Run any Skill in Manus
with one click

Run any Skill in Manus with one click

Data & AI

Discover comprehensive agent skills for data science, machine learning, and AI development. Our marketplace features tools for data analysis, ML model training, LLM integration, and data engineering pipelines. Perfect for data scientists, AI developers, and engineers building intelligent data-driven applications.

openclaw/openclaw

Use to talk to the Discord-backed OpenClaw agent/session; not for archive search.

openclaw/openclaw

Gemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP, or Gemma routing.

openclaw/openclaw

Local speech-to-text with the Whisper CLI (no API key).

openclaw/openclaw

ElevenLabs text-to-speech with mac-style say UX.

agent-harness-construction

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.

agent-introspection-debugging

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases.

ai-first-engineering

Engineering operating model for teams where AI agents generate a large share of implementation output.

agent-introspection-debugging

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.

Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.

continuous-learning

[OBSOLETO - usar continuous-learning-v2] Extractor de skill por hook Stop v1 heredado. v2 es un superconjunto estricto con aprendizaje basado en instintos, con alcance de proyecto y hooks confiables. No invocar v1; dirigir solicitudes de aprendizaje continuo, aprendizaje de sesión y extracción de patrones a continuous-learning-v2.

continuous-learning-v2

Sistema de aprendizaje basado en instintos que observa sesiones mediante hooks, crea instintos atómicos con puntuación de confianza y los evoluciona en skills/comandos/agentes. v2.1 agrega instintos con alcance de proyecto para prevenir contaminación entre proyectos.

autonomous-loops

自動Claude Codeループのパターンとアーキテクチャ — シンプルな順序パイプラインからRFC駆動マルチエージェントDAGシステムまで。

ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.

continuous-learning

Claude Codeセッションから再利用可能なパターンを自動的に抽出し、将来の使用のために学習済みスキルとして保存します。

continuous-learning-v2

フックを介してセッションを観察し、信頼度スコアリング付きのアトミックなインスティンクトを作成し、スキル/コマンド/エージェントに進化させるインスティンクトベースの学習システム。

openclaw-persona-forge

为 OpenClaw AI Agent 锻造完整的龙虾灵魂方案。根据用户偏好或随机抽卡，输出身份定位、灵魂描述(SOUL.md)、角色化底线规则、名字和头像生图提示词。如当前环境提供已审核的生图 skill，可自动生成统一风格头像图片。当用户需要创建、设计或定制 OpenClaw 龙虾灵魂时使用。不适用于：微调已有 SOUL.md、非 OpenClaw 平台的角色设计、纯工具型无性格 Agent。触发词：龙虾灵魂、虾魂、OpenClaw 灵魂、养虾灵魂、龙虾角色、龙虾定位、龙虾剧本杀角色、龙虾游戏角色、龙虾 NPC、龙虾性格、龙虾背景故事、 lobster soul、lobster character、抽卡、随机龙虾、龙虾 SOUL、gacha。

strategic-compact

任意の自動コンパクションではなく、タスクフェーズを通じてコンテキストを保持するための論理的な間隔での手動コンパクションを提案します。

고성능 분석 워크로드를 위한 ClickHouse 데이터베이스 패턴, 쿼리 최적화, 분석 및 데이터 엔지니어링 모범 사례.

continuous-learning-v2

훅을 통해 세션을 관찰하고, 신뢰도 점수가 있는 원자적 본능을 생성하며, 이를 스킬/명령어/에이전트로 진화시키는 본능 기반 학습 시스템. v2.1에서는 프로젝트 간 오염을 방지하기 위한 프로젝트 범위 본능이 추가되었습니다.

iterative-retrieval

서브에이전트 컨텍스트 문제를 해결하기 위한 점진적 컨텍스트 검색 개선 패턴

continuous-learning-v2

Hook'lar aracılığıyla oturumları gözlemleyen, güven skorlaması ile atomik instinct'ler oluşturan ve bunları skill/command/agent'lara evriltiren instinct tabanlı öğrenme sistemi. v2.1 çapraz proje kontaminasyonunu önlemek için proje kapsamlı instinct'ler ekler.

agent-introspection-debugging

针对AI代理故障的结构化自调试工作流程，包括捕获、诊断、受限恢复和内省报告。

ai-first-engineering

团队中人工智能代理生成大部分实施输出的工程运营模型。

ai-regression-testing

AI辅助开发的回归测试策略。沙盒模式API测试，无需依赖数据库，自动化的缺陷检查工作流程，以及捕捉AI盲点的模式，其中同一模型编写和审查代码。

architecture-decision-records

在Claude Code会话期间，将做出的架构决策捕获为结构化的架构决策记录（ADR）。自动检测决策时刻，记录上下文、考虑的替代方案和理由。维护一个ADR日志，以便未来的开发人员理解代码库为何以当前方式构建。

从真实的帖子、文章、发布说明、文档或网站文案中构建基于源材料的写作风格档案，然后在内容、外展和社交工作流中重复使用该档案。当用户希望保持声音一致性而不使用通用的AI写作套路时使用。

claude-devfleet

通过Claude DevFleet协调多智能体编码任务——规划项目、在隔离的工作树中并行调度智能体、监控进度并读取结构化报告。

ClickHouse数据库模式、查询优化、分析以及高性能分析工作负载的数据工程最佳实践。

continuous-learning-v2

基于本能的学习系统，通过钩子观察会话，创建带置信度评分的原子本能，并将其进化为技能/命令/代理。v2.1版本增加了项目范围的本能，以防止跨项目污染。

dashboard-builder

为 Grafana、SigNoz 等平台构建能够回答实际运维人员问题的监控仪表板。适用于将指标转化为可用的仪表板，而非华而不实的展示板。

使用此技能生成或审计设计系统，检查视觉一致性，并审查涉及样式的PR。

gan-style-harness

受GAN启发的生成器-评估器代理框架，用于自主构建高质量应用。基于Anthropic 2026年3月的框架设计论文。

healthcare-cdss-patterns

临床决策支持系统（CDSS）开发模式。药物相互作用检查、剂量验证、临床评分（NEWS2、qSOFA）、警报严重性分类以及集成到电子病历工作流程中。

inventory-demand-planning

为多地点零售商提供需求预测、安全库存优化、补货规划及促销提升估算的编码化专业知识。基于拥有15年以上管理数百个SKU经验的需求规划师的专业知识。包括预测方法选择、ABC/XYZ分析、季节性过渡管理及供应商谈判框架。适用于预测需求、设定安全库存、规划补货、管理促销或优化库存水平时使用。license: Apache-2.0

kotlin-exposed-patterns

JetBrains Exposed ORM 模式，包括 DSL 查询、DAO 模式、事务、HikariCP 连接池、Flyway 迁移和仓库模式。

ralphinho-rfc-pipeline

基于RFC驱动的多智能体DAG执行模式，包含质量门、合并队列和工作单元编排。

基于证据优先的仓库执行工作流，适用于ECC。当用户需要运行命令、检查仓库、调试CI失败或推送带有精确执行和验证证明的窄修复时使用。

token-budget-advisor

在回答前，为用户提供关于消耗多少响应深度的知情选择。当用户明确希望控制响应长度、深度或令牌预算时使用此技能。触发条件："token budget", "token count", "token usage", "token limit", "response length", "answer depth", "short version", "brief answer", "detailed answer", "exhaustive answer", "respuesta corta vs larga", "cuántos tokens", "ahorrar tokens", "responde al 50%", "dame la versión corta", "quiero controlar cuánto usas"，或用户明确要求控制答案大小或深度的清晰变体。不触发条件：用户已在当前会话中指定了级别（保持该级别），请求明显是单字答案，或"token"指代认证/会话/支付令牌而非响应大小。origin: community

ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.

continuous-learning

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.

continuous-learning-v2

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.

iterative-retrieval

Pattern for progressively refining context retrieval to solve the subagent context problem

content-hash-cache-pattern

Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.

blender-motion-state-inspection

Use this skill when inspecting Blender characters, rigs, poses, animation retargeting, ground contact, facing direction, or model-vs-motion alignment where screenshots alone are not enough.

claude-devfleet

Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.

Run any Skill with one click