Volatility Surface Modeling Tool: SVI Parameterization and No-Arbitrage Constraint Validation
This is the Volatility Surface Modeling Tool (v1.0.0) posted by @user_053d27d0 on the SkillHub community, categorized under professional, sourced from community, currently rated 100,000 with 908 downloads and 0 installs, and requires no API key. It targets two common challenges in options pricing and volatility research: backing out implied volatility from option quotes, and fitting discrete observation points into an SVI-parameterized surface while ensuring the parameters meet no-arbitrage constraints. Core features include Black–Scholes implied volatility back-out, SVI parameter calibration, no-arbitrage constraint checks, support for 50ETF and 300ETF options, and 3D surface visualization; the official description ties these into a pipeline: “back-out → calibrate → validate → visualize”. Based on this, the article outlines the capability list, data flow, and applicable scenarios, and notes caveats: the quality of observation points directly affects calibration results; if validation fails, users must decide how to handle it; the tool performs fitting and interpolation, not volatility forecasting. As a note, when writing this article, two attempts to fetch the official page failed, so no verifiable installation commands, directory structure, or configuration fields were obtained; the article only lists information confirmable from metadata. Please refer to the official page for installation commands and avoid copying commands from other Skills or circulated online. Official URL: https://www.skillhub.cn/skills/user_053d27d0/vol-surface-zx; API endpoint: https://api.skillhub.cn/user_053d27d0/vol-surface-zx
Read Moredsh-feiyu-kb: Turning a Local Markdown Knowledge Base into a Callable Tool for AI Models
dsh-feiyu-kb is a DSH plugin (v0.7.5) maintained by koishi-fumo-code that uses pure Markdown for knowledge bases and memory stores, exposing kb_* and mem_* tools to models. It supports ingestion from web pages, files, directories, and RSS feeds, along with a settings page, health checks, and session compression tuning. After installation, run install.mjs in the plugin directory and restart DSH to connect with video browsing plugins and QQ bridge. With no vector database or relational database dependencies, it's ideal for developers who want human-readable, git-friendly notes and cross-channel conversational knowledge accumulation and retrieval.
Read MoreTutu Ba: Hand-drawn Book Mind Maps & Animation
TuTuBa · Book Hand-Drawn Mind Map Animation is a community Skill on SkillHub (v1.5.0, content-creation category, no API key required). It takes a book title as input and outputs a hand-drawn style structured mind map along with an animated explanation featuring real human voiceovers. It covers content extraction, mind map construction, animated narration (hand-drawn style or rounded black-filled editorial illustrations + real human voiceovers), and workflow integration. Based on official documentation, this article introduces its positioning, core features, trigger scenarios, and precautions. The official installation command could not be verified; please refer to the official page for details.
Read MoreCanva: Programmatically Create and Export Designs with Connect API
Canva (@clawhub_abgohel/canva) is a SKILL.md-based Agent Skill released on ClawHub by abgohel (Version 1.0.0, Category: design-media, License: MIT-0). It creates, exports, and manages Canva designs via the Canva Connect API, programmatically generating social media posts, carousels, and graphics. The Skill provides capabilities such as listing designs, reading design details, generating designs by invoking autofills based on brand templates, initiating asynchronous export tasks (supporting PNG/JPG/PDF/MP4/GIF), uploading assets, and listing brand templates. Authentication uses OAuth 2.0; the Skill automatically refreshes tokens, which are stored in ~/.canva/tokens.json. The installation command is `openclaw skills install @abgohel/canva`. After installation, users must create a custom Integration on canva.com/developers and configure the CANVA_CLIENT_ID and CANVA_CLIENT_SECRET environment variables. It requires scopes such as `design:content`, `asset`, and `brandtemplate`. Most endpoints are rate-limited to 100 requests per minute, while uploads and exports are limited to 30 requests per minute. It is suitable for Agent workflows that have established brand templates and require batch production of social media assets.
Read Moredsh-model-auto-retry: Preventing DSH Agent Interruptions under 429 Rate Limiting
An introduction to the **dsh-model-auto-retry** workflow plugin, maintained by kocor01. Once the built-in `dsh-llm-retry` is exhausted, this plugin facilitates in-loop backoff retries specifically for HTTP 429 and `RATE_LIMIT` errors. If necessary, it automatically sends a follow-up prompt to resume execution after the Agent becomes idle. This document covers the **hybrid**, **in-loop**, and **continue** modes, the `cordis.patch.yml` configuration within profiles, installation commands via npm and GitHub, log prefixes, and e2e verification key points. It is designed for long-running tasks that frequently encounter provider rate limits, aiming to minimize the need for manual "continuation" commands.
Read MoreJinko WorkBuddy Daily Work Summary: Compile daily WorkBuddy usage into an HTML report and upload to Xiao Jing Le Xiang.
# Introduction People who use WorkBuddy for their daily work often have to perform the same task at the end of the day: compiling the sessions they initiated and the tasks they processed into a report, and then submitting it to Xiaojing Lexiang (Wei Renke). Manually reviewing sessions, piecing together HTML, and uploading to the platform are routine yet time-consuming steps. The Skill introduced below integrates this entire workflow: it automatically collects daily session data, generates an HTML-formatted work report, and uploads it to the Xiaojing Lexiang (Wei Renke) platform. # What is this `Jinke workbuddy Daily Work Summary` is a community-sourced Skill, located at `@user_b7c5e8cd/work-summary`, version 1.0.0, categorized under `office-efficiency`, and published by `
Read Moredsh-longpress-shot: Long-press to select a screenshot area and insert it into the input box in DSH
dsh-longpress-shot is a DSH client plugin maintained by kkkkk-tubu: on Windows, long-pressing the left mouse button for about 550ms enters box selection mode; after dragging the region, a PNG is generated, saved to ~/.dsh/longpress-shots/, and written to the clipboard. The preview card supports "Send to input box", "Save as", and "Copy path". The install command is `dsh plugin add dsh-longpress-shot`; DSH must be restarted after installation. There is no navbar entry, and the plugin works globally. Screen capture is performed via the host PowerShell GDI and is unavailable on non-Windows systems.
Read MoreFinance: Terminal-based Market Trend Tracking Skill
finance is a ClawHub Skill based on the SKILL.md format, located at @clawhub_anton-roos/finance. Version v1.1.2, published by anton-roos, licensed under MIT-0, and has passed security audits. It is positioned as a market data query tool, covering stocks, ETFs, indices, cryptocurrency (subject to provider support), and forex pairs. Internally, it features caching and provider failover, suitable for high-frequency, lightweight queries such as "What's the current price?", "30-day historical series", or "Summary performance of a watchlist". The default path is usable with zero configuration: stocks use Yahoo Finance (yfinance), and forex uses the ExchangeRate-API Open Access endpoint, both requiring no API keys. Installation is done via openclaw skills install, depending on a Python virtual environment plus requirements.txt, with the cache directory set as .cache/finance. The article introduces its core features, installation and activation methods, typical command usage provided by SKILL.md, and notes such as daily updates for forex, possible rate limiting by Yahoo's unofficial interface, and crypto support being best-effort.
Read Moredownload-wechat-channels: Download WeChat Channels share links locally
**download-wechat-channels** is a WeChat Channels downloading Skill published by SkillHub community user **user_8171c382**. Version 1.0.0, categorized under **dev-programming**, it is sourced from the community and tagged with **requires_api_key=false**. This Skill streamlines the workflow into a single step: "Copy Link → Display Open Source Notice → Scan to Log In → Save to Disk." It identifies WeChat Channels share text or `weixin.qq.com/sph` links and proceeds as follows: first, it displays a free open-source notification for "镇涛 AI 实战笔记" (Zhentao AI Practical Notes). If the user is not logged in, it automatically opens the official Tencent Yuanbao login page for manual QR code scanning; if already logged in, it initiates the download directly. Supported on macOS and Windows, it offers resolution options including Auto, Original, H.264, and H.265. The listing displays a rating of 100,000 and 1,082 downloads. It is suitable for scenarios requiring the backup of WeChat Channels content. Note that first-time usage requires the user to scan the QR code personally, and Linux is not listed as a supported operating system.
Read Moredsh-deep-purge: Six Disk Cleanup Locations to Completely Remove Sessions in DSH
DSH archived sessions do not remove transcripts, indexes, or the billing ledger. The community plugin dsh-deep-purge (kkkkk-tubu, admin-security) cleans up six on-disk locations related to a session ID in one pass on Windows. Its panel supports Dry run, requires typing DELETE to confirm, can create backups, and can auto-restart DSH. The PowerShell script provides -List, -Execute, and -Restore switches. It notes that workspace.json and index.db must be deleted only after quitting DSH, and lists applicable scenarios along with notes on timeouts, dual-window considerations, and more. Install: dsh plugin add dsh-deep-purge. MIT 1.0.0.
Read MoreCompliance Review: A Skill for Structured Compliance Health Checks on Administrative Documents
"Compliance Review" is a professional Skill published by community poster @user_b0d498a1, version 1.0.0, built on the general SKILL.md format and requires no API key. It targets implementation plans, meeting minutes, and administrative action documents from government and public administrative institutions, conducting a compliance check across three dimensions—financial auditing, legal compliance, and disciplinary standards—and produces a structured review report. It is applicable to scenarios such as compliance self-inspections by administrative agencies, ex-ante audit checks, initial screening of disciplinary inspection and supervision leads, and compliance assessments of major projects. The article describes its core features, the coordinate-based activation method, typical usage, and limitations, including the need for manual review and its non-applicability to corporate contracts.
Read MoreAntigravity Goes Next for DSH: Connecting Local Antigravity to DSH Agent Loop
Antigravity Next for DSH (npm: agy-next) is an unofficial DSH model provider maintained by kizaki-R, with the provider id agy-next. It resolves OAuth clients from the local Antigravity desktop or IDE, eliminating the need to create entries in the Google Cloud Console. It supports multi-account pooling, quota telemetry, and cordis.yml configuration, and works with models such as Gemini 4 Argon, Gemini 3/2.5, and Claude. Installation can be done by searching for agy-next in the DSH Marketplace, or by running npm install agy-next@latest in ~/.dsh/profiles/desktop. It requires DSH 0.1.5~0.2.x, Node >=20, and the locally installed official Antigravity. Credentials are stored in DSH_HOME/storages/agy-next-oauth.json, and it is licensed under MIT.
Read MoreTCM Constitution Wellness Assistant: A Skill for Converting Symptom Descriptions into TCM Wellness Regimens
The TCM Body Constitution Wellness Assistant is a Skill provided in the standard SKILL.md format, with the identifier @org-6fjq4wei/tcm-body-constitution-helper, version 1.0.0. Originating from enterprise and published by Zhengzhou Jinfeng Digital Technology Co., Ltd., it is categorized under life-service with a tag indicating requires_api_key=false. It accepts users' symptom descriptions to determine their TCM body constitution type and offers wellness plans across dimensions such as diet, exercise, daily routine, and meridian conditioning. It is suitable for developers seeking to embed wellness advice capabilities into their own products. This article describes its positioning and core functions. It notes that the official page is currently inaccessible, so there are no reproducible installation commands, configuration fields, or typical invocation examples; it is advised to defer to the official address and not to guess commands. It also reminds that wellness advice cannot replace medical diagnosis, that the quality of symptom descriptions will affect the constitution determination, and that, being an initial release, it may be adjusted in the future.
Read Moredsh-prompt-library: Replicating Voyager-style Prompt Library and Session Organization in DSH
The dsh-prompt-library client plugin (v0.17.0, MIT) by Kirby-YiBy delivers a floating prompt library, conversation references, one-click KaTeX formula copying, and session folders within DeepSeek Harness. Data persists to ~/.dsh, and Voyager prompt format import/export is supported. Requires DSH 0.2.1-rc.5+ and Node 20+. Install via: dsh plugin --profile desktop add github:Kirby-YiBy/dsh-prompt-library. No cloud sync or complete segment export is available. The plugin runs with dsh process privileges; source code review prior to installation is recommended.
Read MoreService Design Expert Squad: Gateway for Triage and Collaboration on Complex Consulting Tasks
Service Design Expert Team is the master entry on SkillHub, located at @user_cae83fba/service-design-expert-team, version 1.1.1, categorized under business-ops, published by user_cae_cae83fba. It targets complex, consulting-type tasks spanning service design, customer insight, growth strategy, metrics frameworks, ROI evaluation, evidence audits, theory extraction, and delivery QA, providing unified triage, expert routing, collaboration orchestration, and result synthesis. Prioritize using it when users request to invoke the Service Design Expert Team, enable the Service Design Expert Team, ask for an expert team evaluation, or require design optimization for service experiences, customer journeys, growth plans, metrics frameworks, ROI, evidence audits, or delivery quality. The skill enforces strict guardrails: it does not fabricate sources, case studies, or data; it does not state assumptions as verified facts; it does not replace licensed professional opinions in legal, medical, or financial matters; and when information is insufficient, it outputs assumption ranges and validation paths rather than pseudo-precise numbers. It is not suitable for encyclopedia-style one-off Q&A or tasks lacking business context and unwilling to provide additional information.
Read MoreSKILL Based on the BOPPPS Teaching Model: Decomposing Higher Vocational Education Teaching Plans into Six Gated Phases
This is a vocational teaching design Skill published by the SkillHub community, located at @user_4027a693/boppps-lesson-prep (Version 0.1.1, Category: Education). It generates lesson plans based on the six BOPPPS stages, employing a gated step-by-step progression that requires participatory learning to account for no less than 50% of the content, followed by a four-dimensional self-assessment upon completion. The resource tag `requires_api_key=false` indicates that the Skill itself does not require an additional API key. Official documentation provides no installation commands for git, npm, or curl, nor has it verified directory discrepancies across Cursor, Codex CLI, and Claude Code. The page displays a rating of 100,000, with 985 downloads and 0 installations. While suitable for vocational college teachers preparing new courses, open lectures, or project-based instructional designs, the low installation count and the lack of elaboration on the four self-assessment dimensions suggest that it should first be validated on a small scale using familiar course material.
Read Moredsh-gbk-text: Fixing GBK Text Preview in the DSH File System Layer
Strict UTF-8 decoding in the DSH local file system causes GBK files to display "This file format cannot be previewed temporarily" in the sidebar. dsh-gbk-text performs a GB18030 fallback on FS_NOT_TEXT in fs.readText/streamText, fixing plain text, Markdown, code, and table previews in one go; it is read-only, defaults to GB18030 only, and can coexist with dsh-fs-encoding. The article covers the mechanism, installation commands, configuration options, and known trade-offs such as the 8 MiB limit.
Read MoreTextbook Writing Pipeline: UbD-Driven Reverse Design for Multi-Chapter Textbook Development
Textbook Writing Pipeline is an Agent Skill built on the universal SKILL.md format, maintained by community publisher user_6733bad6, version 0.7.0, classified under content-creation. It applies the UbD (Understanding by Design) reverse design approach to decompose the writing of an entire textbook into five stages and orchestrate them through a workflow. Stages 2 and 3 enforce a dual "gate" requiring author confirmation, and progress is saved to .progress.json to support interruption-resumable writing. It supports planning a full textbook based on existing Word documents or lecture notes, as well as designated chapters within revision projects. It must be installed together with textbook-outline, textbook-chapter, and textbook-exercises under the same skills directory—all three are essential and cannot be omitted. Official URL: https://api.skillhub.cn/user_6733bad6/textbook; SkillHub score: 100000; downloads: 1011; tag: requires_api_key=false.
Read MoreConversion of Element-Based Complaints: Transforming Traditional Complaints into Structured Documents
Introducing the Community Skill "Element-style Lawsuit Conversion" (@user_67eb0ca4/tkk-element-lawsuit, v1.0.0): This tool automatically extracts key elements from traditional lawsuit complaint documents in DOCX/PDF formats. Driven by AI, it fills in the data and generates element-style legal documents based on the official template specified in Fa [2025] No. 82. Supporting 33 civil causes of action, it utilizes a 4-step workflow: Upload → AI Analysis → Edit/Proofread → Preview/Export. The skill outputs DOCX files and requires no API Key.
Read MoreDSH-oopz-voice: Enabling DSH Agents to Enter Oopz Voice Rooms and Speak
dsh-oopz-voice is a DSH workflow plugin maintained by Kingyibin. Using local SenseVoice ASR, an OpenAI-compatible LLM, VITS TTS, and Agora streaming, it enables an agent to listen, think, and speak in authorized Oopz voice channels, and supports yielding and catch-up listening. Install it with `dsh plugin --profile desktop add dsh-oopz-voice`; requirements include Node 20+, Python 3.10+, real Chrome, and an Oopz account. Perceived latency is about 1.6 seconds. It connects via reverse-engineered access to the private protocol rather than through an official API, so please read the compliance and privacy notice before use.
Read More1688 Best Seller Selection | Guo Yiyi: Delegating Sourcing Decisions to Structured Data
1688 Best-Selling Product Selection | Guo Yiyi (v1.0.1) is a community Skill designed for 1688 product selection tasks, located at @user_8d36cde0/alibaba-1688-trend-product-selection-guoyiyi-ecom. Categorized under business-ops, it requires no API Key. It accepts inputs such as 1688 product details, pricing, sales trends, and supplier information, producing three results: a list of trending product candidates, sourcing risk assessments, and preliminary profit screening. It is suitable for 1688 purchasers, cross-border sellers, and product selection teams to conduct preliminary screening and horizontal comparison. A key limitation is that when no platform connection is configured, it only processes user-provided or exported data; it lacks real-time query capabilities and does not generate market data out of thin air, so data sources must be prepared by the user. As of this writing, official documentation pages and API addresses were inaccessible, and the materials provided did not include installation commands, directory structures, or configuration fields. Therefore, this article only describes general loading methods and does not itemize the differences between Cursor, Codex CLI, and Claude Code, nor does it fabricate input formats or output samples. It is recommended to verify the quality of the output independently before use: as the source is community-based, ratings and download counts displayed on the platform do not imply official certification.
Read MoreEncapsulating Repetitive Team Workflows into Installable, Cross-Tool Agent Skills
This skill targets repeated routines within a team, such as pre-review material preparation and pre-release checklists. It addresses the difficulty of reusing ad-hoc prompts and keeping multiple tools in sync. Inputs may include documents, links, code, or rough process notes; the agent converts them into a reusable workflow based on SKILL.md, completes validation and installation, and can also be shared, optionally, across supported agent tools. It is published by SkillHub community user_3c6cb52e, version 1.0.0, category ai-agent, tag requires_api_key=false. Installation commands and tool-specific differences are not provided in the scraped materials, and the article does not fabricate them; before adoption, verify them against the official page and the generated SKILL.md.
Read MoreBencao Q&A - Millennium Old TCM Doctor: Agent Skill for TCM Consultation with Sources
"Ben Cao Wen Wen - Qian Nian Lao Zhong Yi" is an AI skill for medical consultation based on the original texts of 16 classical TCM classics. Published by user_516d7c35, it is categorized as "professional" on SkillHub, sourced from the "community", version 0.4.0, and requires no API Key. It standardizes the consultation process: following the "Ten Questions Song" for step-by-step inquiries, asking only 2-3 key differential questions per round, and converging to a single syndrome diagnosis. It supports multimodal tongue inspection (tongue color, coating color, coating texture, tongue shape, and moisture). All prescriptions and medical advice must specify the dynasty, author, and source; no prescription is given without a source, and ancient text citations are followed by vernacular explanations. For acute and severe cases, it only provides medical reminders and safety triage. It is to be used with caution by pregnant women, children, and chronic disease patients. It is not applicable for modern medical diagnosis or medication substitution, animal diseases, or non-TCM topics.
Read Moredsh-session-health: DSH Session Status Dashboard
dsh-session-health is a DSH client plugin maintained by kingrenqi-wq. It displays the context usage of the most recent request in a floating widget at the bottom right corner. The plugin provides visual alerts—a yellow border and text—when consecutive similar tools fail or when a task exceeds 300 seconds without reaching a terminal state. It only reads local v4 session logs from ~/.dsh/sessions, with no network access or file writing. Clicking the card reveals evidence such as sampling time and failed sequence numbers. Installation is performed by adding an npm package name, Git URL, or local path via the sidebar, and it takes effect immediately upon activation. This tool is ideal for monitoring context usage and toolchain anomalies during long sessions. Please review the source code and MIT license before installation.
Read MoreConverting Scanned PDFs to Text: Transforming Image-based PDFs into Editable Markdown
This article introduces the community Skill "Scanned PDF to Text" (@user_937442fe/scanned-pdf-extractor, version 3.0.2, category office-efficiency). It targets scanned documents for which pdfplumber, markitdown, or PyMuPDF get_text() all return empty output. By rendering high-resolution PNGs page by page and performing recognition with a configured OCR engine, it outputs structured Markdown. Core capabilities include batch processing; two-stage checkpoint-resumable processing for rendering and OCR; automatic deskew of tilted pages (with three safety gates); correct reading order for two-column documents; and structured table recovery based on PaddleOCR PP-StructureV3. The default vision engine works out of the box with zero installation, with optional local engines paddle and tesseract. The materials do not provide installation commands or configuration fields; the article therefore handles these within the bounds of available facts and provides official links for verification.
Read More