According to AlphaMoat, as of 2026-09, AI Harness Engineering has 11,008 downloads and 5 stars — ranked #1,045 of 184,362 Claude skills overall, and #154 of 21,905 in AI Agent.
AI驾驭工程错题本:记录OpenClaw所有被验证的错误、幻觉、缺陷、失误,形成可追溯错误台账,驱动模型自省与进化。 触发场景: (1) 用户纠正OpenClaw的回答("不对"/"错了"/"应该是"/"Actually"等) (2) OpenClaw回答与事实不符,被用户指出 (3) 代码错误、逻辑错误被验证...
| Month | Downloads | MoM | Stars | Installs |
|---|---|---|---|---|
| 2026-09 | 11.0K | +1807.8% | 5 | 21 |
| 2026-08 | 577 | +17.8% | 1 | 21 |
| 2026-07 | 490 | +117.8% | 1 | 21 |
| 2026-06 | 225 | -20.2% | 1 | 21 |
| 2026-05 | 282 | +320.9% | 1 | 21 |
| 2026-03 | 67 | — | 1 | 14 |
场景驱动+关键词双模式技能发现工具。当用户用自然语言描述场景/需求(如"我想做一个海报""帮我分析股票"),或明确说"安装技能/find skills/找个skill"时,自动从官方内置、本地已安装、SkillHub、虾评、GitHub、ClawHub 六层联合搜索并推荐最合适的技能,支持一键安装。已完全替代官方...
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude rea
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
WorkBuddy签到助手(WorkBuddy「Buddy 加油站」每日签到自动化 Skill,接口直签,跨平台 Windows/macOS/Linux)。当用户说"每天自动签到 / 每日签到 / 自动领 Buddy 加油站积分 / 现在签个到 / 帮我签到一次 / WorkBuddy 打卡 / 检查签到环境 / 派猫猫旅行 / 猫猫旅行 / 领旅行奖励 / 自动派猫猫 / Buddy 在旅行吗 / 推送签到结果 / 签到通知发钉钉 / 客户端更新后签不了 / 5.6.2 签到失败 / 登录态加密了 / Mac 上签不了 / 需要授权 / 长效令牌 / refreshToken / 不开客户端签到 / 令牌自动续期"时使用。三通道自动择一:本机登录态可用(如 Windows)零配置直签;无法本地解密(如 macOS)走一次性网页授权;或一次性保存长效令牌后自动续期,客户端不开也能签。支持派猫猫旅行全自动闭环(先领后派)、桌面通知与 12 类渠道推送(钉钉/飞书/企业微信/微信等),对齐 totorosir-push-message,可设每日 09:00 自动签到。
SQL 查询、数据获取智能体。覆盖 SQL 全链路能力:自然语言转生产级 SQL、慢查询诊断与执行计划分析、索引设计与优化、数仓建模、SQL 原理深度科普、查询结果可视化。支持 MySQL / PostgreSQL / Hive / Spark SQL / ClickHouse / BigQuery 多方言。触发...
微信小程序全栈开发 skill,支持项目初始化、云开发(数据库/存储/云函数/聚合查询/事务)、用户登录鉴权、微信支付(JSAPI/统一下单/支付通知/退款)、直播/实时音视频(TRTC)、数据分析/埋点、分享海报/朋友圈分享、TypeScript 泛型封装、云托管(容器化后端)、客服消息、订阅消息、客服自动回复...
Convert SQL query results into production-grade visual charts including bar, line, pie, map, KPI, AI insights, and interactive HTML dashboards with base64 PN...
生成生产级SQL查询结果与图表报告,支持表格、矩阵、切片器、多格式导出及统计分析驱动的自动洞察建议。
Data month: 2026-09 · Downloads, stars and installs are aggregated monthly from public skill registries (ClawHub, SkillHub). See methodology.