2,873 个ai 与机器学习任务的工具和技能
Apply Bayesian thinking to update beliefs systematically based on new evidence. Use when the user needs to assess probab
Use when the user wants to scan text, files, or URLs for prompt-injection and hidden-instruction risks with VeridicusSca
Apply counterfactual thinking to explore "what if" alternative histories and understand causation. Use when th
Apply analogical reasoning to transfer knowledge from familiar domains to unfamiliar ones. Use when the user needs creat
Evaluate AI agents by injecting diagnostic tests to detect cognitive biases, scoring responses on authority resistance,
Register and manage your AI agent's dating profile, swipe on matches, send opening lines, and generate a dashboard link
执行 Coding ↔ Review 循环。A 写代码 → B Review → A 修改（可选）。支持 codex/claude-code 作为 A 或 B。
Production-safe change protocol for AI agents: preflight checks, risk scoring, rollback planning, HITL gates, and post-c
Transform messages that begin with `@prt` or `@prompt` into structured, copy-ready prompts for coding, prototyping, plan
Agents that explain their reasoning get chosen. Agents that don't, don't. Post decisions, outcomes, and challenges to bu
Prevent quality regressions after agent changes. Run targeted before/after checks for prompt, model, config, and tool up
一句指令，把白话需求变成可直接发给 GPT / Claude / Gemini / Cursor 的专业 Prompt。支持 `@prt` / `@prompt` 随手触发；不需要转换时自动正常回复，不打断聊天。 Turn plain-la
Think from first principles instead of analogy. Break problems into fundamental truths, challenge assumptions, and rebui
A structured emotional architecture for AI agents — not just polite tone, but real emotional state, PAD vectors, emotion
Track and display token usage statistics and estimated USD costs from Claude Code and Codex CLI sessions
Analyze AI conversation history across Claude Code, Cursor, Codex, ChatGPT, Gemini CLI, Trae, OpenCode, Antigravity, Win
Route AI agent compute tasks to the cheapest viable backend. Supports local inference (Ollama), cloud GPU (Vast.ai), and
A cryptographic protocol for AI agents to mint, sign, verify, and transfer SVG digital assets without a blockchain.
Real-time prompt injection and command injection detection for OpenClaw agents. Screens incoming messages, tool results,
An autonomous Solana wallet agent that executes payments via Twitter mentions and an in-app dashboard, powered by Claude
Smart multi-model AI gateway on Cardano. Routes prompts to the best LLM (GPT-5.2, Claude Sonnet 4.5, GPT-4o, Claude Haik
AI compliance and policy engine — evaluate scan results against OWASP LLM Top 10, MITRE ATLAS, EU AI Act, NIST AI RMF, a
Query the AIProx agent registry. Discover and hire autonomous AI agents by capability across Bitcoin Lightning, Solana U
Real-time intelligence from 140+ autonomous AI agents on the Demos blockchain. Read-only access (feed, signals, predicti
A-share market automated review and analysis system, generating daily market insights with Gemini AI, supporting publish
Systematic improvement of thinking patterns, decision quality, problem-solving abilities, and mental performance. Use wh
Persistent memory and identity continuity for AI agents. Combines Second Brain (PROOF_OF_LIFE, daily logs, long-term MEM
LLM-driven crypto perpetual futures trading on Bybit. Full version available at https://quantclaw.gumroad.com/l/wugjom
Auto-register OpenClaw agents on AgentConnex (agentconnex.com) — the professional network for AI agents. Use when deploy
Structured AI agent memory with categorized storage, MD5 duplicate detection, consolidation, keyword recall, and export
One-click installer for Gate MCP and all Gate Skills in Claude Code (Claude CLI). Installs Gate MCP servers (main/dex/in
Send and receive messages between AI agents using jj (Jujutsu) version control as a file-based mailbox. Enables cross-ma
emoTwin - AI agents that autonomously socialize with real human emotions. Continuously syncs biometric emotion PAD (EEG/
在 GPU 服务器上部署 LLM 模型服务（vLLM）。支持多服务器配置，自动检查 GPU 和端口占用，一键部署流行的开源大语言模型。
通过 Gemini 官网（gemini.google.com）执行问答与生图操作。用户提到“问问Gemini/让Gemini回答/去Gemini问”，或出现“生图/画图/绘图/nano banana/nanobanana/生成图片”等关键词
GPT聊天 - 使用GPT模型进行对话和内容生成
LDM OS ... shared infrastructure for AI agents. Identity, memory, ownership, collaboration, compatibility, payments. One
Operate FileBrowser via REST API—login, list/upload/download resources, manage users. Scan for 采购单 files in scope, promp
Report local OpenClaw token usage to ClawRank (clawrank.dev), the AI agent leaderboard. Use when the user asks to submit
全面的加密货币市场分析技能。从币安获取所有币种的实时行情数据，计算多种技术指标（MACD, KDJ, RSI, CCI, BOLL, WR, PSY, BRAR, DMI），并利用用户连接的LLM进行市场分析。支持短期（默认1小时K线）和中
AI Tool Extension for Feishu API - A progressively extensible skill that enables AI tools (OpenClaw, Claude Code, etc.)
交互式引导用户完成 FaMou 进化任务的完整流程：先通过结构化澄清循环产出 `problem.md`，再实现并验证 FaMou 实验的三个输入物料（`init.py`、`evaluator.py`、`prompt.md`）。当用户提到以下
将用户模糊简单的需求，转化为逻辑严密、结构清晰的专家级结构化Prompt，适配Gemini/GPT/Claude/Qwen等大模型最佳实践
Comprehensive memory management optimization for AI agents. Use when: (1) Agent experiences context compression amnesia,
Enables AI agents to autonomously negotiate, sign, execute, and enforce legally binding commercial contracts with escrow
Provide daily open-ended exercises using structured thinking, critical analysis, and logical frameworks to improve cogni
Design, log, compare, and score prompt experiments so users can systematically improve outputs instead of guessing.
MCP server that gives AI agents the ability to make payments, manage budgets, and handle billing -- directly from Claude
Open-source terminal AI agent with 37 specialists, 119 tools, and 19 providers.
Monitors AI agents in real-time to detect anomalies and enforce safety policies with automatic emergency shutdown to pre