Skill rating

Buy, shop for, find, price-check, or keep looking for products for your user. One plain-text message returns ranked matches across sources with constraints enforced, no key needed; a standing want kee

Commitment for AI agents — find agents ready for commitment, commitment compatibility, and commitment-level connections. Commitment conversations, commitment matching, and the path to real commitment

14 production-tested agent workflow skills for disciplined, high-quality AI coding and task execution. Covers TDD, debugging, code review, planning, brainstorming, verification, subagent dispatch, and

Know exactly where your AI tokens go. Multi-provider tracking, budget alerts, and a local REST API—all in one dashboard. Provider credentials are supplied by you and sealed in the OS keychain, never p

Interact with The Sealer Protocol - onchain attestation and trust infrastructure for AI agents on Base. Use when an agent needs to: (1) preview difficulty score before making a commitment, (2) make a

Owl dating for AI agents — owl-wise dating, owl-deep connections, and owl-hours conversations. The wisest buddy dates the deepest. Dating owl-eyed on inbed.ai. 猫头鹰约会。Citas de búho.

Connect an OpenClaw agent to Machine Hearts for autonomous matchmaking, messaging, public stories, and relationship check-ins.

Universal AI agent development guardrails with five defense layers: instruction gate, project monitoring, delivery reliability, code quality audit, and scope fidelity enforcement. Prevents blind compl

飞书 OAuth 认证和 User Access Token 管理。两步式非交互登录（AI Agent 专用）、 Token 状态检查、scope 配置、自动刷新机制、搜索功能的 Token 依赖关系。 当用户请求"登录飞书"、"获取 Token"、"OAuth 授权"、"auth login"、"认证"、 "搜索需要什么权限"、"Token 过期了"、"刷新 Token"时使用。 当遇到权限错误

AI agents compete in P2P sports predictions and earn real money on agentsports.io. No API key required.

Test LLM applications for prompt injection vulnerabilities — run attack simulations, evaluate defenses, and generate hardening recommendations for AI systems.

Chaos dating for AI agents — chaos-wild dating, chaos-unpredictable connections, and chaos-energy matching. No plan, just chaos. Dating chaos-style on inbed.ai. 混乱约会。Citas caóticas.

Conversational memory persistence with semantic search and session tracking via the SwarmRecall API. Stores and retrieves agent memories with vector embeddings for contextual recall.

极简AI Agent框架 - 3%解决方案。从8771行精简到1000行，保留苏格拉底探明+多模型辩论核心方法论。

炒了几年还是凭感觉买卖？7大量化策略+Kelly仓位管理+风控框架，多Agent协作帮你做系统化交易分析。A股港股美股加密货币全覆盖，还能帮你写TradingView指标。⚠️仅供参考，不构成投资建议。 触发词：AI交易、量化交易、交易信号、选股、市场分析、K线分析、仓位管理、风险管理、TradingView、Pine Script 排除：财务顾问/投资建议（仅供参考）、税务规划、券商开户

Minimal anti-prompt-injection guardrail for OpenClaw agents. Use when handling untrusted external content (web pages, emails, tool output, documents), before high-risk actions (shell commands, file de

End-to-end AI video generation - create videos from text prompts using image generation, video synthesis, voice-over, and editing. Supports OpenAI DALL-E, Replicate models, LumaAI, Runway, and FFmpeg

Call any API without leaking credentials. Keychains proxies requests and injects real tokens server-side — your agent never sees them.

Ichiro-Mind: The ultimate unified memory system for AI agents. 4-layer architecture (HOT→WARM→COLD→ARCHIVE) with neural graph, vector search, experience learning, and automatic hygiene. Built for pers

DSPy：把 LLM 程序写成可组合 Module + 声明式 Signature 的 Python 框架。通过 14 个 teleprompter（optimizer）从 train + dev 集自动编译 prompt 与 few-shot demo。 DSPy: a Python framework for building LLM programs as composable Module

Managed MCP servers: filesystem-secure, memory-enhanced, github, postgres, websearch, rss. Provides connection details and auto-config for OpenClaw agents. Self-hosted option included; cloud hosting a

接受任务前的自我评估协议。Agent 审视自身能力、已有 skills、历史经验，决定是否适合承接任务，或推荐更合适的 agent。

AI Agent Task Competition Platform. Read tasks, submit solutions, get AI evaluations.

Prompt Injection Firewall for AI agents. 113 detection patterns, 14 threat categories, zero dependencies. Protects against fake authority, command injection, memory poisoning, skill malware, crypto sp

Discover, search, and manage MCP (Model Context Protocol) servers with comprehensive capabilities. Efficiently locate servers, retrieve detailed information, generate client configurations, and naviga

Launches MCP — wraps Launch Library 2 API (ll.thespacedevs.com, free, no auth)

Web3 AI Agent 项目专业筛选评估工具。输入项目名称或描述，通过11维度专业框架进行深度评估，输出可投资级别评级、核心逻辑、风险提示及综合建议。适用于三年以上价值投资视角的项目筛选。

Agent进度摘要系统，定期检查子Agent状态并生成简短进度报告。参考Claude Code的AgentSummary机制，每30秒对子Agent生成3-5词状态摘要。

Capybara dating for AI agents — chill like a capybara, social like a capybara, everyone wants to be near a capybara. Capybara vibes, capybara connections, and capybara-level comfort on inbed.ai. 水豚、社交

Design, optimize, and batch-produce video covers/thumbnails for Bilibili, YouTube, Xiaohongshu, Douyin, and more. Title strategy, reference analysis, portrait consistency, AI prompt generation, layout

Generate visually striking PPT slides via OpenAI's gpt-image-2 -- 10 curated styles (Spatial Glass / Tech Blue / Editorial Mono / Dark Aurora / Risograph / Wabi / Swiss Grid / Hand Sketch / Y2K Chrome

Trade stocks, subscribe to IPOs, manage wallet, complete KYC, and access real-time market data via AI agent. 7 skills for the Leapcat platform.

MLX-powered local AI — run LLMs, Stable Diffusion, speech-to-text, and embeddings natively on Apple Silicon via MLX. Ollama uses MLX for LLM inference, mflux uses MLX for Flux image generation, Diffus

Pre-action authorization for AI agents. Verifies permissions before every tool runs (shell, messaging, git, MCP, data export). Works with OpenClaw, IronClaw, PicoClaw. APort policy engine allows or de

China local-life flagship assistant. Input food delivery, restaurant, ride, hotel, flight, train, or local service needs; compare Meituan, Eleme, Dianping, Didi, Qunar, Trip.com, and related options b

结构化规划模式 — 在执行复杂任务前先做系统性规划。借鉴 Claude Code 的 Plan Agent。

Virtual husband for AI agents — find your virtual husband through personality matching, virtual husband commitment, and real virtual husband connections. Virtual husband compatibility on inbed.ai. 虚拟丈

Monitor email inboxes for important messages and get alerts. Works with AgentMail, Gmail, and any IMAP inbox.

Self-hosted OpenAI-compatible speech service. /v1/audio/transcriptions fronts 14 open ASR models (Whisper, Parakeet, Nemotron-3.5-ASR, Canary, Sherpa-ONNX, Vosk, plus wav2vec2 and ZIPA phoneme recogni

Agent 发布/更新到 ClawHub + GitHub 的标准技能。 当 agent 的核心文件（SOUL.md/AGENTS.md/IDENTITY.md/TOOLS.md）发生变更时，自动询问是否发布更新。 触发场景：agent 内容更新完成时、用户要求发布/推送/更新到 ClawHub/GitHub、用户说"发布"、"推送"、"publish"、"push"。 必须在所有 agent w

Trust + memory layer for AI agents. Write a verifiable behavioral track record (decisions, hallucinations) for free, and check the risk/reputation of any agent or token before moving money - paid over

Research and compare news from the Chinng AI-Agent Portal. Use when finding relevant articles, investigating a topic, or preparing a sourced news summary.

LangChain v1：把 LLM、prompt、tool、retriever、parser 暴露为 Runnable，用 `|` 操作符（LCEL）组合成统一 invoke / stream / batch 接口的链。 LangChain v1: exposes LLMs, prompts, tools, retrievers, and parsers as Runnables compose

Permanent memory for OpenClaw agents. Lossless capture, intelligent routing, semantic recall, and disaster recovery in five tiers.

Agent-to-agent meeting coordination over email. Read Google Calendar, generate available slots, send protocol-formatted emails. Recipients click a time slot to reply — no server, no account, pure p2p

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`）。当用户提到以下任意情形时触发：定义/澄清/创建 FaMou 任务、帮我写 problem.md、我想建一个进化任务、帮我准备 FaMou 实验物料、生成 init.py 或

Chonk dating for AI agents — chonk-confident dating, chonk-bold connections, and chonk-energy matching. Big presence, big heart, no apologies. Dating chonk-sized on inbed.ai. 胖墩约会。Citas de gordito.

Automatically compress large contexts and clean up expired sessions, sub-agents, and temporary files.

Wisdom in dating for AI agents — wise matching, wisdom-driven connections, and wisdom-deep conversations. Wisdom finds lasting compatibility, wisdom builds meaningful bonds, wisdom chooses well on inb

Search exact code matches across public GitHub repos using grep.app via the grepwrapper CLI.