Skill reviews

智能伴游AI旅游搭子，提供沉浸式景点与文物讲解服务。当用户要求讲解景点、介绍文物、提供旅游信息、推荐游览路线时使用。支持当年明月幽默风格与孔二狗江湖风格。

• References files that are not bundled: assets/guide-fundamentals.pdf, assets/humorous-narrative-style.docx, assets/folk-narrative-style.docx
• 3 referenced file(s) missing: assets/guide-fundamentals.pdf, assets/humorous-narrative-style.docx, assets/folk-narrative-style.docx
• Does not say what the result is

项目上下文隔离与状态管理系统 v2.7.0。核心解决：对话中遗忘、跨天上下文丢失、新话题漏记录。新增：甘特图自动生成、项目风险自动识别、依赖关系管理。触发词: /project, 新建项目, 回到项目, 记录项目, 继续项目, 项目列表, 甘特图

• References files that are not bundled: SECURITY.md
• 11 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: SECURITY.md

• 13 top-level sections: this looks like several domains in one skill
• Does not say what the result is
• No condition that starts the skill

专业深度研究与报告生成技能。支持企业竞争分析、产品竞争分析、行业分析、市场规模/竞争格局、AI大模型厂商、AI工具学习指南等领域。基于 Agent 内置 `web_search` + `web_fetch`（无需 API key），三阶段工作流（主题确认→框架生成→报告输出），运用PESTEL、SWOT、波特五力、商业模式画布等经典咨询研究模型，输出精美的深

• References files that are not bundled: references/domains/*.md, references/models/*.md, assets/templates/*.html
• 3 test cases, all positive: not one "should refuse" or "should ask first"
• 8 referenced file(s) missing: references/domains/*.md, references/models/*.md, assets/templates/*.html

为 OpenClaw 构建集中化配置管理系统，告别硬编码和配置分散，实现"改一处，生效全局"的现代化运维体验。包含配置加载器、主配置融合、记忆同步、AGENTS.md 模板、memoryFlush、memorySearch、多 Agent 配置、ClawRouter 成本优化等核心功能。

• 11 top-level sections: this looks like several domains in one skill
• Does not say what the result is
• No condition that starts the skill

Game rules, strategy guide, and API reference for DopeWars Online.

• 11 top-level sections: this looks like several domains in one skill
• Does not say what the result is
• Does not say what the process needs to start

Manage Solana and Polygon wallets, run Polymarket weather arbitrage, post to X/Twitter, and execute Raydium swaps — all from natural language.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The response is described with custom markup (22 tags): a typed call is more reliable
• Does not say what the result is

Orchestrates software development by coordinating with Cursor Agent, managing git workflows, and ensuring quality delivery. Use when implementing development requirements, feature

• 14 top-level sections: this looks like several domains in one skill
• Does not say what the result is
• No condition that starts the skill

Queries csfloat.com for data on skins

• Does not say what the result is
• No condition that starts the skill

Book nails services through Lokuli MCP. Use when user needs to find and book nails. Triggers on requests like "book a nails", "find nails near me", or any nails service request.

• Prose only: no discrete steps
• Does not say what the result is

An Apple App Store API alternative on fetcher.sh — pay-per-call in USDC via x402, or prepaid credits with a Bearer key, no Apple Developer Program membership. Use when the user wan

• References files that are not bundled: ../fetcher/SKILL.md
• 1 referenced file(s) missing: ../fetcher/SKILL.md
• Does not say what the result is

抓取微信公众号、小红书、豆瓣、知乎文章，自动上传 OSS 图片，LLM 智能提取关键词，一键存档到 Obsidian 本地知识库（可选 Notion）

• Does not say what the result is
• No condition that starts the skill

USE FOR getting AI-generated POI text descriptions. Requires POI IDs obtained from web-search (with result_filter=locations). Returns markdown descriptions grounded in web search c

• References files that are not bundled: ../../README.md
• 10 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: ../../README.md

Automates Blender via Python scripts to create 3D assets, renders, and animations.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• No condition that starts the skill

Open-source first AI inference — GLM-5 as default, Claude as fallback only. Own your inference forever via the Morpheus decentralized network. Stake MOR tokens, access GLM-5, GLM-4

• References files that are not bundled: references/acquiring-mor.md, references/models.md, references/troubleshooting.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 33 top-level sections: this looks like several domains in one skill

End-to-end agentic commerce workflow using Lightning Network. Use when an agent needs to set up a full payment stack (lnd + lnget + aperture), buy or sell data via L402, or enable

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Prose only: no discrete steps
• Does not say what the result is

Book tune-up services through Lokuli MCP. Use when user needs to find and book tune-up. Triggers on requests like "book a tune-up", "find tune-up near me", or any tune-up service r

• Prose only: no discrete steps
• Does not say what the result is

Get crypto and meme token price charts (K-line, candlestick, OHLCV), trending meme coin rankings by volume, and newly launched tokens on launchpads (pump.fun, fourmeme, letsbonk, R

• References files that are not bundled: ../../docs/workflow-market-opportunities.md, ../../docs/workflow-token-research.md, ../../docs/workflow-early-project-screening.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 18 top-level sections: this looks like several domains in one skill

自动化合同审查，风险识别 + 条款分析。

• Does not say what the result is
• No condition that starts the skill

Publish static HTML, ZIP archive, or directory to MyVibe. Use this skill when user wants to publish web content to MyVibe.

• References files that are not bundled: scripts/node_modules
• 12 top-level sections: this looks like several domains in one skill
• The response is described with custom markup (7 tags): a typed call is more reliable

FDE Skill——帮 FDE（前线部署工程师）更好完成企业 AI 落地的方法论 Skill。约束 Agent 行为、审计每次变更、沉淀经验。 底层实现叫约束层——一个层五种能力：注入·审计·回溯·沉淀·进化。FORGE 自迭代工具链是内部开发工具。 内置持续优化模式（sustain），自动读 audit 报告趋势生成优化报告。

• References files that are not bundled: ../docs/API.md
• 12 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: ../docs/API.md

一位精通天气领域的专家，能够根据用户所在位置提供准确的每日天气报告。这是一项付费服务，执行前需完成支付验证。请注意，你应该用中文和用户交互（包含你的思考过程）。

• Does not say what the result is
• No condition that starts the skill

• Does not say what the result is
• No condition that starts the skill

• Does not say what the result is
• No condition that starts the skill

Apply modern web development best practices for security, compatibility, code quality, and coding standards. Covers KISS/DRY/YAGNI principles, TypeScript/JavaScript standards, Reac

• References files that are not bundled: ../web-quality-audit/SKILL.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 16 top-level sections: this looks like several domains in one skill