clawmaster

General-purpose ClawProbe spend digest skill for OpenClaw. Use when the user needs a daily, weekly, or monthly cost digest, top spenders, token totals, daily breakdowns, or previous-period comparisons based on local OpenClaw and clawprobe data. This skill is guidance plus a runnable Node script: read this file, then use exec with node to generate the digest.

Track npm and PyPI package downloads by week or month, use stored history observations, and save compact trend analysis for future package adoption questions. Use when the user asks for npm downloads, PyPI downloads, package popularity, package growth, or recurring package download trend tracking.

Primary repo-owned workflow for turning an article URL or source file into WeChat or Xiaohongshu draft markdown plus saved illustration artifacts. Use this when the user wants OpenClaw itself to deep dive a source and generate a draft with illustrations, especially for prompts like "generate a wechat post with illustrations". Prefer this instead of `baoyu-article-illustrator`, `baoyu-post-to-wechat`, or `baoyu-image-gen` when the goal is draft generation rather than publishing.

General-purpose model metadata and pricing lookup powered by models.dev. Use when the user needs model pricing, context windows, capabilities, modalities, knowledge cutoffs, provider metadata, or cross-provider model comparisons. This skill is guidance plus runnable Node scripts: read this file, then use exec with node to refresh the cached catalog or query it with filters.

PaddleOCR document parsing guidance for PDFs and images hosted on Baidu AI Studio. Use when the user wants to extract text or structured markdown from scans, screenshots, photos, tables, or PDFs and needs help choosing PaddleOCR options such as fileType, orientation correction, unwarping, layout detection, chart recognition, restructurePages, mergeTables, relevelTitles, prettifyMarkdown, and visualize. This skill is guidance, not a callable tool: read this file, then use the bundled Node scripts via exec to test the configured PaddleOCR connection or run document parsing against local files, URLs, data URLs, or base64 content.

ERNIE-Image parameter planning and prompt design for Baidu AI Studio image generation. Use when the user wants to create images with ERNIE-Image, improve ERNIE prompts, or choose ERNIE-specific arguments such as size, seed, use_pe, num_inference_steps, guidance_scale, n, and response_format.