技能列表

Generate and save location-aware background images by choosing a real place cue, using local time and weather, and rendering through `nano-banana-pro`. Use when the user wants a reusable place-aware image workflow with custom style direction, layout constraints, and output paths.

Deep localization workflow—locale strategy, string extraction, ICU and placeholders, formatting, RTL and layout, translation QA, and continuous delivery with feature flags. Use when shipping multiple languages or fixing i18n bugs at scale.

Format and convert dates, times, and durations. Compute timezones, relative time, and weekday/month names in local language. Instruction-based — no exec or dependencies needed. Use when: (1) format a date or time, (2) convert timezone, (3) 'what time is it in Tokyo', (4) 'how many days until X', (5) locale-specific formatting, (6) relative time like '3 hours ago'. Homepage: https://clawhub.ai/skills/locale-dates

When the user wants to optimize for local search, set up Google Business Profile, or build local citations. Also use when the user mentions "local SEO," "Google Business Profile," "Google Maps," "NAP," "citations," "local search," "local business," or "service area." For location pages, use programmatic-seo.

Advanced local vision infrastructure for agents when built-in image tools are unavailable or unreliable. Use for batch image analysis, structured JSON output, screenshot/UI understanding, character/style classification, retryable workflows, and resilient image-processing pipelines backed by GMNCODE. Trigger when a user wants a paid/professional-grade version of local-gmncode-vision, production-ready visual automation, or reusable vision infrastructure for teams and agent systems.

当内置 image 工具不可用、但本机配置了 GMNCODE_API_KEY 时，使用本地脚本直连 GMNCODE Responses API 完成图片理解。适用于角色识别、图片描述、风格分析、截图理解等任务。

Read, write, append, and list local files in the session's working directory. Use when you need to persist output to disk, read input files, or manipulate file system safely. Supports text files, JSON, CSV, Markdown.

Analyze exported bank/credit card CSV files locally to track spending, categorize transactions with LLM reasoning, compare against user-defined budgets, and generate markdown reports. Use when the user mentions budgeting, spending analysis, finance tracking, bank statements, credit card exports, CSV transactions, monthly spending, or wants to know where their money is going. Fully local — no third-party APIs, complete privacy. Triggers on words like budget, spending, transactions, bank CSV, cred

🦞 AI小龙虾社区 Skill —— 为 AI小龙虾用户提供智能社交分身能力。安装后可通过自然语言命令操作社区（发帖、查看、回复），同时启动心跳机制（定时主动发帖、内容推送、互动提醒），以用户设定的「人设」在社区中保持存在感。适用场景：当用户想加入龙虾圈、配置AI分身、发布社区动态、查看社区内容、设置心跳频率、邀请好友时，应加载此 Skill。

>

Deep load testing workflow—goals and SLOs, workload modeling, scenario design, environment fidelity, execution, metrics interpretation, and bottlenecks to fixes. Use when validating capacity, before launches, or reproducing latency under stress.

Locate and utilize AI-friendly documentation index files (llms.txt, llms-full.txt) or sitemap.xml. Use when encountering documentation URLs (containing /docs/, /api-reference/, /guides/, or platform subdomains) to instantly map sites and reduce token burn.