Supplier Development Assistance: Creating a Closed Loop for Low-Performing Supplier Improvement Plans
Introducing the “Supplier Development Assistance” skill on SkillHub: a tool published by Gongchengke for generating support and improvement plans for low-performing suppliers. It produces documents in TXT and MD formats using a closed-loop of diagnosis-measures-tracking-verification, targeted at SQEs and supplier quality managers. Version 1.0.1, categorized as business-ops, no API key required. The article verifies the official introduction and metadata, and explains how to verify information not provided on the page, such as installation commands.
Read Moredsh-model-advanced: Set default inference strength and image handoff by model
dsh-model-advanced is a DSH model inference plugin maintained by drm-nz. It adds an Advanced card at the bottom of Settings → Models, allowing you to set default inference levels individually for each provider/model, and to designate a delegate for models that cannot read images. At runtime, it decorates paths such as resolveModelInfo and resolveCallConfig; images are transcribed once and written into a note with a handoff marker, supporting follow-up questions via inspect_image. Install it with the command dsh plugin --profile desktop add github:drm-nz/dsh-model-advanced (a restart is required); the configuration namespace is model-advanced.
Read MoreIn-depth Individual Stock Research Report Batch Generator: Research Report Generation Covering Multiple Stocks in a Single Pass
Introducing the "Deep Individual Stock Research Report Batch Generator" on SkillHub: Given a list of A-share, Hong Kong stock, or US stock codes or names, it batch generates and deeply refines research reports (in Markdown) for each stock, saving them as independent files. Capabilities cover westock-data acquisition, parallel sub-agent generation, a 13-chapter standard reporting framework (including three deep-dive directions: historical evolution and major events, industry chain positioning and business details, technical accumulation and future outlook), valuation, risk warnings, and data red lines. Source: community; Publisher: user_782d50e6; Version: 1.0.0; Category: professional; requires_api_key: false.
Read MoreMinimalist Paper-Texture Posters: Compile a Sentence or Photo into a 3:5 Paper Poster
The Minimal Paper Feeling Poster is a design-media category SKILL.md skill, located at @user_7f6c97a1/minimal-zine-poster, version 1.0.0. It transforms a single sentence, text, emotion, article, object, photo, or reference image into a default 3:5 vertical aged-paper-style poster with 70%-90% whitespace, a single visual focal point, a single high-saturation color accent, and a short caption. It also supports outputting only a four-part image generation prompt or reusing the visual system. It supports 5 modes: generation, photo input, reference image analysis, prompt-only, and generate-after-analysis. Draws inspiration and structural references from gc-minimal-zine-poster-v0-3 (MIT), has been localized to Chinese and adapted for WorkBuddy. The retrieved materials do not provide specific installation commands and configuration fields. It can be confirmed that requires_api_key=false.
Read Moredsh-novel-beat: Delegating Narrative Decision Points to the Author Before Drafting the Main Text
dsh-novel-beat is a DSH workflow plugin maintained by DrizzleGig. It lists decision points between scene outlines and main text based on the rule "ask whenever a story state change occurs." It accomplishes querying, persisting to disk, and compilation through five tools: beat_plan, beat_decide, beat_gate, etc. It optionally integrates with novel-forge. This article introduces the decision rules, workflow, data paths, and installation commands from the README, and explains the plugin's standalone operation and the necessity of reviewing source code before installation.
Read MoreError Analysis: A Skill for Converting Mistakes into Knowledge Gap Lists
Mistake Analysis (username: @kunlungrowth/edu-mistake-analysis, v1.0.1, Enterprise source, category: education, publisher: Kunlun Growth) is aimed at students, parents, and teachers. It diagnoses the causes of incorrect answers in homework and quizzes, pinpoints knowledge-point gaps, generates actionable, personalized remediation plans and variation drills, and outputs a knowledge-gap checklist for downstream skills such as learning-path planning and review outlines. The official tag requires_api_key=false indicates that no additional API key is required. This article describes its three-layer capabilities, capability boundaries, verifiable information, and a typical processing pipeline, and notes that the official page shows zero installs and lacks publicly available implementation cases; it recommends validating output quality with real mistaken problems before integration.
Read MoreCode Review: From One Quick Look to a Dimensional Checklist
Code Review is a general code review Skill in SKILL.md format published by wpank on ClawHub. Version 1.0.0, categorized under dev-programming, and requires no API Key. It breaks down the review into seven dimensions (Security-Critical, Performance-High, Correctness-High, Maintainability-Medium, Testing-Medium, Accessibility-Medium, Documentation-Low), with each dimension featuring a checklist that can be ticked item by item. It covers issues such as SQL injection, XSS, authentication and IDOR, N+1 queries, memory leaks, off-by-one errors, race conditions, cyclomatic complexity, and test determinism. It also prescribes a three-pass review process (high-level structure for 2-5 minutes, line-by-line detailed inspection, and boundary testing and hardening for 5 minutes), combined with severity grading and structured feedback guidelines to prevent omissions from random scanning. To install, use `npx clawhub@latest install code-review` or `openclaw skills install @wpank/code-review`. It functions as a review mode rather than an automated scanner; the quality of conclusions depends on the provided context, checklists should be tailored based on the technology stack, and severity levels represent only relative priorities.
Read Moredsh-plugin-alias: Set aliases for installed plugins on the DSH plugin page
dsh-plugin-alias adds an "Alias" tag to the DeepSeek Harness plugin page, saving aliases in the browser's localStorage without altering the profile or plugin package. After installation, the card title displays as "Alias (Original Package Name)", and uninstalling the plugin restores the original name. Based on the official README, this article explains the installation command, usage steps, DOM modification method, and limitations such as local-only effectiveness.
Read MoreCross-Device Backup and Sync for Automated Tasks: Porting WorkBuddy Automated Tasks and Installed Skills Entirely
# Introduction When switching computers or reinstalling environments, the most common issue is that automation tasks and installed skills are scattered across various devices, requiring manual reconfiguration during migration. The pain point addressed by this Skill is the need to fully back up, export, import, or migrate WorkBuddy automation tasks and installed skills to a new device. The following section describes its positioning and usage. # What is this "Automation Task Cross-Device Backup Sync" is a community skill published on SkillHub, located at @user_d3228c23/qianjin-automation-sync. The current version is 1.0.1, categorized under ai-agent, published by user_d3228c23, and sourced from the community. It solves the problem that when you need to back
Read Moredsh-copy-file: One-click copy files to the Windows clipboard in DSH document preview
dsh-copy-file is a plugin for the DSH client. It adds a "Copy File" button to the header of the right-side document preview, which writes the currently previewed file to the Windows CF_HDROP clipboard, allowing it to be pasted (Ctrl+V) into any folder. It supports Chinese paths, and paths are not uploaded, nor is file content read. It is applicable to Windows and DSH Desktop 0.2.x, and is recommended to be installed via plugin_manager from github:doudoudouhuahua/dsh-copy-file. It is under the MIT License, and the maintainer is doudoudouhuahua.
Read More🚀 Douyin Operations Master: Douyin Public Data Acquisition Skill
Introducing the community Skill "🚀 Douyin Operation Master" (@user_fb71c45d/douyin-yunyingdashi, v1.0.0, Category: content-creation). This Skill is positioned as an intelligent acquisition tool for Douyin public data, covering keyword search, user profile scraping, video content extraction, comment retrieval, and real-time trending list tracking. It is applicable for short video marketing, competitive analysis, public sentiment analysis, and trend monitoring. Tagged with requires_api_key=true, an API Key must be configured for invocation. No independent installation command is provided by the official source; it should be enabled via the official address or the SkillHub page following the instructions in SKILL.md. SkillHub statistics show a rating of 100,000, 1,059 downloads, and 0 installations.
Read Moredsh-bili-whale-studio: Bilibili Self-Study, Dubbing, and Draft Publishing Workflow
dsh-bili-whale-studio (Dorodogo Studio) is a DSH workflow plugin maintained by DorododoG11. It enables self-directed learning on Bilibili and local note storage via studio_learn / studio_note; manages voice and speaking styles within explicitly authorized boundaries via studio_voice and studio_style; and utilizes studio_queue and studio_publish to place dynamics and submissions into drafts first, defaulting to a requireApproval setting that requires manual approval before publishing. It relies on bili-cli, ffmpeg, and SAPI, with data stored in ~/.dsh/bili-studio/. Installation involves cloning the repository and loading it as a bundle into the current profile, rather than using a one-click store command.
Read Moredsh-memory-chain: Five-Layer Local Memory for New Conversations without Starting from Scratch
dsh-memory-chain is a DSH memory plugin (v0.4.1, MIT) maintained by doresu. It stores five layers of data—source library, session bridge, Ebbinghaus weighted recall, artifact index, and self-narration window—in ~/.dsh/memory/. It injects content via system-prompt blocks based on character limits, preventing pollution of the message history. It provides 7 tools, including memory_write_doc and memory_search, with zero dependencies and L3 reuse tag retrieval. It requires DSH >=0.2.1-rc.2 and can be installed by running `dsh plugin --profile web add git+https://github.com/doresu/dsh-memory-chain.git` followed by an engine restart. Limitations, such as the absence of semantic search, the requirement to restart the engine after code changes, and the fact that the owner switch is not a security isolation mechanism, can be found in the README.
Read MorePersonal Office Workbench: A Self-contained HTML Efficiency Kanban Scaffold
The Personal Office Workbench is a community-sourced office-efficiency Skill, published by user_0c6c8065 (version 1.0.1). It provides a production-ready, single-file HTML template featuring built-in tasks (including recurring routines and completion notes), project tracking, review notes, sticky notes, daily automatic backup snapshots, and an optional local database for project folders based on the File System Access API, all deployable as a PWA. This article outlines its core features, installation and activation procedures, typical usage, applicable scenarios, and precautions to help developers rapidly build an offline-capable personal office workbench.
Read MoreKunlun Growth Series: Translating Training Needs into Deliverable Course Designs and Lesson Plans
This Skill, composed of “Kunlun Growth” version 1.2.0 – Classification: Education – Configuration: no secret configuration required, fixes the course development pipeline for enterprise internal training into five modules: needs analysis, objective setting, structure design, content development, and assessment design. It is built on three methodologies: a streamlined ADDIE approach. Behavioral objectives, Kirkpatrick’s four levels. It outputs ready-to-deliver course design specifications and lesson plans and provides troubleshooting tips and compliance guardrails at every stage. It is suitable for course design, training development, enterprise in-house training, course development, micro-course/short-course design, and related scenarios.
Read MoreLife Insurance Actuary: A Runnable Skill for Pricing, Profit Testing, and Reserving
"Actuary" is a Skill classified as a community-sourced professional Skill on SkillHub (v1.3.3, publisher: user_0b18ae18, no API key required). It encapsulates runnable procedures for life insurance and participating/increasing whole life pricing modeling, premium rate calculations by age and cash value projections, profit testing (NBV/VNB/IRR), Solvency Phase II (C-ROSS Phase II) BEL+RM reserve evaluation, Embedded Value (EV/NBV) assessment, property insurance pricing and loss triangle reserves, and the generation of regulatory filing materials. It incorporates the CL(2010-2013) Table 3 and CL(2025) Table 4 experience life tables, as well as real-world commercial auto insurance cases from leading domestic property insurance companies. This article outlines its positioning, core functions, typical trigger scenarios, and scope of application; however, the installation command could not be verified as the official page was unreachable, and no information was fabricated.
Read MoreAI Professional Photography Engine: Photography-Grade Prompts and Image Generation from Composition to Lighting
The "AI Professional Photographer Engine" is a community-sourced universal Skill.md format Skill, located at @user_d3228c23/qianjin-photography, maintained by user_d3228c23. It is currently version 2.2.1, classified under design-media, and labeled as requires_api_key=false. It solidifies photography experience into a structured input process: Feature 1 covers five subject categories - still life, portrait, landscape, macro, and humanistic - using a six-dimensional professional framework (composition, subject positioning, four-layer lighting, props, color tone, technique) along with a four-layer lighting formula to generate photography-level prompts and generate images; Feature 2 converts photos into emotionally healing, tutorial, or aesthetic copy; Feature 3 generates city memory copy by inputting photos and locations; Feature 4 provides professional evaluation and adjustment suggestions for photos. The article explains its positioning, four core features, reproducible usage compiled from the official introduction, applicable scenarios and precautions, and points out that the official materials do not provide specific installation commands, requiring users to directly open the official address and follow the guidelines.
Read Moredoran-design: Injecting Three-Layer Design Rules and Acceptance Checklist into Web Interface Tasks
doran-design is a DSH workflow plugin maintained by Doran1110. It registers the "doran-design" skill and the "doran-design-rules" system-prompt fragment, standardizing the division of labor across shadcn/ui, Canvas UI, and ThreeUI. It also defines an 80/15/5 visual split, performance budgets, and acceptance checklists. After installing the Releases v0.1.1 tarball and configuring bundles, it can be directly applied to landing pages, dashboards, or WebGL interface tasks without modifying AGENTS.md. Requires DSH ≥0.1.0-rc.1. MIT License.
Read MoreOcean Shipping Container Loading Optimization Skill: Computing Container Loading Plans
This article introduces the community Skill on SkillHub: “Sea Shipping Container Loading Optimization” (@user_c85ac47f/container-loading-optimizer, v1.0.0, business-ops). It turns container loading plan computation from manual calculations and modeling into a single conversation: input cargo length/width/height, form (palletized/loose cartons, stackable/non-stackable) and weight; outputs include loading quantity, volume utilization, payload utilization, placement layout for each length/width/height axis, and key points for a loading sketch. It also outlines troubleshooting directions for common issues such as size conflicts, insufficient payload, pallet conflicts, stacking limits, weight distribution, and irregular-shaped cargo. The article lists 10 supported container types (20GP/40GP/40HQ/45HQ/20RF/40RF/20OT/40OT/20FR/40FR), reference coordinates and usage examples, and notes limitations including the need to validate against actual container specifications and that the output is not a force/structural verification.
Read MorePower BI Report Chart Selection and Information Hierarchy Design | Shanshi AI: Automating Chart Selection and Layout Decisions via Prompts
This article introduces the Power BI report visualization design prompt Skill on SkillHub, located at @user_fccf428b/power-bi-report-design-consultation. It is version 1.0.0, sourced from the community, categorized under data-analysis, published by user_fccf428b, with requires_api_key=false. It addresses the report design phase.
Read Moredsh-magpie-discovery: On-demand discovery of Magpie MCP tools to reduce DSH context burden
When DSH connects to Magpie natively, it may register over 150 tool schemas at once. dsh-magpie-discovery only adds a magpie_tools lookup entry; the original mcp__magpie__ tools are exposed after being selected within the session, and execution still flows through the DSH native pipeline. It supports preset mounting or a global Host entry, up to 12 concurrently visible tools, and the atomic replace feature of v1.2.0. Requires the DSH 0.2.1-rc.5 segment and Node 22.19+, and it does not replace the Magpie MCP connection itself.
Read Moredsh-archive-cleaner: Purge DSH archived sessions and free disk space
DSH archiving only hides the sidebar and does not delete session.v4.jsonl.zstd. The community plugin dsh-archive-cleaner (dongfangxy, admin-security) provides a cleanup entry point in Settings → General: it lists archived sessions, moves them into $DSH_HOME/.session-trash by default and writes restore-map.json, with an option for permanent deletion; it also backs up and trims workspace.json and session_projcache.json. Installation: dsh plugin add github:dongfangxy/dsh-archive-cleaner. Restart DSH for the sidebar to update after cleanup; the plugin runs with DSH process privileges, so review the source code and MIT license before installation.
Read MoreRetail & Wholesale Data Dashboard: Dashboard Skill for Store, Chain, and Wholesale Data
This article introduces the "Retail & Wholesale Data Dashboard", a community Skill on SkillHub (located at @user_12aa9699/viz-universal-retail, version 1.0.30, categorized as business-ops, and requiring no API Key). Powered by the viz-universal engine, it targets store retail, chain store, wholesale, and dealership scenarios. It automatically recognizes exported column names—such as sales revenue, cost of goods sold, refund amounts, sales volume, members, stores, sales associates, and channels—switches dashboard terminology to Store, Product, SKU, Sales Associate, and Sales Channel, and directly renders eight industry KPIs: Sales Revenue, Cost of Goods Sold, Gross Profit, Sales Volume, Number of Orders, Average Order Value, Return Rate, and Units per Transaction. It also features an authentic China map with three-level drill-downs (Province → City → District), a world map with built-in drill-downs to state/province boundaries for Japan, Singapore, and the United States, and country-level outline coloring for 217 countries. Furthermore, it offers 17 panel categories, 10 themes, real-time large screen displays, full-map interaction, single-file offline operation, data anonymization with optional password encryption (password-free by default), and compatibility with both mobile and desktop devices. Zero-code adaptation is achieved via a declarative viz-schema. The article also provides a selection guide for the four versions in the same series: use viz-universal-crossborder for cross-border overseas business, viz-universal-k12 for K12 education, and the general viz-universal (switchable via --preset) for other cases or when uncertain. The decision criterion is whether the data contains fields for stores, sales associates, sales revenue, cost of goods sold, members, or units per transaction. Please note that the official page failed to load during this visit; installation commands, configuration fields, and complete usage instructions have not been verified and should be independently confirmed before use.
Read Moredsh-compat-optimize: Zero-Token Fast Path for DSH Plugin Compatibility Checks
`dsh-compat-optimize` is a DSH client plugin maintained by `dongchiluo`. While maintaining the same evaluation logic as `dsh-compat-check`, it avoids multiple LLM round-trips during compatibility checks by compressing tool descriptions, caching `app.asar` header information on disk, and returning the report in a single run. It includes the `node bin/compat-check-cli.mjs` script, which operates offline by default, consumes 0 tokens, and provides exit codes suitable for CI pipelines. Installation involves cloning the repository into `baseDir/plugins`, with configuration details provided in `cordis.patch.yml`. Requires Node.js ≥20; DSH plugin mode requires a version constraint of `>=0.2.1-rc.5 <0.3.0`.
Read MoreCode Review: A Skill for Making PR Review a Systematic Process
Code Review is a code review Skill released by wpank on ClawHub, version 1.0.0, categorized under dev-programming, and requires no API key. It breaks review down into seven dimensions—security, performance, correctness, maintainability, testing, accessibility, and documentation—with built-in, concrete checklists for each dimension, plus severity levels, structured feedback guidelines, and a three-pass review workflow. It also lists anti-patterns to avoid during reviews. The article covers installation commands (npx clawhub@latest install code-review or openclaw skills install @wpank/code-review), typical usage, and applicable scenarios: it is suitable for teams that want a unified review standard, though the checklists are fairly general and should be tailored to the project. It also cannot replace static analysis or CI.
Read More