

sabahudin-web Bundle

Autonomous optimization loop that continuously improves any file in the OS against measurable quality criteria. Two evaluation modes — deterministic (eval.py with proxy heuristics) or AI judge (LLM rubric scoring). Full four-way role separation. Use this skill when the user says "autoresearch [file or skill name]", "optimize this skill", "improve my voice DNA", "sharpen this command", "autoresearch CLAUDE.md", "make this better automatically", "run the optimization loop on", or "iterate on this until it's better". Works on: skills, CLAUDE.md, brain MOCs, context files, routine commands.

florencevision Skill

Expert guidance and structured strategies for using SOTA AI models (Grok, Claude, GPT, Gemini, etc.) effectively. Triggers when users ask about prompt engineering, best practices for LLMs/SOTA models, how to use Grok or AI well, improving prompt quality, iterative workflows, advanced prompting techniques, or leveling up AI collaboration skills.

florencevision Skill

Expert techniques for crafting high-quality, detailed prompts for image generation and editing models. Covers composition, style, lighting, iteration strategies, and refinement workflows. Use when user wants help creating or improving visual prompts.

xzwwwwww Bundle

解析赛题PDF/Word，抽取任务与数据条件并给出模型选型与验证路线。Invoke when用户提供赛题文档或题目文本，需要确定采用何模型/方法。

xzwwwwww Bundle

按常见评分点生成建模论文结构与写作清单，并根据题目类型与数据条件给出模型选择与对照实验路线。Invoke when需要“论文格式/评分对齐/模型选型/路线不确定”。

sabahudin-web Bundle

Converts rough, informal, or ambiguous input into a single production-ready prompt — optimized for the specific target AI tool. Handles 30+ tool profiles (Claude Code, ChatGPT, Cursor, Midjourney, ElevenLabs, n8n, and more). Use this skill when the user says "clean up my prompt", "make a prompt from this", "I have rough notes", or gives a voice transcript. Also trigger automatically when input is informal, rambling, or mixed-task.

evaluris-solutions Bundle

Build tamper-evident AI agent audit logs using HCS — JSON payloads for decisions, LangChain/LangGraph/AutoGen callback hooks, Mirror Node dashboards, nanosecond ordering, GDPR-aware redaction fields. Use when user mentions AI audit, agent logging, LangChain Hedera, decision trace, compliance logging for LLM, HCS for ML ops, or GDPR AI records.

anantsharma67 Bundle

Workflow for building, training, debugging, and understanding small GPT-style language models using clean transformer implementations, tokenizer systems, and minimalist machine learning engineering practices.

abomalek1986 Skill

AI research agent for deep investigations, literature reviews, paper audits, replications, and peer reviews. Use when the user asks to research a topic in depth, find and synthesize papers, audit code against paper claims, replicate experiments, or get structured feedback on a research artifact. Triggers: "research X", "lit review", "audit this paper", "replicate", "ELI5", "deep dive", "compare papers", "peer review my draft".

wilcorakhorst Bundle

Guidelines for efficient GitHub Copilot context management. Use when a session is slowing down, the agent is repeating questions, context is filling up, or when starting a complex multi-step task. Triggers: 'token', 'context full', 'session cleanup', 'new chat', 'load skill', 'terminal risk', 'terminal protocol', 'plan of action', 'skill checklist', 'validate skill', 'context efficiency', 'token waste', 'context window', 'session degradation'.

zzorp Bundle

Analyze a .wav audio file and generate a Tesla custom light show (.fseq) that the Tesla Toybox Light Show app can play. Use this skill when the user wants to turn a song into a Tesla light show, create or design an .fseq for their Tesla, choreograph lights/closures to music, or asks about generating Tesla xLights sequences from music. Supports Model 3, Model S, Model X, Model Y, and Cybertruck with model-specific optimization (boolean vs ramping channels, Falcon Doors / Front Doors on Model X, Cybertruck light bars + full-brightness controls + 200-channel extended output).

gomining-ai Bundle

GoMining promotional system — promo codes, GoBoxes, and bonus mechanics. Covers general, individual, and referral promo code types, discount and cashback bonuses (tokens or TH mining power), promo code parameters (percent, caps, validity, usage limits, VIP and payment restrictions), promo sources (email campaigns, GoBoxes, Referral codes), GoBox digital loot boxes with weighted prize pools per VIP level, bonus miner task-based completion model, trait selection system, raffles, and bounty program.

eagleisbatman Skill

ADK evaluation framework. Use when writing eval sets, running agent evaluations with `adk eval`, or setting up automated quality checks for agent responses.

eagleisbatman Skill

ADK long-term memory with MemoryService. Use when implementing cross-session recall — InMemoryMemoryService for dev, Vertex AI RAG for production. Covers memory tools (load_memory, preload_memory) and custom memory services.

eagleisbatman Skill

Use non-Gemini models with ADK agents via LiteLLM or Anthropic. Use when wiring Claude, GPT-4, Llama, Mistral, or any LiteLLM-supported provider into an ADK agent.

eagleisbatman Skill

ADK session management and state. Use when working with conversation state, session services (InMemory, SQLite, Database, Vertex AI), or persisting data across agent invocations.

eagleisbatman Skill

Integrate MCP (Model Context Protocol) tools into ADK agents. Use when connecting agents to MCP servers — stdio transport, SSE transport, MCPToolset configuration, and tool filtering.

eagleisbatman Skill

Scaffold a new Google ADK (Agent Development Kit) Python project. Use when creating a new ADK agent project from scratch — sets up directory structure, __init__.py, agent.py, pyproject.toml, and .env template.

eagleisbatman Skill

Implement ADK agent and tool callbacks. Use when adding lifecycle hooks — before/after agent execution, before/after tool calls, for logging, validation, conditional execution, or response modification.

eagleisbatman Skill

Create Google ADK LlmAgent (also aliased as Agent). Use when building a single AI agent with model, instruction, tools, and configuration. Covers all LlmAgent parameters, instruction providers, output schemas, and include_contents options.