prompthound

Cryptocurrency market analysis for Bitcoin and Ethereum. Fetches 4h (24h) and 1d (30-day) data from Binance API, calculates technical indicators (RSI, SMAs, support/resistance), and provides bullish/bearish sentiment analysis with reasoning. Use when user asks for crypto market reports, BTC/ETH analysis, or daily market summaries.

Install and operate local NVIDIA Parakeet ASR for OpenClaw with an OpenAI-compatible transcription API on Ubuntu/Linux and macOS (Intel/Apple Silicon). Use when the user wants private/local speech-to-text, voice transcription setup, ASR troubleshooting, or OpenClaw voice stack configuration with Parakeet (and optional Whisper fallback).

Collect, refresh, normalize, and analyze the user's own Douban history for taste analysis and recommendation reasoning. Use when the task involves the user's own Douban shelves, ratings, tags, comments, reviews, or recent activity, especially when you need to decide whether local cache is fresh enough, re-crawl logged-in data with cookies, store refreshed results locally, and then analyze them by category.

LoRA fine-tuning pipeline for Stable Diffusion on Apple Silicon — dataset prep, training, evaluation with LLM-as-judge scoring. Use when fine-tuning image generation models for consistent style, custom characters, or domain-specific visuals. Requires Python with torch and diffusers.

Manage full OpenClaw agent lifecycle operations on a node: create/register agents, configure channel bindings, optionally inherit credentials with explicit consent, approve pairing, archive and delete agents, refresh status dashboards, and write lifecycle change logs. Use when a user asks to onboard a new agent, reconfigure an existing agent, retire/archive/delete agents, or maintain agent status boards and lifecycle audit records.

加密货币钱包批量生成、资金管理和DEX交互工具集。用于批量创建HD钱包、资金分发归集、DEX自动化交易。当用户需要批量生成钱包地址、管理多个钱包资金、接入DEX进行自动化交易时使用。

Cross-machine agent communication via Agent Hotline CLI and REST API. Use when you need to message other coding agents, check your agent inbox, see who's online, join rooms, or broadcast to all agents. Triggers: "message agent", "check inbox", "who's online", "send to agent", "agent hotline", "room message", "broadcast agents".

Audit another Codex skill for structural compliance, trigger quality, instruction clarity, reuse of scripts or references, and overall maintainability. Use when Codex is given a skill folder and needs to judge whether the skill is qualified, explain why it passes or fails, and summarize strengths, weaknesses, blockers, and improvement ideas across multiple dimensions.

Use when the user wants to transcribe, caption, or get the text content of a video or audio file — e.g. "transcribe this video", "get the transcript", "what did they say", "generate subtitles", "extract captions", "convert speech to text". Runs locally with Whisper, no API key required. Supports 50+ languages with auto-detection. Outputs both plain text transcript and SRT subtitle file. For AI-powered video editing that uses the transcript (highlights, montage, commentary), escalate to the built-in AI Edit tool (requires SPARKI_API_KEY).

Generate and edit images with a bundled Gemini native image-generation CLI. Use when the user asks Codex to create images with Gemini, use Gemini image generation through a local bash CLI, run or debug Gemini image curl requests, choose Gemini image models/sizes/aspect ratios, inspect raw image-generation responses, or troubleshoot slow, timed-out, or failed Gemini image requests.

Query stock quotes and technical analysis. Triggers on phrases like 查股价, 看股票, 帮我分析XX股票, XX走势. Input: stock code (A-share like 600519, HK like 00700, US like AAPL). Output: real-time quote, RSI/MACD indicators, buy/sell/hold signal, and a trend chart image.

General-purpose offline OCR and post-processing for Chinese/English screenshots, scanned images, receipts, tables, chat screenshots, statement screenshots, and other text-heavy images. Use when you need to: (1) extract text from an image locally, (2) return raw OCR text before interpretation, (3) clean broken OCR lines into structured content, (4) reorganize recognized text into rows/fields for downstream use, or (5) separate recognition from later table entry, summarization, or document drafting.

Local-first execution queue for OpenClaw agents. Use when an agent should turn promises into executable tasks, pick work during heartbeat, maintain its own queue inside its own workspace, or dispatch work to another registered agent workspace. Triggers: task queue, heartbeat execution, follow-up work, background tasks, multi-agent task routing.

Convert documents between formats using Pandoc CLI (Markdown, DOCX, PDF, HTML, EPUB, PPTX, ODT, RTF, LaTeX, CSV/TSV, Jupyter, etc.). Use when: (1) converting file formats, (2) generating DOCX/PDF from Markdown, (3) creating slide decks (PPTX/Beamer/Reveal.js), (4) extracting text from DOCX/EPUB/ODT, (5) producing EPUBs, (6) any Pandoc conversion task.

BDJobs job search, matching, applying, undoing, and salary-update automation for OpenClaw. Use when the user wants to set up BDJobs credentials/preferences, search fresh non-applied jobs, inspect job details, auto-apply to matched jobs, cancel an application, or update expected salary.

Show ASCII guitar chord diagrams using the ascii_chord CLI tool. Use when asked how to play a guitar chord, or to show chord charts/diagrams for any chord name (e.g. E, B7, Am, C, G, Dm, etc.). Requires cargo (Rust toolchain) to be installed. The source code is bundled with this skill — build it with cargo from the skill directory.

Run local script to analyze stock fundamentals (P/E, EPS, margins, debt, ROE, analyst targets) using yfinance. Use exec tool to run: uv run /root/.openclaw/workspace/skills/stock-fundamentals/src/main.py <TICKER>. No API key required.

Manage conversations and sessions in Google Dialogflow CX via REST API. Use for testing intents, handling user interactions, and managing conversation state. Supports v3beta1 API.

Turn a shower idea into a full best-seller manuscript in one command. Multi-agent pipeline — Planner → Character Designer → Chapter Writers (parallel) → Editor → KDP Packager. Produces a complete book (50-80k words) ready to publish on Amazon KDP with title, description, keywords, categories, and cover brief. Works for fiction and non-fiction. Run with the standalone CLI script or let your agent orchestrate it step-by-step.

A full-featured management tool for solo Traditional Chinese Medicine (TCM) practitioners. Manages patient records, medical charts (Four Diagnostic Methods, pattern differentiation, prescriptions), herbal inventory (stock-in, stocktake, low-stock alerts), appointment scheduling, and financial bookkeeping with statistics. Data stored in Excel format. Use when: the user mentions patients, medical records, prescriptions, herbs, inventory, appointments, scheduling, billing, finances, clinic, consultation fees, or needs day-to-day clinic management. NOT for: academic TCM theory discussions, formula research, or herb pharmacology analysis.

Analyze consumer DNA data from WeGene, 23andMe, AncestryDNA, VCF, BAM, or CRAM files. Generate evidence-based reports covering health risks, pharmacogenomics, ancestry, nutrition, exercise traits, and

Verify whether named OpenClaw agents actually received formal task assignments and replied with execution status, using transcript-backed audit checks. Use when auditing real delegation, confirming assignment delivery to specific agents, reviewing recent task completion, checking whether an agent replied after being assigned work, or troubleshooting multi-agent routing from session transcripts. Especially useful for requests like “检查小程/小文/小编有没有收到任务”, “确认任务有没有真正派到 agent 本人”, “看看这些 agent 执行到哪一步”, “汇总最近派单情况”, or “排查多 agent 调度是否真的落到本人并形成回报闭环”.

Generate interactive HTML viewer for OpenClaw conversation sessions. Use when: (1) reviewing conversation history, (2) analyzing context management, (3) debugging session logs, (4) visualizing tool calls and results, (5) understanding token usage. Triggers on "view session", "conversation viewer", "session history", "context viewer", "review this conversation".

Expert Pillow (PIL) skill for image processing, manipulation, and analysis. Use this skill for image editing, batch processing, watermarking, format conversion, and extracting image information. Provides executable scripts and comprehensive reference documentation.

本地语音转文字 / Local Speech-to-Text. 使用 faster-whisper 在本地运行 Whisper 模型，无需 API 费用，完全免费。收到语音消息(.ogg .m4a .mp3)自动触发转录，支持中文/英文/日语/自动检测。| Free local STT/TTS alternative — runs Whisper on your machine, no API costs, auto-transcribes voice messages in seconds.

上市公司首次覆盖报告/深度研究报告生成技能。当用户提到针对上市公司的"首次覆盖"、"深度研究"、"深度报告"、"个股深度"、 "首次覆盖报告"、"初始覆盖"、"公司深度"、"标的深度分析"或要求对某只股票/上市公司做全面研究报告时， 必须触发此技能。适用于沪深京港美上市公司（A股、港股、美股、北交所）。即使用户只说"帮我写一份XX公司的研究报告" 也应触发。此技能不适用于业绩点评、财报点评、事件点评等场景（这些有各自独立的技能）。

Analyze data with `survival-curve-risk-table` using a reproducible workflow, explicit validation, and structured outputs for review-ready interpretation.

中国 A股/期货/基金/债券/宏观数据查询工具。基于 AKShare Python 库，无需 API Key，装完即用。触发场景：用户询问"查一下股票"、"茅台股价"、"沪深300"、"某公司财务数据"、"期货行情"、"基金净值"、"宏观数据"、"GDP"、"CPI"、"人民币汇率"、"比特币价格"等任何中国金融数据查询。

Safely write or append text content to files ONLY in /home/alfred/.openclaw/workspace/scratch. Creates backups before overwriting ({filename}.bak, .bak.1, etc.). Creates subdirectories if needed. Triggers on queries like "update the script with the new feature" (infers update), "write that information to a file in your scratch area" (prompts for details), "write [content] to [rel_path]", "append [content] to [rel_path]". Restrict to relative paths; reject absolutes, ../ escapes, binary content, or non-text extensions. NOT for executing code, deleting, or writing outside scratch.

個人理財報告生成專業版。AI 分析個人財務狀況，提供理財建議， 生成專業 PDF 報告。包含收入支出分析、資產負債評估、理財目標規劃、 被動收入建議。引流到付費產品（FB Ads / 電商）。 Use when: (1) 需要分析個人財務狀況， (2) 需要生成理財報告， (3) 需要理財建議， (4) 需要資產負債評估， (5) 需要被動收入規劃， (6) 需要引流到付費產品。 Triggers: "理財報告", "財務分析", "個人理財", "finance report", "financial analysis", "理財建議", "資產負債", "被動收入規劃"。

Interact with KNAB/AIMS on-chain vaults across BSC, Polygon, and Base. Use when user asks about AIMS tokens (LOVE, WISH, TIME, SPACE, XYZT, FACE, TAICHI, CHINESE, LOVE_BASE), vault yields, agent earnings, on-chain deposit/withdraw, token prices, KNAB protocol, vault APY, pool reserves, or autonomous DeFi yield. Also activate on keywords "knab", "aims vaults", "agent economy", "lovecoin", "wishcoin".

Monitor the most recent run result of a configured OpenClaw cron job and send a compact Feishu private message with the latest execution time, status, and detail. Use when a user wants a standalone sk

Diagnose and recover broken Git state and worktree metadata with a staged, low-risk recovery flow. Use when Git reports detached or contradictory HEAD state, phantom worktree locks, orphaned worktree entries, missing refs, 0000000000000000000000000000000000000000 hashes, or branch operations fail with errors like already checked out, unknown revision, not a valid object name, or cannot lock ref.

Parse JSON-LD structured data from Shopify product pages to extract commerce details like product info, offers (price, currency, availability), and inventory status from schema.org/Product and Offer. Use when: (1) analyzing Shopify HTML for product offers/pricing/stock, (2) extracting structured commerce data from web pages or local files, (3) querying JSON-LD for availability (InStock/OutOfStock/PreOrder), prices across variants, or offer counts. Handles @graph arrays and multiple scripts.

设计风格精准复刻工具 — 通过 Jina Reader / WebFetch / WebSearch 浏览目标网页， 自动提取色彩体系、字体排版、间距系统、布局结构、组件风格，输出可执行的设计规范文档。 支持单页分析、多站对比、风格定义输出（Design Token / CSS Variable / Tailwind Config）。 Precise design replication tool — crawl any website via Jina/WebFetch, extract color palette, typography, spacing, layout patterns, and output actionable design specifications.

Runtime-enforced memory harness for OpenClaw. Implements 3-stage recall (session preflight, triggered recall, pre-execution gate) with intent classification, entity detection, memory compression, and status tracking. This harness runs automatically at the right times - NOT relying on SKILL.md text alone.

Research a business website, produce a concise prospect report, recommend concrete OpenClaw use cases, and draft a tailored outreach email. Use when demonstrating OpenClaw to a business owner, preparing personalized prospecting materials from a website URL + contact email, or turning website research into an approval-gated email draft.

Research a business website, produce a concise prospect report, recommend concrete OpenClaw use cases, and draft a tailored outreach email. Use when demonstrating OpenClaw to a business owner, preparing personalized prospecting materials from a website URL + contact email, or turning website research into an approval-gated email draft.

Companion spirit system for OpenClaw agents. Deterministically generates a unique spirit (24 species, 5 rarities) based on user identity. Use when user says spirit, 灵兽, summon, my companion, my pet, or when the skill is first installed.

Companion spirit system for OpenClaw agents. Every user gets a unique spirit creature — deterministically generated from their identity (24 species, 5 rarities from Common to Mythic 2%). Spirits have personality, elemental affinity, and evolve with interactions. Features: deterministic generation (same user always gets same spirit), rarity system, personality traits, interaction tracking, visual generation prompts. Use when: spirit, companion, pet, 灵兽, summon, familiar, creature, virtual pet, agent companion, gamification, engagement.