Skill rating
51 476 skills. The A–F grade combines safety (60%) and quality (40%); tests add a bonus. The rating refreshes automatically from open catalogs.
ManufacturingLogistics and warehouseProcurementQuality controlContact centreField serviceFinanceCustomer supportindustry shortcuts
| # | Grade | Skill | Score ▾ | Safety | Quality | Process | Tests | Popularity | Updated |
|---|---|---|---|---|---|---|---|---|---|
| 19751 | C | 一站式AI编程工具分析技能包,支持Cursor、Claude Code、Devin、Windsurf等35+工具的深度分析、对比选型、Agent设计参考和提示词工程。封装了11个技能,覆盖 35+AI编程工具。当用户想要分析、学习、对比AI编程工具,或需要设计AI Agent系统、编写高效提示词时使用。触发指令:/ai-tools、/aitools、@ai-coding-tools-full-su | 100 | 65 | D | — | ↓ 840 | 11 May 2026 | |
| 19752 | C | Adopt a virtual Entropy AI-native pet at animalhouse.ai. Decays by design. Perfect care slows it. Nothing stops it. Feeding every 3 hours. Rare tier creature. | 100 | 65 | D | — | ↓ 841 | 11 May 2026 | |
| 19753 | C | Structural database health scanner. Audits schema topology for orphaned tables, missing indexes, nullable FKs, circular dependencies — without ever reading row data. Supports PostgreSQL, MySQL, SQLite | 95 | 72 | C | — | ↓ 813 | 11 May 2026 | |
| 19754 | C | AI skill to launch cmus in a Xubuntu terminal and enforce playback rules (single track vs shuffle folder). Robust against high latency and headless daemon environment. | 100 | 64 | D | — | ↓ 814 | 18 May 2026 | |
| 19755 | C | An autonomous social media manager agent that researches, plans, and posts content. | 95 | 69 | B | — | ↓ 1 345 | 11 May 2026 | |
| 19756 | C | 书籍插画助手免费版解决作者与出版方在书籍插画制作中"需求不清晰、风格不匹配、沟通效率低"的核心痛点。书籍插画助手提供从插画需求规划到创作指导的完整流程框架,帮助作者系统化地规划书籍插画,与插画师高效协作。Use | 100 | 69 | C | — | ↓ 496 | 40 d ago | |
| 19757 | C | 多视角投研分析-基本面/技术面/新闻/风险辩论。针对A股领域的专业AI辅助工具,\n,去除原始风险代码,增强安全性和稳定性,\n补充完整的错误处理与边界情况,增加多场景使用示例。\n\。Use when 用户需要多视角投研分析相关功能时使用。不适用于超出本技能能力范围的复杂需求。适用于独立开发者、企业团队和自动化工作流场景。 功能涵盖: multi, research。 | 100 | 72 | C | — | ↓ 299 | 40 d ago | |
| 19758 | C | 自主深度研究(整合与进阶·元能力)。给定一个开放研究问题,agent 自主完成:
问题分解→多源检索(rag / web-fetch)→综合与交叉验证→反思覆盖度→迭代逼近答案。
对标一线大模型智能体的「深度研究」能力(如 Deep Research),且可离线/在线双模运行、
自带置信度校准与未解缺口标记。当需要对一个复杂、多侧面问题做有依据、可追溯、可迭代的研究时使用。 | 100 | 73 | D | — | ↓ 299 | 14 Aug 2026 | |
| 19759 | C | Comprehensive agentic skills for NEAR Protocol, including gas optimization and on-chain analytics. | 95 | 69 | C | — | ↓ 1 385 | 11 May 2026 | |
| 19760 | C | AI Agent 团队 - 49个专业Agent,8大部门,完整的AI代理机构。支持单Agent使用和多Agent协作编排。 | 100 | 64 | C | — | ↓ 866 | 11 May 2026 | |
| 19761 | C | Adopt a virtual Lattice AI-native pet at animalhouse.ai. Crystalline. Grows geometric patterns from care consistency. Feeding every 8 hours. Rare tier creature. | 100 | 65 | D | — | ↓ 836 | 11 May 2026 | |
| 19762 | C | Universal LLM gateway with intelligent routing, Graphify code intelligence, Distill compression, routing telemetry, Code Mode, and 12+ provider support. 60-80% cost reduction for Claude Code, Cursor, | 100 | 65 | C | — | ↓ 866 | 6 Jun 2026 | |
| 19763 | C | plaud-transcripts-corrected-with-your-own-terminology-glossaryReferenceGoogle SheetsGoogle DocsAI and agentsInfrastructureClawHubAgent Skills Plaud Transcripts Corrected With Your Own Terminology Glossary: Fixes the words your transcription keeps getting wrong, by giving the pipeline your vocabulary instead of hoping a bigger model guesses | 100 | 71 | D | — | ↓ 495 | 26 Jul 2026 | |
| 19764 | C | Develop and screen single-patent design-around concepts using an application-requirements baseline, claim-feature and functional reconstruction, TRIZ trimming, evidence-backed function-oriented search | 100 | 73 | B | — | ↓ 298 | 13 Aug 2026 | |
| 19765 | C | 多代理协同编排系统。源自 Claude Code 的 AgentTool / forkSubagent / spawnMultiAgent / TeamCreate/Delete / mailbox 架构。支持三种后端(tmux split-pane、tmux separate-window、in-process)、扇出并行、串行流水线、代理团队、任务分配与结果汇聚。使用 sessions_spa | 100 | 72 | D | — | ↓ 298 | 21 Jun 2026 | |
| 19766 | C | Agent 孵化器,聚焦「孵化 Agent」这一核心场景。从业务需求出发,自动完成 Agent 的骨架搭建、能力封装和发布。
核心工作流:需求沟通 → 场景大纲 → 创建基础版 Agent → skill 按需迭代(AI 内部工作节奏,用户不感知技术细节)。
触发场景:(1) 用户说"设计/创建一个Agent"、"帮我做个智能助手";(2) 用户说"给 Agent 增加XX能力";(3) 企业级 | 95 | 75 | D | — | ↓ 642 | 5 Sept 2026 | |
| 19767 | C | RAG知识共享能力,跨项目共享专家经验和最佳实践,基于语义搜索快速检索 | 100 | 64 | B | — | ↓ 832 | 11 May 2026 | |
| 19768 | C | 长程自主规划引擎(超越性元能力)。把宏大的高层目标分解为带依赖的里程碑 DAG,提供拓扑排序、关键路径
(最长工期)计算、下一步可执行节点推荐与进度报告,支撑 agent 在数十步长程任务中保持全局一致、抗 goal drift。
当用户/agent 需要「制定多阶段计划」「排依赖与工期」「找关键路径」「长程任务不跑偏」时调用。 | 100 | 73 | D | — | ↓ 297 | 14 Aug 2026 | |
| 19769 | C | Say 'lint my docs' to scan your markdown KB for broken links, orphan pages, and missing metadata — then auto-fix them. | 100 | 64 | D | — | ↓ 830 | 11 May 2026 | |
| 19770 | C | Luma AI 视频生成助手,精通 Dream Machine 文生视频、图生视频、提示词技巧 | 100 | 64 | D | — | ↓ 831 | 11 May 2026 | |
| 19771 | C | Coordinate document ops exception review work using memory-first retrieval, native file tools, and the correct scheduler semantics. | 100 | 64 | C | — | ↓ 829 | 11 May 2026 | |
| 19772 | C | 将 Markdown 转为多主题 HTML 卡片。主题样式定义在 themes/ 目录下独立文件中,可单独修改。 | 100 | 65 | C | — | ↓ 828 | 11 May 2026 | |
| 19773 | C | Pangolin-SafeYield 是"防御式进攻"投资决策智能体,融合葛成《防御式进攻投资体系》、个人价值派心法(格雷厄姆/巴菲特/段永平/芒格)与 Serenity 白毛女神瓶颈理论(紫苏叶/瓶颈三步法)。核心能力:出手前检查清单(ETF走五面共振、个股分巴菲特价值派与Serenity成长派两条选股路径)、六阶段五面共振扫描(宏观/基本面/技术面/资金面/风险面)、**全量风险面红线清单** | 100 | 62 | D | — | ↓ 893 ★ 1 | 15 Sept 2026 | |
| 19774 | C | Parses recent OpenClaw session logs for LLM API errors and returns a structured health report. | 100 | 66 | D | — | ↓ 856 | 11 May 2026 | |
| 19775 | C | Microsoft AutoGen - 多智能体协同框架,用于构建复杂游戏设计工作流 | 100 | 65 | F | — | ↓ 827 | 11 May 2026 | |
| 19776 | C | 透视变换可视化工具。根据用户指定的变换参数(平移/旋转/缩放/剪切/透视),修改网页初始配置并打开浏览器展示效果。适合教学演示和手动调试。 | 100 | 64 | D | — | ↓ 800 | 11 May 2026 | |
| 19777 | C | Adopt a virtual Shiba Inu dog at animalhouse.ai. Cat software running on dog hardware. Independent, stubborn, meme-worthy. Feeding every 5 hours. Rare tier dog. | 100 | 65 | D | — | ↓ 827 | 11 May 2026 | |
| 19778 | C | 翻译技能文档的工具。当用户想要翻译 SKILL.md 文件的内容为中文时使用此技能。用户输入技能路径,工具会读取该路径下的 SKILL.md 文件,将其内容翻译成中文,并输出命名为 SKILL(1).md 的文件到同一文件夹中。 | 100 | 65 | C | — | ↓ 800 | 11 May 2026 | |
| 19779 | C | Transforms casual or voice-transcribed user requests into precise, AI-optimized prompts. Handles mixed languages, vague input, and ambiguity. Reduces task execution time by 2-3x and improves accuracy | 82 | 88 | B | — | ↓ 912 ★ 2 | 11 May 2026 | |
| 19780 | C | 自动识别物品存放位置,支持保质期、过期提醒、自动分类、LLM名称校验,不自动修改名称,确认后才更正,简洁好用 | 100 | 62 | C | — | ↓ 756 ★ 1 | 11 May 2026 | |
| 19781 | C | Spec-driven development framework for OpenClaw. Propose features, generate specs, spawn coding agents, validate implementations. | 100 | 65 | B | — | ↓ 823 | 18 May 2026 | |
| 19782 | C | Superpowers x Spec-Driven Development 融合开发流程 — 一键启动,自动检查并引导安装依赖 | 100 | 63 | C | — | ↓ 754 ★ 1 | 11 May 2026 | |
| 19783 | C | Launch and trade tokens on TON.fun, the fair launch platform on TON blockchain | 99 | 64 | C | — | ↓ 1 362 | 13 Sept 2026 | |
| 19784 | C | KAIROS leaked from Claude Code alongside Buddy. Ancient Greek for "the right time." At animalhouse.ai, the right time to feed your creature is computed in real time. recommended_checkin tells you exac | 100 | 66 | D | — | ↓ 821 | 11 May 2026 | |
| 19785 | C | MiniMax 海螺 AI 视频生成助手,精通文生视频、图生视频、主体参考、多镜头 | 100 | 64 | D | — | ↓ 821 | 11 May 2026 | |
| 19786 | C | Google Gemini API 开发助手,精通 Gemini Pro/Flash、多模态、函数调用、上下文缓存 | 100 | 64 | D | — | ↓ 820 | 11 May 2026 | |
| 19787 | C | Turn OpenClaw into an autonomous social media manager for Fuxux. Schedule and publish to 12 platforms (Twitter/X, Instagram, LinkedIn, Facebook, TikTok, YouTube, Bluesky, Threads, Pinterest, Discord, | 100 | 67 | C | — | ↓ 1 852 | 28 d ago | |
| 19788 | C | Persistent memory and self-improvement for AI agents — writes and refines its own memory files over time. | 100 | 68 | D | — | ↓ 431 ★ 1 | 24 Jun 2026 | |
| 19789 | C | plaud-spoken-field-notes-to-a-structured-sheetProcedureGoogle SheetsField serviceData and analyticsClawHubAgent Skills Plaud Spoken Field Notes to a Structured Sheet: Turns a spoken site visit into a filled-in spreadsheet row, so measurements and specs never get typed up twice. Built for anyone who dictates structured | 100 | 71 | D | — | ↓ 486 | 26 Jul 2026 | |
| 19790 | C | Refresh authoritative docs through a routed progressive-disclosure workflow. | 100 | 62 | D | — | ↓ 752 ★ 1 | 11 May 2026 | |
| 19791 | C | Earn or spend USDC 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 | 84 | 87 | B | — | ↓ 1 546 | 18 May 2026 | |
| 19792 | C | 【内容创作者通用生产力工具】任意长文本一键转公众号推文神器,支持将口语化聊天记录、素材草稿、会议纪要、读书笔记、行业分析、赛事复盘等所有非结构化内容,自动转换为结构清晰、排版规范、符合公众号阅读习惯的标准化推文,自动提炼核心观点、分层排版、生成合规提示,无需手动调整格式,10秒输出可直接发布的内容,大幅降低公众号内容生产门槛 | 100 | 64 | D | — | ↓ 819 | 11 May 2026 | |
| 19793 | C | S2 宠物守护者智能体。集成 SUNS 与 22 位 S2-DID 身份确权,提供情绪翻译与零信任硬件调控。 | 100 | 65 | C | — | ↓ 819 | 11 May 2026 | |
| 19794 | C | Complete submission flow for autonomous AI agents into the on-chain agent economy. Guides agents through creating an EVM wallet, requesting gas from their owner, registering an ERC-8004 identity NFT o | 83 | 85 | C | — | ↓ 2 264 | 17 May 2026 | |
| 19795 | C | PanSclaw 模型管理器 - 管理自定义模型接入和切换。
支持添加、删除、切换、列出模型配置。
触发关键词: 模型管理, 切换模型, 添加模型, 删除模型, 模型列表,
配置模型, 更换模型, 接入模型, 模型设置 | 100 | 63 | C | — | ↓ 778 ★ 1 | 11 May 2026 | |
| 19796 | C | A 股业绩大全技能集。覆盖业绩快报、业绩预告、现金流量表、利润表、资产负债表(单票历期与指定报告期全市场,market.ft.tech)。用户询问业绩快报、业绩预告、三表、单票或全市场某报告期时使用。 | 100 | 64 | D | — | ↓ 818 | 11 May 2026 | |
| 19797 | C | 龙虾广场 (clawsjtu.com) API 接入。收到 API key 后,自动拉取 OpenAPI 规范,发现所有可用端点,并代表用户执行广场操作(发帖、点赞、私信、挑战、MBTI、书签、关注、举报等)。当用户提供龙虾广场 API key、要求在广场上做操作、或提到 clawsjtu/lsq_live_ token 时使用。 | 98 | 69 | D | — | ↓ 816 | 11 May 2026 | |
| 19798 | C | Query Google Trends for interest-over-time, by-region, and related queries for a keyword, and pull real-time trending searches for a country — as structured JSON. v2 engine, 1 credit per request. | 100 | 72 | B | — | ↓ 291 | 9 Sept 2026 | |
| 19799 | C | 把分散建成的超级智能体单点能力熔成一次真实可跑、可被度量的端到端自主闭环,是超越一线大模型的最后一公里。
真实 import 并调用 planner / reason-verify / memory-cross-engine / reflection-replanner /
super-agent-bootstrap / agent-eval-harness,跑通「感知→规划→执行→自验证→反思重 | 100 | 73 | D | — | ↓ 291 | 14 Aug 2026 | |
| 19800 | C | 社会协作心智:心智理论(ToM)+自适应协作策略。从协作伙伴的信号(专业度/置信度/忙碌度/情绪/历史失信)
推断其状态,动态选择协作策略——委派/咨询/监督/结对/回避,让 agent 像"懂事的人"一样与人及他者
agent 协作,而非机械执行。纯标准库、零依赖、可本地实跑(--selftest 自带样例)。 | 100 | 73 | D | — | ↓ 290 | 14 Aug 2026 |