Cross-border E-commerce Standalone Site Facebook Product Testing Agent: A Three-Agent Workflow for Regional Market Analysis, Facebook Ad Library Product Selection, and Creative Generation
This Skill is a community-sourced project on SkillHub with the internal identifier `independent-store-agent-suite`, version 1.0.0. Published by `user_96df57c8`, it is categorized under `business-ops`. At the time of data scraping, it had a rating of 100,000, 952 downloads, and 0 installations. It is tagged with `requires_api_key=false`, meaning no additional API Key is required for use. The Skill deconstructs the product selection and creative material workflow for cross-border independent websites into three Agents that execute in a fixed sequence: 1. **Agent 1** performs regional market analysis, outputting 10–30 product directions and 30–60 English search keywords for the Facebook Ads Library. 2. **Agent 2** must ask for the desired number of candidates to collect. It then searches the Ads Library with settings set to `Region = All` and `Ad category = All ads`. It records specific ad ID links, advertisers, landing pages, and video download status. Candidates are scored based on sellability, creative strength, copy strength, supply chain feasibility, and risk score. Agent 2 outputs a CSV of candidates and pauses for user confirmation. 3. **Agent 3** processes only `approved` products. It first verifies if the ad, video, and landing page refer to the same product, then creates a `product_identity.json`. It generates a fixed output of 2 main images plus 5 detail images, with independent prompts for each. Detail images utilize the language of the target market. Generated images must be displayed to the user for review before proceeding. The fixed sequence is: **Agent 1 -> Agent 2 -> User Confirmation -> Agent 3 -> User Review -> Packaging after Approval**. Skipping Agent 1 or Agent 2 is not allowed. **Limitations:** * The Facebook Ads Library does not provide data such as clicks, traffic, conversions, or CPA; the Skill does not fabricate this data. * Without browser or download capabilities, Agent 2 enters manual guidance mode: videos that cannot be downloaded are marked `needs_manual_download`; inaccessible landing pages are marked `manual_source_required`; if image generation is unavailable, it outputs `prompts_only`. * The Skill does not process high-risk products related to knives, firearms, food, drugs, health supplements, medical efficacy, finance, politics, or religion. * No installation commands (npm, pip, or git clone) are provided in the documentation; installation instructions should follow the official page.
Read MoreZhixia Selection Data - Shopee Big Data Analysis: Enabling Agents to Read Shopee Selection Data Directly
**Introduction to ZhiXia Product Selection Data - Shopee Big Data Analysis Skill:** This Skill analyzes sites, categories, products, shops, brands, trends, and hot search keywords via Shopee MCP. It is applicable for market size assessment, category product selection, competitor research, ranking analysis, shop/brand diagnosis, and keyword trend analysis. Published by Guangzhou Mengla Information Technology Co., Ltd. (Enterprise Source), it is categorized as data-analysis, Version 1.0.5, with the tag requires_api_key=true, indicating an API Key is required. As the currently scraped data does not provide installation commands, configuration fields, or enablement steps for various editors, and the official page failed to load, this article truthfully states that these installation and enablement details cannot be verified; it is suggested to refer to the official address. Meanwhile, precautions regarding data coverage, update frequency, authorization scope, and version changes are also noted.
Read Moredsh-repo-map: Generating compact directed repository graphs with regex
dsh-repo-map (lengrufeng2008) is a "memory"-category plugin of the DeepSeek Harness community. It scans repositories using regex heuristics to generate a compact map of source files and top-level symbols, without relying on LSP or call graphs. This article introduces its positioning, the division of responsibilities with dsh-code-intel / dsh-repomix, the SkillHub installation method, CLI and Harness usage, and its capability boundaries. Version 0.1.0, MIT licensed, requires Node 20+.
Read MoreInstant Thesis Search: Local Academic Paper Retrieval and Export
Paper Quick Search is a community skill on SkillHub, located at @user_3cdbf8ea/paper-search. Version 1.0.4, published by user_3cdbf8ea, it implements local retrieval and export of academic papers using pure Python and includes a built-in index of classic papers. It is tagged with requires_api_key=false, indicating that no additional API key is required. The article verified page information such as name, coordinates, version, source, category, rating, and download count, and noted that installation commands and typical usage examples were missing from the retrieved materials; no content was fabricated.
Read MoreSurvey List Generation: Integrating the Preliminary Research of Seeyon OA Business Solution into a Case Folder
"Research Checklist Generator" is a community-sourced Agent Skill, located at @user_66a8fb19/research-checklist-generator, version 1.0.0, published by user_66a8fb19, categorized under business-ops, sourced from community, with a rating of 100000, 937 downloads, 0 installs, and tagged as requires_api_key=false. It is used prior to business solution generation: based on user-uploaded contract scopes, business handover documents, research records, and related attachments, combined with Seeyon OA / CAP4 / integration official materials and necessary web searches, it produces a unified case package, an Excel research checklist, and a handover draft for "Business Solution Generation." Core features include unified case package organization, Excel research checklist generation, handover draft preparation, Seeyon capability boundary assessment, multi-round confirmation of unclear items, and organizing input files, research outputs, and subsequent solution outputs into the same case folder. Applicable scenarios include pre-research for business solutions, Seeyon capability boundary assessment, customer data surveying, industry case supplementation, and multi-round confirmation. The article also describes input materials and output structure, a three-step usage workflow, and notes precautions such as input completeness requirements, the need for manual review of web search results, and zero installation count.
Read Moredsh-profile-backup: Backup DSH Profile Configuration Only, Excluding node_modules
dsh-profile-backup (lengrufeng2008) is a SkillHub "Memory" category DSH plugin that performs configuration-only backup/restore of Profiles, excluding node_modules. It offers "check" for archive path validation and "force" for overwrite semantics. Based on the GitHub README and package.json, this article describes version v0.1.0, the Node >=20 requirement, three CLI examples, and limitations such as "no sessions/secrets, no boot-test, non-full-machine backup." Please refer to the SkillHub page for installation instructions.
Read MoreMulti-Factor Stock Selection (US Stocks): US Stock Factor Selection Skill Based on westock-mcp
The Multi-Factor Stock Selector (US Stocks) is a community Skill on SkillHub, located at @user_ecbd3b70/us-stock-selector. Version 1.0.0, it falls under the "Professional" category and is published and maintained by user_ecbd3b70. Leveraging the Tencent Stock MCP (westock-mcp), it provides multi-factor screening for US equities with the Dow 30 as the default stock pool, addressing the initial costs developers face when building their own data pipelines and computing factors. The article details its positioning, core features, installation and activation process, typical usage, as well as applicable scenarios and limitations. It also notes that the official documentation does not elaborate on specific factor details, necessitating verification after loading the Skill.
Read MoreWorkBuddy Growth Plan Assistant: Breaking Down Growth Plan Tasks into Executable Steps
# Introduction The WorkBuddy Growth Plan is a task-based system: complete tasks to accumulate points and energy. The challenge for developers lies in the fact that these tasks are scattered across various entry points on the web. Some can be claimed with a few clicks, while others require personal, manual operation. Scrolling through pages individually and keeping track of completed tasks versus those still pending is a pure waste of time. The "WorkBuddy Growth Plan Assistant" Skill introduced below solves this problem. It organizes the 17 Growth Plan tasks one by one, provides official procedures and constraints, and instructs agents on which tasks can be automated and which must be done manually. ## What is this This is a community Skill published on SkillHub (Source: Community, Category: ai-agent, Publis...
Read Moredsh-preflight: Static pre-check for DSH plugins
dsh-preflight is a DSH plugin maintained by lengrufeng2008 that performs static package-surface preflight checks on plugin directories or npm pack artifacts, covering bundle patches, lifecycle scripts, skill frontmatter, redundant artifacts, and tarball residue. It supports the CLI (including --json and --tarball flags) as well as invocation via plugin_preflight within DSH. It does not perform installation, runtime, or security authentication; PASS does not imply security. Requires Node >=20. Licensed under MIT, version 0.1.1.
Read MoreClassroom Teaching Lesson Plan: Introduction to Skills
The "Classroom Teaching Lesson Plan" skill is a teaching documentation capability designed for primary, secondary, and university teachers. Coordinate: @user_1ad64560/teaching-lesson-plan, Version 1.0.0, Source: community, Category: education, Publisher: user_1ad64560. It consolidates subject lesson plan design, open lesson and high-quality course design, Word-to-PPT conversion, PPT-to-Word conversion, DOCX/PDF/PPTX/Markdown format conversion, and intelligent layout adjustment (including body text, headings, paragraphs, and line spacing) into a single entry point. This reduces the repetitive labor of manual copy-pasting between Word and PowerPoint. Official trigger conditions include user mentions of keywords such as lesson plans, instructional design, open lessons, courseware, PPT, Word, format conversion, typesetting, line spacing, blackboard design, teaching reflection, and core competencies. This skill requires no API key. As no official installation command is provided in the materials, please visit the official page to confirm the import method before use.
Read MoreWeCom Tone Polishing: Factual Message Tone Refinement Skill
This article introduces the community Skill "WeCom Tone Polish" (@user_bd3231bd/wecom-tone-polish, version 0.1.1, source: community, category: office-efficiency, tags: requires_api_key=false). It refines WeCom or WeChat work message drafts based on recipient relationships and communication goals without altering facts. The article covers positioning, core features, installation information gaps, typical usage directions, and applicable scenario constraints. Official URL: https://api.skillhub.cn/user_bd3231bd/wecom-tone-polish.
Read Moredsh-plugin-doctor: Perform a Static Health Check on Installed DSH Profiles
dsh-plugin-doctor 由 lengrufeng2008 维护，对本地已安装的 DSH profile 执行静态检查：比对 package.json 依赖与 node_modules，校验 dsh.bundle.patch 的目标，并识别 cordis.patch.yml 中重复的 patch id/name。支持命令行调用与 DSH 内 plugin_doctor 调用，可输出 JSON；不进行安装、运行时或网络检查，也不是自动修复工具。需要 Node >= 20，采用 MIT 许可证。
Read MoreFinancial Analysis of Trending News: Translating Multi-Platform Hot Lists into Bullish and Bearish Judgments for Bonds, Sectors, and Futures
Introducing the community-level Skill "Hot News Financial Analysis" (Hot-Analyzer, version 1.0.2, categorized under data analysis) on SkillHub. This skill scrapes trending lists from multiple platforms and analyzes sentiment impact—both positive and negative—on interest rate bonds, credit bonds, Shenwan industry sectors, directly related assets, and futures products. Its goal is to transform preliminary sentiment assessment from ad-hoc scripts into standardized, reusable procedures. The article outlines its positioning, verified capability boundaries, installation and activation methods, and coordinate information. It also documents data gaps: the official page failed to load, with no specific installation commands, Skill directory paths, or configuration fields provided. Differences among Cursor, Codex CLI, and Claude Code remain unverified, hence no commands were given. The official documentation also lacks reproducible call examples; typical usage is only described via input-output conventions. Key considerations include platform bias in trending lists, the need for sampling validation of judgment criteria, and the need to independently assess community engagement given 868 downloads but 0 installations. Conclusions should not be treated as direct trading signals.
Read MoreAI Demo Plan Factory: Turning WorkBuddy Client Demonstrations into a Pipeline
AI Demo Factory is a community-sourced AI agent Skill, located at @user_93048af5/ai-demo-builder (Version 2.6.2), requiring no external API keys. It transforms the creation of WorkBuddy client demo proposals from a manual process into a standardized pipeline. By providing a single input (client name, industry, or role), it automatically executes four workflows: AI implementation痛点 discovery (public intelligence, job descriptions, and industry cases), persona modeling and demo matrix design (orchestrated by business processes with verified skill items), production of the proposal webpage and resource bundle trio (simulated data, pre-run results, prompts), and end-to-end verification with safety self-checks and delivery. Deliverables include a proposal webpage available in four styles, multiple demo kits, a README index, and a verification report. Built-in assets encompass nine major industry resource libraries, an index of 49 real-world cases, 20 verified scenario libraries, the WorkBuddy capability map, and a list of potential pitfalls. It supports three scenarios: live demos, remote demos, and training delivery. It also supports three launch modes: custom for single clients, batch by industry, and batch by role. Trigger words include "AI scenario cases," "scenario case creation," "demo proposal," "client demo," "training plan," "demo design," "partner demo," and "sales enablement demo." This article also outlines installation and activation instructions, typical usage, and necessary limitations.
Read Moredsh-otel: Export dsh-token-audit Aggregated Data as OTLP/JSON Metrics
dsh-otel is a DSH plugin maintained by lengrufeng2008 that converts the JSON summary from dsh-token-audit into OTLP/JSON metrics for easy ingestion by collectors such as Grafana and Langfuse. It exposes only aggregate-level metrics (cost, tokens, sessions, calls, and per-model stats), with no network data and no per-turn spans. This article describes the CLI pipeline and the otel_export usage within DSH based on the repository README, and lists metric names and usage boundaries. MIT license. Node.js >= 20.
Read MoreStop-Slop AI Content Filter: Automated Moderation Tool for UGC
According to the official SkillHub introduction, Stop-Slop AI is an automated moderation tool designed for community operators, content platforms, and enterprises. It utilizes AI models to detect and filter spam, malicious comments, and sensitive information. Supporting both text and image content analysis, the tool offers real-time moderation APIs and batch processing modes, employing a combination of proprietary filtering rules and open-source models. It is categorized under IT-Ops & Security with the tag `requires_api_key=false`, indicating no additional API key is needed, and holds a score of 100,000 with 1,310 downloads. However, the official page crawl failed during writing, preventing verification of installation commands and usage. Furthermore, the designated source repository is actually an English writing style optimization Skill, which is inconsistent with the functional description provided in the introduction; thus, it is necessary to distinguish between the described functionality and the actual repository content during evaluation.
Read MoreEarly Math Enlightenment for the Kindergarten-to-Primary Transition: Reading Math Exercises for Children Aged 4-7
"Math Enlightenment for Kindergarten-to-Primary Transition" is a community-level educational Skill published on SkillHub, located at @user_902bd6de/skill-math-study. Version 1.0.0 requires no API Key. Designed for children aged 4-7, it covers seven progressive stages: number recognition, reading, writing, quantity correspondence, addition, subtraction, and comprehensive operations. All questions and instructions are read aloud in Chinese via the browser's Web Speech API, enabling children who cannot yet read to independently understand the questions and complete exercises. It is triggered by user requests such as "teach children math," "math practice for kindergarten-to-primary transition," "toddler addition and subtraction," "generate math problems for kids," or "voice-read math problems." The official page displays a rating of 100,000 and 997 downloads. Voice narration relies on a browser environment and Chinese speech synthesis support.
Read Moreyq-weixin-connect: Integrating Agents with Personal WeChat
yq-weixin-connect is a community Agent Skill designed for the general SKILL.md format (Version 1.0.0, Category: ai-agent, Tags: requires_api_key=false, Coordinates: @user_15292d5a/yjkj-yq-weixin-connect). It solves a single problem: standardizing the QR code scanning connection process for Personal WeChat. It ensures the Agent executes a fixed sequence step-by-step when a user says "Connect Personal WeChat," "Access Personal WeChat," "Bind Personal WeChat," or "Personal WeChat Scan," without skipping steps or improvising. The boundaries are equally clear: this Skill is not applicable when users refer to "WeCom" or "Enterprise WeChat"; the `wecom-connect` Skill should be used instead. The article explains what the Skill is, its core functions, and installation/activation methods (note: the SkillHub page crawl failed this time, so specific installation commands and configuration fields were not verified and have not been guessed). It provides reproducible examples for trigger phrases and exclusion scenarios, and concludes by listing the target audience and precautions, including the fact that Personal WeChat has no official open API and that rating and download data appear anomalous and require independent verification. Official URL: https://api.skillhub.cn/user_15292d5a/yjkj-yq-weixin-connect
Read Moredsh-openapi-diff: OpenAPI JSON Structural Breaking Change Check
dsh-openapi-diff is a community plugin for DeepSeek Harness maintained by lengrufeng2008. It checks for breaking structural changes between two OpenAPI JSON files, including: deletion of paths, methods, parameters, properties, or responses; addition of new required fields; parameters becoming required; and type changes. It supports invocation via `node bin/dsh-openapi-diff.mjs` and the DSH tool `openapi_diff`. It only supports JSON and does not fully handle `$ref`, `oneOf`, or `allOf` semantics; a clean result does not guarantee behavioral compatibility. Requires Node >= 20. MIT License.
Read MoreMiddle School Mathematics Exercises and Test-making Assistant: Integrating Assessment Research into a Self-contained Skill
**Skills in Test Question Research and Development for Junior High School Mathematics Teachers** Coordinates: @user_fca2c9bd/junior-high-math-proposition Version: 1.0.2 Source: Community Category: Education **Four Core Capabilities:** 1. Generate original variant questions. 2. Query proposition rules (SOLO classification, two-way specification tables, and methodologies for High School Entrance Exam propositions). 3. Analyze and deconstruct final challenging problems (commentary). 4. Comparative analysis of High School Entrance Exam questions. **Features:** This tool is fully self-contained and functional offline; it does not rely on external knowledge bases, question banks, or external skills such as .docx processing. **Distinction from Batch Test Generation Tools:** Unlike batch test assembly tools, this solution focuses on teaching teachers how to design questions and create variants, supported by meta-rules for proposition and comparative commentary. It is not applicable for student drills, tutoring, exam prediction, or the falsification of original exam texts. **Trigger Conditions:** Keywords and phrases including junior high school math variant questions, test question research, proposition rules, commentary on final challenging problems, two-way specification tables, SOLO classification, and High School Entrance Exam proposition methods.
Read MoreDaily Auto Sign-in [Gubji AI Assistant]: Automating WorkBuddy Daily Check-ins with a Script
This article introduces the "Daily Automated Check-in [Gùjíbù AI Assistant]" Skill. It provides an idempotent Python script that reads the local desktop login token to call WorkBuddy's official check-in API, and facilitates daily unattended automatic check-ins through Windows Task Scheduler. Starting with the pain point of developers being prone to forgetting manual daily check-ins, the article outlines the Skill's positioning (attributed to SkillHub user `user_862f479a` under the `office-efficiency` category), its core functions, typical usage scenarios based on natural language intent, and its applicable scenarios and limitations (reliance on a local login token, scheduling via Windows Task Scheduler, and installation commands unverified due to a failed scrape of the official page). It concludes by providing the official link.
Read Moredsh-mcp-doctor: Static Validation of Local MCP JSON Configuration
dsh-mcp-doctor is a DSH workflow plugin maintained by lengrufeng2008 that performs static validation on local MCP JSON files. It checks structures such as mcpServers, command/url fields, PATH executability, URL syntax, args/env types, and duplicate naming. It does not start services, perform handshakes, or access the network. It supports both `node bin/dsh-mcp-doctor.mjs` and `mcp_doctor` within the Harness. Requires Node >=20. MIT v0.1.0. This is not a security audit; command lookup depends on the current environment.
Read MoreAudit Report Entry Master: Moving Audit Report Data into Due Diligence Templates
Auditing Report Entry Master (@user_d078f748/due-diligence-template, v1.0.0, community, office-efficiency, Rating 100000, Downloads 1048) is designed for financial institution practitioners to enter PDF audit reports or financial statements into due diligence report templates in a specific format. It declares requires_api_key=false. This article verified the official page to confirm the input/output, classification, and API-free declaration. However, it notes that detailed capabilities such as scan recognition, direct reading of the "three financial statements" from Excel, cross-checking (reconciliation), and run_pipeline.py appear in the lead profile but could not be individually verified; viewing the official page first for confirmation is recommended. Installation commands and platform-specific instructions were not provided in the retrieved data and have not been fabricated. It is suitable for professionals in banking, factoring, and leasing who need to transcribe audit reports into internal templates. Users should note that the output format is bound to the official template, scanned copies require manual review, and cross-checking should be performed after entry. The version is the Community Edition 1.0.0.
Read MoreHuman Trace Puzzle · Viral Figure Database: Compiling "Newly Viral Figures" into Traceable Dossiers
"Person Trace Puzzle · Viral Figure Dossier" is a community-sourced, general-purpose SKILL.md knowledge-management Skill, version 1.2.0, published by user_84aa03cf at @user_84aa03cf/chenlin-rising-figure-dossier, tagged requires_api_key=false. It targets scenarios where "someone suddenly goes viral due to a top award, a breakout moment, or controversy, and readers want a systematic understanding of them": input a person's name plus the reason for going viral (award or event), and it outputs a semi-processed research package with original links. It supports both Markdown and DOCX formats, does not provide expert explanations but only assembles narrative traces, leaving judgment to the reader. Triggering is via natural language; official examples include "Build a dossier for XX," "XX just blew up—collect materials," "Make a complete collection / speech compilation for XX," and "Piece together XX's life story and traces." The text also notes what could not be verified this time: the official installation command and configuration fields, and the specific implementation of the self-described three-engine pipeline—"cognition amplifier → OSINT → authentic voice"—which should be taken as subject to the official page. It further highlights limitations such as material quality depending on public sources, links being the primary value, and a small sample size.
Read Moredsh-license-audit: Static License Inventory for DSH Plugin Packages and Dependencies
dsh-license-audit is a DSH admin-security plugin maintained by lengrufeng2008. It performs offline static license inventories of the plugin's root package.json and installed top-level node_modules, flagging strong copyleft and unknown licenses for review. This is not legal advice. It supports running `node bin/dsh-license-audit.mjs`, the `--json` flag, and using `license_audit` within DSH. It does not scan the full dependency tree, requires no network access, and is not an SPDX parser. Requires Node >= 20. Version 0.1.0. MIT License.
Read More