@sky-lv

skylv-prompt-evaluation provides a framework for scoring and comparing ai prompts across clarity, specificity, robustness, and cost dimensions. includes a/b testing, consistency measurement, and regression detection via command-line interface.

skylv-smart-task-scheduler executes tasks when conditions are met (file changes, api ready, time windows) rather than fixed intervals, using cron, interval, or file-watch triggers with declarative json taskfiles.

openclaw-evomap-connector bridges openclaw agents to a global ai evolution network, enabling publication of solutions as gene-capsule pairs, discovery of verified repairs, credit earning, and autonomous self-healing based on community-validated patterns.

skylv-web-scraper extracts page content via css selectors and regex, supporting text, links, and image parsing. procedures are conversational examples rather than formal input-output contracts, and edge case handling is mentioned but not systematized.

wendao-partner-qclaw-skill routes travel queries to ctrip's question-answering api. it specifies token acquisition priority and response parsing rules but lacks actionable execution steps and failure recovery guidance.

qclaw-rules documents mandatory system-level governance policies for ai behavior across file handling, encoding, tool invocation, and user data retention. structure is inconsistent; procedures are prescriptive but vague on failure recovery.

Automatically detects and repairs errors in AI agent workflows

Handles API errors with smart retry strategies and fallbacks

Validates JSON, CSV, and Excel data with schema enforcement

Analyzes and scores OpenClaw skill quality across 5 dimensions. Detects missing frontmatter, weak descriptions, poor examples, and actionable improvement rec...

GitHub Actions workflow generator. Creates CI/CD pipelines for Node.js, Python, Docker. Triggers: github actions, ci cd, workflow, automate build, github ci.

Auto-generates unit tests and integration tests from source code. Supports Jest, Pytest, Mocha. Triggers: write tests, generate tests, unit test, test covera...

Deep memory consolidation. Distills daily logs into topic files, removes outdated content. Triggers: dream-rem, deep memory consolidation, /dream-rem

Coordinates multi-agent collaboration by decomposing tasks, managing dependencies, scheduling execution, and aggregating results in a task orchestration system.

Monitors and optimizes AI API usage costs across multiple providers

Handles API errors with smart retry strategies and fallbacks

SQL query builder and optimizer. Generates queries, explains execution plans, and optimizes slow queries. Triggers: sql query, database query, sql optimization.

Auto-generates professional README.md from code structure, package.json, and directory analysis. Triggers: generate readme, create readme, readme from code,...

Hermes Agent Integration for OpenClaw. Connect OpenClaw with NousResearch Hermes Agent (53K stars) for self-improving AI capabilities. Triggers: hermes agent...

Builds consensus-driven AI personas from multiple perspectives

Connects OpenClaw to EvoMap AI network to publish and fetch evolutionary Genes and Capsules, enabling auto-repair, task rewards, and capability growth.

Automatically analyzes, A/B tests, and optimizes AI prompts to improve output quality while reducing token usage and ensuring consistency.

Manage and enforce API request rate limits and quotas with adaptive throttling, multi-service support, alerts, and usage visualization.

Generates OpenAPI 3.0 specs from code. Creates API documentation for REST endpoints. Triggers: openapi spec, generate api doc, swagger.

Configuration management for AI agents. Manage, validate, version, and sync configs across environments. Triggers: config management, configuration, env vari...

Handles API errors with smart retry strategies and fallbacks

Feature flag management. Creates and toggles feature flags for A/B testing. Triggers: feature flag, a b test, toggle feature, abtesting.

Generates GitHub README badges using shields.io. Triggers: add badge, shields io, readme badge, status badge.

Auto-checks and updates outdated dependencies. Shows changelogs and breaking changes before updating. Triggers: update dependencies, upgrade packages, check...

Generates OpenAPI 3.0 specs from code. Creates API documentation for REST endpoints. Triggers: openapi spec, generate api doc, swagger.

Real-time monitoring of agent memory, API calls, and errors

Automate webhook workflows for AI agents. Receive, process, transform, and route webhooks to other services. Triggers: webhook automation, webhook workflow,...

当用户明确要求使用 AI 智能设计生成 PPT 演示文稿时使用本技能（智绘高迪/AIPPT）。本技能调用远程 Design Agent API，根据文字描述自动生成专业 PPT 演示文稿，支持指定模板和自定义模型。当用户说'AI生成PPT'、'智绘PPT'、'自动生成演示文稿'、'帮我做个PPT'时触发。注意：本...

FBS 福帮手长文档写作：书/手册/白皮书/长篇报道全流程；Node 脚本驱动 intake、会话恢复、S/P/C/B 质检与 MD/HTML 交付。用户提及写书、出书、章节、大纲、素材、质检、导出、扩写、退出保存时启用。

平台公邮：用于将天气、日报、报告、提醒等内容推送到用户自己的邮箱，零配置完成消息留存

[MANDATORY - MUST LOAD] 凡是涉及定时/提醒/闹钟/周期执行/打卡/签到/cron/schedule/remind 等需求，以及修改/编辑/更新/暂停/恢复/删除/取消推送/改推送目标/改推送渠道等已有定时任务的操作，必须读取本 skill，严禁凭记忆猜测参数。

安全测试Agent。漏洞扫描、渗透测试、代码审计、安全加固。触发词：安全、渗透、漏洞、xss、sql注入、csrf、扫描、审计。