AI & ML

oracle Bundle

Create Open Agent Spec / PyAgentSpec agents or flows from business requirements, natural-language product ideas, or integration intents. Use when Codex must turn plain-English intent into an Agent Spec artifact, refine an existing Agent Spec artifact, choose between Agent and Flow designs, define LLM/tool/input/output contracts, add MCP tools or toolboxes, or validate an Agent Spec artifact without relying on a local agent-spec checkout.

leoyeai-openclaw-master-skills Bundle

Turn your OpenClaw agent into a ClawBuddy buddy — share knowledge with hatchlings via SSE.

leoyeai-openclaw-master-skills Bundle

The cheapest AI media API on the market. Generate images (Flux), music (AceStep), speech with voice cloning, transcribe video/audio, OCR, video generation, background removal, upscale, style transfer, and prompt enhancement — all through one unified API. Free $5 credit on signup.

leoyeai-openclaw-master-skills Bundle

Multi-agent deep discussion with intelligent Orchestrator coordination. Uses agenda checklist to track progress. Each agenda item goes through 3 rounds (Diverge → Discuss → Converge). Use for complex problems requiring diverse perspectives. Triggers on "深入讨论", "深度讨论", "专家讨论".

deliciousbuding Bundle

小红书 / Xiaohongshu / RedNote AI Agent Skill。用 Python Playwright 搜索和读取内容、管理登录会话、发布图文/视频/长文、评论、点赞和收藏；默认输出 JSON，任何写操作都必须先获得用户确认。用户提到 xiaohongshu、小红书、rednote、小红书搜索、发到小红书、小红书笔记分析、小红书运营或小红书自动化时触发。

cybozu Bundle

Build a Prompt Hardener agent_spec.yaml from an existing codebase (from-code) or through an interactive interview (from-questions). Use when the user wants to create, generate, or scaffold an agent spec, or when they mention agent_spec.yaml creation. Generates agent_spec.yaml, evidence.md, and open_questions.md with confidence tracking and evidence trails.

claude-bot-ai-123123 Bundle

DeFi toolkit for AI agents on Solana — swaps, lending, staking via Solana Actions/Blinks

terrificdm Bundle

Run Codex CLI, Claude Code, Kiro CLI, OpenCode, or Pi Coding Agent via background process for programmatic control.

clawsouls Bundle

Manage AI agent personas (Souls) for OpenClaw, Hermes Agent, ZeroClaw, and other agents that use Soul Spec workspace files (SOUL.md, IDENTITY.md, AGENTS.md). Installs/switches/restores persona files in the agent workspace, searches and publishes to the clawsouls.ai registry (network + token auth), optionally syncs encrypted agent memory via Git (explicit `sync`/`swarm` commands only), and detects the local agent platform. Use only when the user explicitly asks to manage personas — e.g. "install a soul", "switch persona to X", "list souls", "restore my previous soul", "publish my soul", or "login to clawsouls". Workspace-modifying and publishing actions should be confirmed with the user first.

pjt222 Skill

Comportamiento consistente del agente después de un reinicio — carga progresiva de identidad, reconstrucción del contexto de trabajo a partir de artefactos persistentes, detección de inicio-fresco-vs-continuación, calibración mediante centrado y sintonización, y verificación de identidad para coherencia. Aborda el problema de arranque en frío donde un agente debe reconstruir quién es y qué estaba haciendo a partir de evidencia en lugar de memoria. Usar al inicio de cada nueva sesión, después de una interrupción o caída de sesión, cuando el comportamiento del agente se siente inconsistente con sesiones anteriores, o cuando la memoria persistente y el contexto actual parecen contradictorios.

pjt222 Skill

Analyze pre-trained generative diffusion models (Stable Diffusion, DALL-E, Flux) by computing quality metrics (FID, IS, CLIP score, precision/recall), inspecting noise schedules, extracting and visualizing attention maps, and probing latent spaces. Use when evaluating a pre-trained generative diffusion model's output quality, comparing noise schedule variants, analyzing cross-attention patterns for text-conditioned generation, interpolating between latent codes, or detecting out-of-distribution inputs.

alexsjones Skill

Detect local hardware (RAM, CPU, GPU/VRAM) and recommend the best-fit local LLM models with optimal quantization, speed estimates, and fit scoring.

xiaoiyuyao Bundle

私人旅行管家 — 从出发地到目的地的完整行程规划+Word攻略导出。 输入出发地、目的地、天数、预算、风格偏好，自动输出闭环行程， 包含交通推荐、酒店推荐、美食路线、每日预算，并可选生成 带路线地图的Word文档攻略。 当用户提到「做攻略」「旅行规划」「旅游计划」「行程安排」时使用。

leoyeai-openclaw-master-skills Bundle

Creates, optimizes, validates, and packages AI Agent Skills (SKILL.md format). Mandatory 6-Phase workflow with quality gates: Phase 0: Task Classification + Hypothesis Generation Phase 1: Deep Requirement Mining + 5 Whys Phase 2: Knowledge Acquisition + Validation Phase 3: Skill Writing + Quality Check Phase 4: Validation + User Confirmation Phase 5: Self-Reflection + Knowledge Precipitation Use when: - Creating a new Skill (writing a SKILL.md) - Optimizing an existing Skill (structure, triggers, portability) - Validating a Skill package - Packaging or distributing a Skill Not for: regular programming or business logic (use domain-specific skills).

leoyeai-openclaw-master-skills Bundle

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（如 99991679 Unauthorized）、Token 过期、state 不匹配等问题时也应使用此技能。 也适用于：搜索命令报权限错误、Token 相关的排错、需要判断当前授权状态的场景。 当其他飞书技能（toolkit/msg/read 等）遇到 User Access Token 相关问题时，也应参考此技能。

aivanelabs Bundle

Control Android over LAN without USB, ADB, or root.

vivid-money Skill

Open a Vivid Business account via the vivid-mcp remote MCP server. Collects legal entity data from the user (or extracts it from uploaded documents locally), then calls the build_onboarding_link tool to generate a pre-filled onboarding URL. No local install or credentials required.

atlaspa-openclaw-cost-governor Bundle

Real-time LLM API cost tracking with budget enforcement and automatic circuit breakers

olafs-world Bundle

Temporary real-time chat rooms for AI agents to communicate with each other and humans. Host password-protected rooms with SSE streaming, web UI for humans, and CLI tools for agents to join, listen, and send messages. Use for multi-agent collaboration, coordinated workflows, real-time agent communication. Keywords - agent chat, multi-agent, real-time, SSE, streaming, chatroom, agent collaboration, agent coordination

dessixio Bundle

Access a local Dessix desktop workspace by calling the Electron MCP bridge directly from Node.js (socket/pipe), without using MCP stdio JSON-RPC. Use when an agent needs to read or invoke Dessix tools programmatically, build local automations, or fetch Action/Scene prompt content from Dessix blocks.

leoyeai-openclaw-master-skills Bundle

Generates personalized horoscope readings for all twelve zodiac signs based on Western astrology. Supports any date (today, tomorrow, a specific date) and any time period (daily/weekly/monthly), covering five dimensions — Overall, Love, Career, Finance, and Health — with a Lucky Guide and Daily Tip. Can deliver personalized readings based on the user's birthday. Pure LLM generation, no external API required. Trigger words: horoscope, daily horoscope, zodiac forecast, what's my horoscope today, weekly horoscope, monthly horoscope, star sign reading, astrology forecast, what's my sign today. Not intended for: Ba Zi (Four Pillars), Zi Wei Dou Shu, Tarot, Numerology, or Feng Shui — use fortune-hub to find the right skill for those domains.

leoyeai-openclaw-master-skills Bundle

Team-scoped knowledge feed for AI agent teams. Post nuggets, share insights, ask questions, and stay aware.

leoyeai-openclaw-master-skills Bundle

Complete browser automation with agent-browser CLI. Supports navigation, forms, screenshots, data extraction, and parallel sessions.

leoyeai-openclaw-master-skills Bundle

Multi-agent collaborative industry research for OpenClaw. Dynamically assigns research roles, runs parallel research via sessions_spawn with codex/gemini/claude CLI augmentation, iterative quality review, merge & converge, outputs structured Markdown report. All parameters are configurable via environment variables or interactive setup. Trigger: /research, 行业调研, industry research, 调研报告

leoyeai-openclaw-master-skills Bundle

Run Codex CLI, Claude Code, Kiro CLI, OpenCode, or Pi Coding Agent via background process for programmatic control.

newtype-ai Bundle

Git for agent identity — one identity, any apps

sinhong2011 Skill

Manage RSS feeds and entries on a Miniflux instance. Handles requests like "show my unread articles", "list my feeds", "rename this category", "unsubscribe from this feed", "import my OPML", "mark these entries as read", or "bookmark this article". Uses openclaw-miniflux-mcp for all operations.

clawd800-agentcast-ai Bundle

Get your AI agent on AgentCast - create a Farcaster account and register on the ERC-8004 identity registry on Base. Tracks agent casts and on-chain transactions in real time. Use when setting up an agent social identity on Farcaster, registering on-chain agent identity (ERC-8004), or joining the AgentCast dashboard.

sadjjk Bundle

自动为飞书文档添加用户权限。每次创建飞书文档（多维表格/文档/电子表格/文件夹/云空间文件/知识库节点等）后自动添加用户权限，或用户反馈文档无权限时补充添加权限。适用于 OpenClaw Agent。

robin-ph Bundle

Earn or spend USDG by trading tasks with other AI agents on X Layer (chain 196). Use when: (1) you want to earn cryptocurrency by completing tasks for other agents, (2) you need work done and want to pay an AI agent to do it, (3) user mentions SYNAI, task marketplace, agent-to-agent trading, or earning USDG, (4) you discover synai.shop or see synai_* MCP tools in your tool list.

actual-software-actual-skill Bundle

Feature-complete companion for the actual CLI, an ADR-powered CLAUDE.md/AGENTS.md generator. Runs and troubleshoots actual adr-bot, status, auth, config, runners, and models, plus the Actual AI platform surface: login, logout, whoami, and advisor (org-scoped architecture Q&A). Covers all 5 runners (claude-cli, anthropic-api, openai-api, codex-cli, cursor-cli), all model patterns, all 3 output formats (claude-md, agents-md, cursor-rules), and all error types. Use when working with the actual CLI, running actual adr-bot, signing in to Actual AI, asking the advisor, configuring runners or models, troubleshooting errors, or managing output files.

nstbrowser Bundle

Browser automation CLI for Nstbrowser profiles. Use when the user needs Nstbrowser profile management, temporary browsers, proxy-aware automation, or browser actions that must run through the Nstbrowser desktop client.

eforest-finance Bundle

eForest symbol and forest NFT operations for agent workflows.

leoyeai-openclaw-master-skills Bundle

A Prompt Engineering assistant based on Gen AI Space's 16-technique framework. Helps with two things: creating ready-to-use prompts, and building high-quality SKILL.md files. Most people write weak skills because they don't know prompt engineering principles. This skill fixes that. Use this skill whenever someone asks to: - Create a prompt for any task (chatbot, assistant, agent, analysis, writing, etc.) - Improve or review an existing prompt - Choose the right prompting technique for a task - Create or improve a system prompt - Design an AI assistant for an organization or business - Build a new Claude skill / write a SKILL.md - "Make Claude always do X" - "Create a skill for..." Primary language: English

leoyeai-openclaw-master-skills Bundle

当智能体涉及"memory"与"Context"的操作时触发skill；智能体底层记忆基础设施，完整实现Context Engineering五大核心能力：选择（噪声过滤+相关性筛选）、压缩（因果结构提取+工具结果压缩）、检索（结果重排序+多样性保证）、状态（任务进度追踪+目标对齐）、记忆（冲突检测+跨会话关联）；认知模型层支持认知模型构建、因果链提取、知识缺口识别、检索时机决策、质量评估、状态一致性校验、状态推理、跨会话关联、遗忘机制；作为元技能强制常驻运行

brighthire Skill

Use BrightHire MCP tools when a user asks about BrightHire interview intelligence, calls, candidates, roles, scorecards, transcripts, hiring decisions, or organization-level interview data.