WeChat Official Account Viral Articles Writing Master: A Nine-Step Writing System from Topic Selection to Retrospective
WeChat Official Account Viral Articles Writing Master (@user_557dbafb/gzh-viral-writer, v1.0.0, community source, content-creation category, no API Key required) is a writing Skill for Official Accounts that covers a nine-step workflow: material comprehension, topic selection, title hook design, narrative pacing, structural templates, style-based writing, four-level quality assurance, platform optimization, and data retrospective. It integrates Khazike-level stylistic techniques with viral-spread strategies, positioning "how to write" and "how to go viral" within a unified writing process. It is applicable to drafting, rewriting/editing, title optimization, retrospective analysis (e.g., why it failed to go viral), continuation and expansion, etc. The official documentation provides an explicit list of trigger phrases for activation. The SkillHub page shows a score of 100,000 and 915 downloads, with 0 installations. The article also covers the functional boundaries and typical use cases, and notes caveats such as installation methods depending on the runtime environment and the limited availability of community feedback samples.
Read MoreForeign Trade RFQ: Clarifying Buyer Requirements and Specification Matrices - The Organizing of Scattered Buyer Demands into a Quotable Matrix
This article introduces the community Skill "Foreign Trade RFQ Requirements Clarification & Specification Matrix" (SkillHub, business-ops, version 1.0.0, requires_api_key=false). It organizes overseas buyer emails, chat records, drawing summaries, and inquiry forms into a quotable requirements specification matrix, identifies critical gaps, and generates English clarification questions. It supports updating the RFQ ledger, version discrepancies, and quotation status based on buyer replies. It is applicable for foreign trade RFQ pre-screening and internal quotation handovers, without guessing missing specifications or replacing engineering, certification, or contract reviews. The article describes core features, general activation methods, typical workflows, applicable scenarios, and limitations.
Read MoreVoiceTranser: Local Voice Input and Auto-Paste under DSH
VoiceTranser (Lumos-789, v1.0.1, MIT) is a SkillHub client-side DSH plugin: the repository declares dsh.bundle, and after installation the agent assists with local deployment via the voicetranser skill. The backend is a macOS daemon; while holding a hotkey, it records audio over HTTP /start|/stop, transcribes locally with Qwen3-ASR MLX, SenseVoice, or mlx-whisper, corrects the text via corrections.json, and pastes it at the cursor. It is intended primarily for Apple Silicon, while Intel uses the CPU engine; Python 3.11+ and uv are required, and Accessibility permissions are used for automatic pasting. Based on the GitHub README and the SkillHub directory page, this article describes its capabilities, typical commands, and how to run it persistently with launchd.
Read MorePLC teaching plans & practical training design assistant: Leave repetitive lesson-prep tasks to Skill
This Community Skill, designed for PLC course instructional assistance, is published and maintained by user_befb1651 (Version 1.0.0). It is categorized under "education", sourced from "community", and requires no API Key. Its capabilities include lesson plan framework generation, covering progressive practical project design (ranging from start-stop control to comprehensive sorting lines), generation of accompanying documents such as assignment briefs, grading rubrics, and safety precautions, as well as built-in ideological and educational touchpoints related to the craftsman spirit and safety protocols. The article details its positioning, core capabilities, activation method (refer to the official page for details), typical conversational usage, applicable scenarios, and important guidelines: outputs are intended as preliminary drafts; safety points and grading weights must be vetted by instructors before use, and any incompatibilities with specific equipment conditions should be explicitly stated in the prompt description.
Read MoreQuad: Distill character mindset frameworks and books' methodologies into publishable Skills
Quad, a Skill creation framework published on SkillHub, is positioned not as a single prompt, but as a quaternary closed loop covering the entire process from inspiration gathering to continuous evolution, comprising: Nuwa, Cangjie, Lineage, and Darwin. The article begins by outlining the problems it solves, followed by introducing its verified core capabilities: distilling personas or books into Skills, composite master packs, packaging unified workflows, and reusable code assets. Subsequently, it explains that installation and activation require verifying the SKILL.md format and code dependencies first, and then provides a usage pathway from single-item distillation to publication and iteration, as well as limitations regarding the target audience, platform compatibility, and source material quality.
Read MoreReact Monitor Agent: Replay Review and Checkpoint Board
React Monitor Agent (Lumos-789) provides agents with a web-based dashboard featuring review replay and checkpoints, addressing the path dependency of the session chat window. Specifically, rma-core (:8790) logs events, while rma-board (:5173) replays the timeline and facilitates decision-making at Plan, Progress, Risk, and Delivery checkpoints. The DSH bundle serves as a skill shell, orchestrating the startup of cloned repositories. It defaults to FIXTURE mode for offline demos, while live mode connects to the core. It complements dsh-superagent: DSH handles agent self-regulation, whereas RMA manages human-side review bandwidth. MIT License.
Read MorePlease provide the Chinese technical article title you need translated. I am ready to assist you!
**AI Code Security Audit Pro** is a community-maintained reference skill for code security auditing. Published by user_310c0202 (Version 1.4.1), it originates from the community, is categorized under dev-programming, and is tagged with requires_api_key=false. Designed for development and DevSecOps scenarios, it performs static security analysis on languages including Python, Java, JavaScript/TypeScript, Go, Rust, C/C++, PHP, Ruby, Swift, Kotlin, and Solidity. It covers the OWASP Top 10 and common CWE weaknesses, identifying risks such as injection, authentication flaws, sensitive information disclosure, unauthorized access, and input validation defects. The output includes vulnerability locations, risk levels, root cause analysis, and remediation guidance. This tool is intended for auxiliary screening and educational purposes; due to the possibility of false positives and negatives, its conclusions require manual review. It does not replace professional penetration testing or compliance audits conducted by certified institutions. No unified installation command is provided in the official documentation. The text lists only verified locating fields; for installation and activation methods, please refer to the official page.
Read MoreSenior Specialist in Smart Agriculture Digitalization and AI Transformation Skill: Structured Advisor for Agricultural Digitalization Diagnosis
Introducing the community Skill on SkillHub: "Smart Agriculture Digital & AI Transformation Senior Expert / Agriculture Digital & AI Transformation Expert" (@user_82981261/agriculture-digital-ai-expert, version 1.0.0, category: professional, requires_api_key=false). This Skill targets scenarios involving agricultural digitalization and AI transformation, covering business formats such as open-field grain and oil crops, facility agriculture, economic fruit orchards, livestock (pigs, poultry, cattle, sheep, dairy cows), aquaculture, unmanned agricultural machinery, digital villages, cold chain processing, and agricultural product e-commerce. It also addresses needs including agricultural IoT, precision agriculture, agricultural large models, high-standard farmland, agricultural subsidy policy matching, agricultural ROI demonstration, agricultural maturity assessment, and agricultural product traceability. It is designed for expert-level diagnosis, planning, selection, demonstration, or implementation. The official description claims its architecture consists of an original "four-pillar" system (cross-reference network, retrieval freshness, rigorous gates, and a zero-human-intervention self-iteration engine), positioning it as a traceable, verifiable, and ever-fresh "living expert system." As this is a declaration by the author, the SKILL.md file after installation shall prevail. The article provides coordinates and page entry points, does not fabricate installation commands, and suggests verifying file contents and primary sources prior to actual invocation.
Read MoreHTML-PPT Lightweight Development Courseware: Offline Single-File HTML Presentation Skill
This article introduces the SkillHub community Skill "html-ppt-lightweight development courseware." It generates offline, single-file HTML presentation courseware featuring built-in navigation, editing, fullscreen mode, and drag-and-drop capabilities. It is suitable for HTML presentations, courseware, web-based PPTs, interactive slides, and training materials. The article provides the Skill's coordinates, version, source, category, ratings, and download statistics. It verifies its functionalities for page navigation, fullscreen, editing, advancing slides via mouse clicks, and draggable content blocks, and indicates that `requires_api_key=false`. Furthermore, it notes that official documentation does not provide installation commands and that the source is community-based; given 937 downloads but 0 installations, it recommends piloting it in a small scope before adoption.
Read MoreMalo Browser: Scripted Demo Browser and Agent Backend Web Runtime
Introduction to the malo-browser DSH plugin (0.1.3, MIT) maintained by Lumos-789: an Electron-based scenario-oriented Stage/Recorder with 1080p30 evidence recording, a Director and loopback control API, and multi-agent isolated sessions via daemon lease ports. It covers the installation method identified by SkillHub for Lumos-789/malo-browser, dsh and Node engine requirements, npm build steps, as well as typical commands for the fixture service, hidden recording, the control API, and the daemon, along with macOS/permission considerations.
Read MoreCredit Risk Modeling: Delegating Probability of Default and Credit VaR Calculations to Skills
This paper introduces a community Skill for "Credit Risk Modeling" (credit-risk-zx, v1.0.0, published by user_053d27d0, classification: professional, community source). It packages four classic credit risk models into a unified entry point: KMV-Merton default probability, Gaussian/t/Clayton Copula dependence structure, credit VaR, and Altman Z-Score, covering single-entity default, portfolio dependence, portfolio loss, and financial early warning. The Skill is based on the general SKILL.md format and tagged with requires_api_key=false, requiring no additional authentication. The article provides the installation command npx skillhub add @user_053d27d0/credit-risk-zx, and notes that parameters and return structures should be verified against the SKILL.md included in the package. Since the public page lacks reproducible call examples, the article does not fabricate examples but instead recommends installing first and then performing small-sample trial calculations and result verification. The conclusion lists applicable scenarios (prototype validation, teaching demonstration, pluggable risk control components) and considerations (community source requires self-verification, models are sensitive to assumptions and parameters, Z-Score needs recalibration across industries, and installation volume is relatively low), along with the official address.
Read MoreGuide to Football Tactical Training: Implementing Formations and Tactical Coordination into Football Skills in Practice
This is a football training-oriented Skill published by SkillHub community publisher user_3c6cb52e, version 2.0.1, categorized under education, with the tag requires_api_key=false, meaning no additional API key is required. It is positioned within sports and fitness skills, with its capability boundaries covering three things: parsing football formations and positional responsibilities, breaking down tactical coordination in terms of movement patterns and passing lanes, and providing suggestions for individual technical training and team tactical drills. The article first outlines the pain points this type of Skill aims to address—general models tend to remain at a superficial level when discussing football, lacking specific actions, repetition counts, and groupings. It then explains what it is and lists its verifiable core functionalities. Subsequently, it honestly notes that the retrieved materials contain no installation commands or configuration fields, providing only a verifiable page URL and citation coordinates, and recommends first opening the SkillHub page to confirm integration methods for clients such as Cursor, Codex CLI, and Claude Code. Next, it presents four illustrative calls based on the introduction, covering formations, tactical coordination, individual training, and team drills respectively. Finally, it lists applicable scenarios and precautions, including noting that the source is community-generated and outputs require self-review, that no injury prevention constraints were observed, and that the entry information is relatively thin. It also explains that during this retrieval, ratings and download counts were inconsistent across different sources, and actual page figures should be taken as authoritative.
Read Moremake-it-a-bit-better: Small, Verifiable Product Polishing in Rounds
The Lumos-789 workflow DSH plugin "make-it-a-bit-better" performs autonomous polishing driven by skills: each round enforces a 3-perspective brainstorm, makes small single-round changes (≤3 files / ~100 lines), commits locally after verification, and writes to `.agents/mabb/ledger.md`; oversized ideas are moved to the icebox. Requires a Git repository root and DSH ≥0.2.1-rc.2. Install via `dsh plugin add` with a local path or "make-it-a-bit-better". No push by default; writes to the target repository with the permissions of the current dsh process.
Read MoreAuspicious Day Selection: Turning Folkloric Date Selection into a Reproducible, Local Computing Skill
"Zejiri" is a community-sourced folk date selection Skill categorized under life-service. Currently at version 1.0.3, it holds a SkillHub rating of 100,000 with 930 downloads and requires no API Key. Targeting developers seeking to embed "auspicious date selection" capabilities into conversational products, it accepts the event (e.g., wedding, house entry, opening, groundbreaking, burial, sacrifice, travel, or contract signing), the beneficiary's zodiac or birth details, and a feasible time range. Powered by *lunar-python*, it calculates Gregorian and Lunar calendars, the Four Pillars, Twelve Jianchu, Yellow/Black Paths, Clashes, Do's and Don'ts, as well as Auspicious/Inauspicious Deities and favorable times. It features built-in validation for fixed inauspicious days (such as Yang Gong Ji, San Niang Sha, Ten Great Failures, and Four Separations/Four Absolutes). For groundbreaking and burial events, it also validates site directionality relative to the Annual Three Sha, Grand Duke (Tai Sui), and Year Breaker. The system performs multi-layer filtering and scoring to rank candidate dates, returning a list featuring pillars, Jianchu, recommendations, and favorable times, along with a deliverable auspicious date document. The entire process is computed locally without internet connectivity. It serves as a reference for folk culture and does not constitute legal, medical, or investment advice. The article also outlines installation commands and configuration fields not covered in the source materials, as well as boundary conditions that require validation during integration.
Read MoreSkill Workshop: A Tool for Transforming Repetitive Workflows into Maintainable Skills
Skills Atelier (@user_f55dd365/skills-atelier, v1.2.3, community, ai-agent) is a community Skill for creating and optimizing Skills. It places skill creation and the optimization of existing Skills on a single workflow: it can generate well structured Skills from scratch, review, condense, and modify existing Skills, and advise on how to write descriptions, when to split references, and how to define completion criteria. The official version is selectively optimized for token reuse and concise writing, with requires_api_key=false. The document describes core features, entry point information, reproducible trigger phrases, and usage notes; installation commands and other details should be taken from the official page, and initial outputs should be treated as drafts and validated.
Read MoreGuster: A DSH Workflow Plugin for Cross-Project Auditing and Evolving Agent Contexts
Guster is a DSH workflow plugin maintained by Lumos-789, serving as the control plane for agent context: it scans the registry, performs doctor policy checks, computes seven-dimension CHI scores, generates JSON plans and applies them with --yes, and can initialize a lite Guster Hub. The CLI targets Python 3.9+ with no third-party dependencies; DSH installation is via `dsh plugin add /path/to/guster`. It is suitable for multi-repo/full-machine build, AGENTS, skills, knowledge and credentials governance scenarios; the plugin runs with the current process's permissions, and the source code and MIT license should be reviewed before installation.
Read MoreGenerative Media Skills for AI Agents: Enabling Agents with Generative Media Capabilities
This article introduces the skill "🎭 Generative Media Skills for AI Agents" (ID: @org-eyw2ohcx/samuraigpt-generative-media-skills, version 1.0.0, enterprise source, publisher: RealQ, category: design-media) available on SkillHub. The skill wraps generative media calls in a standard SKILL.md file, powered underneath by MuAPI, and is tagged with requires_api_key=true, meaning an API Key must be configured before activation. Because publicly crawled materials did not include the full SKILL.md body or installation commands, this article only states verifiable facts and explicitly notes that the interface list, installation methods, and call examples must be taken from the official page; no speculation is made. The official URL and the rating and download data captured at the time of crawling are provided.
Read Moredelivery-video: Turning working features into verifiable delivery demos
The DSH workflow plugin `delivery-video` for Lumos-789 transforms functional prototypes into SHA256-bound delivery demos. It features verify-before-record logic, `episode.json` recipes, edge-tts narration with word-synced subtitles, and strict preflight/render/verify plus render gate enforcement. Install via `dsh plugin add` with a local path; requires python3, ffmpeg, and edge-tts>=7.3.1. It also supports feedback for defect videos. MIT 1.1.1.
Read MoreHong Kong CBBC Outstanding Risk: Query on Distance to Trigger Price and Outstanding Volume
The Skill from Antseer MCP, based on Futu OpenAPI v10.7, provides the ant_hk_stock_data tool, covering three categories of Hong Kong stock data: the call price and market concentration of callable bull and bear contracts, the spot prices of the underlying stock and the Hang Seng Index, and K-line backgrounds, with native Hong Kong dollar (HKD) quotations. It is suitable for distance monitoring and market concentration analysis of callable bull and bear contracts. Installation commands and configuration fields are missing from the existing documentation, and no official page was verified in this review; the tool must be enabled strictly based on official URLs.
Read MoreShort Video Editing Pacing and Final Video Quality Checks ｜ Jianshi AI: Transforming Final Video Quality Checks into an Actionable Checklist
An Agent Skill designed for short video and livestreaming teams, it handles editing rhythm control and final video QA across topic selection, production, publishing, and post-mortem review for Douyin, WeChat Channels, and Xiaohongshu. It delivers actionable plans, checkpoints, and risk boundaries. The article outlines its positioning, core features, installation and activation methods, applicable scenarios, and precautions.
Read MoreBaton: Deterministic Scheduling of Tickets and Subagents for OpenSpec Changes
Baton (dsh-openspec-baton) is a DSH workflow plugin for Lumos-789: it deterministically schedules tickets/DAGs on approved OpenSpec changes using SessionController and the session_control.py CLI. The main session forwards actions to subagents, verifying success strictly via sealed receipts. It supports per-task isolated git worktrees, up to 5-way parallelism, and a live tasks.md plan. Requires DSH 0.2.1-rc.2+, Python 3.10+, and a subagent tool; install via `dsh plugin add <local_path>` or `dsh-openspec-baton`.
Read MoreImage to PPT: Batch convert image folders into one-image-per-slide PPTX files
This article introduces the community Skill "Images to PPT" (@user_6fd83c94/images-to-ppt, Version 1.0.0, category: office-efficiency), which converts image folders into PowerPoint (.pptx) presentations with a "one image per page" layout. Each image occupies one slide, fills the slide completely while maintaining aspect ratio and centered alignment, supports png/jpg/jpeg/bmp/gif/webp/tif/tiff.Media, and requires no API key. It explains titles positioning, core functionality, and trigger use cases (e.g., upload an image folder to generate a deck, batch-convert images to slides, or one-image-one-slide workflows), and clarifies that it handles image placement on slides and does not manage text layout slide ordering depends entirely on filenames. The installation command is not included in the available documentation and has not been fabricated—readers are directed to the official address for installation instructions
Read MoreTransforming Intensive Paper Reading into Structured Reports
Literature Close Read is an Agent Skill tailored for academic paper reading scenarios, located at @user_9cc4d736/literature-close-read. It is version 1.0.0, maintained by the community publisher user_9cc4d736, categorized as professional, and does not require an API key to enable. It does not retrieve literature or download full text; instead, it performs structured interpretation of provided paper content and outputs a report covering the research topic, research design, methods, results, innovations, limitations, gaps, and overall research logic. It supports three usage modes: in-depth reading of a single paper, comparative reading of multiple papers, and extraction of methods and/or results. The article outlines its functional boundaries, how to enable it, reproducible usage examples, and cautions: report quality depends on the completeness of the input text; when method details and data are involved, the source text should be consulted for verification.
Read Moredsh-session-tree: Visualize Workspace DSH Sessions as a Browsable Fork Map
Session Tree (`@lulaalu/dsh-session-tree`) is a DSH 0.2.x client plugin maintained by lulaalu. It opens a full-page "session tree" via a tree entry in the web sidebar. Acting as a read-only interface for `ctx.sessions` and `turnOutline`, it visualizes sessions, conversation turns, and forks as a map organized by workspace. It supports history inheritance, sub-sessions, archiving, and node navigation. This article covers the design philosophy, features, installation methods (via GitHub, npm, and indexed sources), and known limitations. Please verify the source code and MIT license before installation.
Read MoreSuper Lotto Statistical Prediction System v1.1: Breaking Number Generation into Verifiable Statistical Processes
**# Introduction** If you tell a model "help me predict Super Lotto numbers," in most cases, it will either make up a set arbitrarily or slightly modify the numbers from the previous draw. While the numbers are generated, you cannot determine the basis for them, nor can you verify afterwards where the error occurred. Professionals in data analysis are accustomed to a different approach: every step relies on reproducible statistics, and every step can be questioned and replaced. The Super Lotto Statistical Prediction System v1.1 introduced below is built according to this philosophy. It decomposes "number selection" into several stages: hot/cold/warm statistics, gap value backfilling, zone break analysis, correlation structure identification, combination filtering, and independent back-zone analysis, while utilizing reinforcement learning to automatically adjust weights. It does not guarantee a win, but it ensures that you can clearly see the input and output of every step. **# What is this?** A system designed for the Super Lotto (Front Zone: pick 5 from 35, Back Zone: pick 2 from 12).
Read More