dsh-pstack: Using the pstack Workflow on DeepSeek Harness
dsh-pstack is maintained by l246804, porting Cursor pstack's skills, playbook, and subagent workflows to DeepSeek Harness (DSH). It bridges the interface differences between DSH and Cursor through five native tools, including pstack_skill and pstack_subagent. Install it via `dsh plugin --profile web add dsh-pstack`. It requires DSH >=0.2.1-rc.5 and Node.js >=24.21.1, and on first use you must run `/setup-pstack` to generate `pstack-models.mdc`. The main entry point is `/poteto-mode`, accompanied by slash commands for architecture, verification, decision logs, and more. The plugin runs with DSH process privileges, so please review the source code and MIT license before installing.
Read MoreRegulatory Conflict Self-Checker: Locating Clause-Level Issues Before Policy Disputes Become Incidents
The Policy-conflict-checker (@user_fa14b5bc/policy-conflict-checker, version 1.0.0, sourced from the community, categorized under knowledge-management) is a Skill designed for plain-text reasoning. It accepts two or more policy or notification texts as input and outputs a clause-level conflict matrix. It identifies five types of conflicts: interpretation discrepancies, inconsistent standards, process conflicts, benefit offsets, and timeline conflicts, while providing four-level severity ratings and a prioritized revision list. It addresses the challenges of managing numerous policy documents with scattered revisions and interpretation drift, where manual clause-by-clause comparison is costly and prone to omissions. Its key advantage lies in pinpointing conflicts to specific clauses and indicating which ones should be revised first, facilitating pre-publication self-checks. The tag requires_api_key=false indicates that no API Key is needed and there are no programming dependencies. Platform data (crawled on 2026-11-04): Rating 100,000, Downloads 1,287, Installs 0. As official documentation does not provide CLI installation commands or configuration file fields, no inferences are made in this article. Usage limitations: Recognition capability depends on the clarity of the clause phrasing; it performs static comparison only and does not judge legality or replace legal advice; conflict types are limited to the five preset categories.
Read Moredsh-line-bot: Integrating LINE Messaging API into DeepSeek Harness
dsh-line-bot (Hanson0901) integrates the LINE Official Account Messaging API into DSH: local webhook signature verification, HTTPS exposure via Cloudflare Tunnel, automatic renewal of channel credentials, and a reply generation Agent running inside the same process. Supports "Da Fei Yu" or plug-in self-defined persona, proactive sending, Reply Splitting, and a complete LINE Bot Configuration Dashboard. Requires DSH ≥ 0.2.0-rc.1 and Node ≥ 22; can be installed via Dashboard bundle, `npx dsh-line-bot install`, or `dsh plugin add`. MIT-licensed, configurations stored under `~/.dsh/line-bot/`.
Read MoreProject Graph Assistant: Automation Skill for Repetitive White-collar Tasks
Project Graph Assistant, released by Zhiyu Technology, falls under the office-efficiency category. Version 1.0.0 does not require an API key. It helps white-collar professionals handle repetitive tasks related to business automation and quickly obtain structured and reusable work deliverables. Its value lies in reducing the time spent on repetitive organization rather than replacing business judgment. The number of installations is 0. It is recommended to conduct small-scale validation before integrating the assistant.
Read MoreEnglish Speaking Practice Assistant: Breaking Down Oral Practice into a Replicable Path
The Oral English Practice Assistant is a general-purpose Skill designed for oral practice, published and maintained by Kunlun Growth. Classified under "education" and sourced from an "enterprise," its current version is 1.1.2. It addresses the lack of structured pathways, random practice content, and non-standardized feedback in oral language learning. The Skill solidifies the practice process into a chain: Level Assessment → Scenario Breakdown → Input Accumulation → Output Practice → Feedback & Correction → Consolidation. It incorporates three methodologies—three-dimensional positioning, the lexical chunk method, and shadowing—and breaks down into five functional modules: level assessment, scenario breakdown, input accumulation, output practice, and feedback & correction. The Skill page indicates `requires_api_key=false`, meaning it can be used without an API Key. Official documentation does not include installation commands or reproducible invocation examples; therefore, it is recommended to refer to the official page to confirm installation methods and compatible clients before integration. It is suitable for individual learners seeking structured oral practice paths, developers looking to integrate oral coaching capabilities into their products, and educational researchers requiring references for standard oral practice workflows. It is important to note that the Skill does not mention adaptive difficulty adjustment or pronunciation scoring capabilities, and specific details regarding compliance safeguards are not elaborated in the provided materials. These should be verified independently before deploying in products面向 the public.
Read MoreContest PPT HTML Design System_Qiuye Workplace: Creating a Unified HTML Preview Page for Competition PPTs
This is a PPT HTML page design system for national and educational innovation competitions, produced by Qiuye PPT. Published on SkillHub under the "community" source, it is categorized under "office-efficiency" with version 1.0.4. It standardizes the design specifications for HTML preview pages of competition presentations: a red and white color scheme, vertical title bars in the top-left corner, a 1600×900 canvas (16:9 ratio), and a card-based content layout. It is applicable to core pages such as pain point analysis, technical solutions, and business models. This system is triggered when users need to create HTML preview pages for competition PPTs; it outputs HTML preview pages rather than editable .pptx files. The tag `requires_api_key=false` indicates that no additional API key is required. The documentation does not provide installation commands, directory paths, or configuration fields; the body text states this factually and recommends referring to the official page for details. As no official reproducible examples are provided, no commands or prompts are fabricated. The applicable scenarios involve the creation of HTML preview pages for competitions such as the National Innovation Competition and Educational Innovation Competition. Please note that this is not equivalent to a finished PPT product; the color scheme and layout are tailored for competition scenarios, and the page types are concentrated on core presentation pages.
Read MoreLesson Presentation Scripts and Micro-Course Scripts: Structuring Lesson Preparation Content into Formal Documents
"Lesson Plan and Micro-course Script" (@kunlungrowth/edu-micro-lesson) is an educational Skill published by Kunlun Growth on SkillHub. Versioned at 1.0.0 and categorized under education, this enterprise-sourced Skill holds a rating of 100000 and has seen 1417 downloads, tagged with requires_api_key=false. Addressing the issue of generic large language models producing teaching research drafts lacking fixed sections, it solidifies textbook analysis, student profile analysis, teaching objectives, teaching methods, instructional procedures, and design rationale into the generation workflow. By inputting the topic and student information, it produces structurally consistent lesson plans and accompanying micro-course scripts, ensuring the procedure divisions in both correspond to each other. The article outlines core features, activation methods (note that the documentation lacks command-line installation instructions, specifying only compatibility with the general SKILL.md format and no API Key requirement), and typical usage examples. It also discusses applicable scenarios and limitations, such as the necessity for manual verification of textbook and student content, and suggests testing with real topics first due to low installation numbers.
Read Moredsh-legal-workbench: A Workbench for Reading and Writing Obsidian Notes in the DSH Right Panel
dsh-legal-workbench is a DSH client plugin maintained by gaog88666-boop. It provides SOP tree browsing on the right side of the conversation, inline glossary editing, recording with optional Volcengine real-time transcription, full-text search, and optional email drafts and usage badges. Requires DSH ≥0.2.0. Install via `dsh plugin --profile desktop/web add dsh-legal-workbench`. On first use, configure the Markdown library path. All data and the ~/.dsh-workbench configuration are stored locally, with no account or telemetry required.
Read MoreSpeak Plain (dsh-speak-plain): Polish DSH final answers with a selected model
Maintained by Exception-H, the DSH plugin **dsh-speak-plain** polishes final answers using configured models without affecting the primary model's task or context. The polished version is displayed by default, while the original answer is collapsible. It supports a master switch and auto/manual polishing modes (v0.3.1), offers GenUI compatibility, and does not store API keys. Based on the official README, this article covers installation commands, configuration paths, typical usage, and MVP boundaries (e.g., timeout, word count limits, polishing only successful final answers), while advising users to review the source code and MIT license prior to installation.
Read Moredsh-tts-bridge-wechatagent-bridge: Transforming TTS Bridge Audio into Native WeChat Voice Messages
A DSH workflow plugin by epsilonH-eps that records the audio read by `dsh-tts-bridge` from `chat.deepseek.com` in Edge via WASAPI, falling back to `edge-tts` when necessary. The audio is then converted to SILK and sent as a WeChat native voice message (`localType=34`) via a `WeChatAgent` hook or Frida. It exposes the `wechat_voice_send` tool for WeChat agents. Supported environments are limited to Windows and WeChat 4.1.10.27. Installation requires running `setup.ps1`, adding it to the desktop profile via a link method, and configuring `dshAccess`. MIT license, v0.1.0.
Read Moredsh-zotero-skill: Streamlining Zotero Literature Workflow into a Pipeline in DeepSeek Harness
dsh-zotero-skill is a workflow plugin (MIT, npm 0.5.5) maintained by Eason-0712 for DeepSeek Harness. Utilizing the Python standard library to connect the local Zotero API with OpenAlex, it covers literature discovery, tracking research frontiers, filtering core papers, tag organization, batch reading packages, categorization and gap discovery, BibTeX and LaTeX/Markdown citation, optional 0.5 full-text deep reading, and daily OpenAlex indexing. Installation: `dsh plugin --profile <profile> add dsh-zotero-skill`; requires Node 20+, Python 3.10+, Zotero 10, and the local API. The plugin runs with DSH process privileges; Zotero authorization is required for database writes.
Read MorePatent Literature Visualization Analysis Assistant: Decomposing Patent Text into Structural Diagrams and Reports
This article introduces the community-sourced Skill "Patent Document Visualization Analysis Assistant" (located at @user_921c36cf/patent-deep-analysis, version 1.0.1, classified under knowledge-management). It exclusively focuses on extracting, decomposing, summarizing, and visualizing the technical content and protection scope of patent documents, without conducting infringement, invalidity, or FTO assessments. Core capabilities include: autonomous selection of visualization schemes based on technical domain and claim complexity (claim structure tree, technology decomposition diagram, functional model diagram, protection scope heatmap); extracting distinguishing features and core issues through comparison with self-described prior art; and identifying potential technical problems that the patent may address. It supports input via PDF, images, and DOCX through OCR or text parsing, ultimately producing self-contained HTML reports with diagrams rendered in real-time via Mermaid. The tag requires_api_key=false indicates no API key is required. The article provides a trigger keyword list, reproducible invocation workflows, and usage scenario considerations, while noting that installation commands are not included in the materials, and that ratings and download counts vary across different crawl snapshots and therefore no fixed values are cited.
Read MoreWhole-House Customization Pricing & Pitfall Advisor: Breaking Down Cabinet Quotes into Costs
"Whole-House Customization Quotation & Pitfall Advisor" is a Q&A-style Skill maintained by user_8ca2df90, a publisher in the SkillHub community. Positioned from a factory-side perspective, it aims to help homeowners decipher whole-house customization quotations. It estimates cabinet projection area based on floor area and provides tiered price ranges for cities nationwide. It breaks down quotations into factory unit prices, retail prices, markup rates, and eight major cost modules to assess merchant profit margins. It exposes common practices such as inflated building areas, hidden fees in packages, pricing by unfolded area, substituting high-quality hardware with inferior ones, and "free design" traps. Additionally, it provides five essential clauses for fixed-price contracts, an 8-element audit for quotation sheets, and a 9-step acceptance checklist. The coverage spans from tier-1 cities to county towns, addressing environments from humid southern regions to northern underfloor heating. The persona is "Lao Yang," a whole-house customization factory owner with 20 years of experience, emphasizing conclusion-first approaches and authentic, non-AI-generated content. According to retrieved data, the version is 2.2.2, categorized under life-service, sourced from the community, and tagged with requires_api_key=false (no API Key required). This document does not fabricate installation commands or configuration fields; installation methods must be checked on the official page. The quotations are ranges, not actual prices, and cannot replace on-site measurement. The cost analysis is a comparative model from a factory perspective. In case of specific disputes regarding contracts and acceptance checklists, consultation with local professional advice is recommended.
Read MoreIntroduction to the Doubao Image Generation Skill: Using Your Own Key to Access Seedream
Doubao Image Generation (Zhishu Channel) is an image generation Skill based on SKILL.md that utilizes the user's Key from Zhishu (zhishuai.net) to call the Doubao Seedream series models. It supports text-to-image, image-to-image, and image editing, consuming the user's Zhishu account quota rather than WorkBuddy credits; user notification and consent are required before each generation. This article verifies the official address and the parameters, capabilities, environment variables, and supported resolutions of the similarly named Volcano Engine channel version (released by wanxing0724). It further explains the differences between the two versions regarding publisher, channel, rating, and download count, and outlines the configuration and usage constraints.
Read Moredsh-subagent-bridge: Building a Subagent Bridge between Codex and DeepSeek Harness
`dsh-subagent-bridge` is a DSH workflow plugin maintained by Dogtiti that exposes a local MCP endpoint within the host. It enables Codex or Claude Code to dispatch tasks such as `dsh_task`/`dsh_spawn` to the Harness in a subagent manner and retrieve final responses. DSH agents can also reverse-delegate via `codex_dispatch` and `claude_dispatch`. It supports specifying models and workspaces per call, queue/steer follow-ups, and unattended hypothetical policies. Requirements: DSH ^0.2.1-0; MIT license; the endpoint is written to `~/.dsh/bridge/endpoint.json`.
Read Moredsh-video-vision: Storyboards and Text Maps Enabling the Harness to Directly "See" Video
dsh-video-vision is a DSH client plugin maintained by Destinhue that uses ffmpeg for local video analysis, providing five tool chains: video_probe, video_outline (zero visual token text map), video_storyboard, video_zoom, and video_read. It supports file paths, direct links, and Bilibili links. To install, enter the plugin directory, execute `node bin/install.mjs`, and restart DSH. It is suitable for scenarios requiring Agent reasoning with reference to screen content or on-screen text. Before use, please review the source code and MIT license, and note that the plugin runs with DSH process permissions.
Read MoreShuoruan · Cross-border E-commerce Profit Calculation: Turning Selling Price and Procurement Cost into Dynamic Break-even Models
Input the selling price and procurement costs to generate a formula-linked Excel P&L model and a one-page Word decision report. The system covers Amazon FBA, Temu (Full-Service), Shein, TikTok Shop, and DTC sites, featuring automatic switching between commission-based and full-service reconciliation modes. It includes four inverse calculation indicators: break-even selling price, break-even ACOS, reverse-calculated pricing based on target net margin, and price reduction headroom. It offers a four-tier traffic light grading for net profit margins. Selling prices support multi-currency with editable exchange rates, while costs are in CNY. The solution is zero-dependency, requires no coding, uses no API keys, and works offline; industry defaults are applied for missing parameters and clearly marked as estimates.
Read MoreDSH Technique for Accelerating Large File Downloads in GitHub Releases
Maintained by chenjrastro-tech, the DSH plugin `github-release-download-acceleration` operates with zero dependencies under Windows PowerShell 5.1 and the system curl. It features self-checking of proxies and mirrors, testing across four types of routes, time-limited concurrent ladders for large assets, multi-segment range downloads, and SHA256 verification using release digests. It supports natural language skills and the `ghdl.ps1`/`ghdl.sh` runners. Installation via `dsh plugin add github:chenjrastro-tech/github-release-download-acceleration` is recommended.
Read MoreDating Coach: Orchestrating Emotional Methodologies and Networking Resources into a Skillset
Love Coach is the main entry point for a skill package published on SkillHub, located at @org-bzwfrdvh/love-coach, published by AIPDD, version 1.0.1, categorized under education. It contains 10 sub-skills: 4 on the methodology side, distilled from approximately 200,000 words of first-hand emotional materials, containing 5 mental models, 9 decision heuristics, and a complete expression DNA, covering scenarios such as relationship analysis, relationship judgment, chat responses, pickup openers, and more; and 6 on the networking side based on AIworkin MCP, covering contact sourcing, demand posting, AI communication preview, SNS expansion, service listing, order taking, and more. The main entry point is responsible for demand guidance, information validation, and sub-skill orchestration, claiming to have successfully tested 30 MCP tools. An API Key is required for configuration. Specific installation commands and configuration fields could not be obtained from the official page during verification, and this article has not fabricated any information. It is suitable for products that need to handle emotional counseling conversations in Agents or connect to networking resources. Platform compliance requirements should be confirmed before integrating with the networking side.
Read Moredsh-fish-river: The "Big Fat Fish" Where Personalities Can Only Grow from the Event Stream
dsh-fish-river is an MIT-integrated version of ssamurias/dsh-fish and Britneycode/dsh-fish-soul: It has no personality settings page; personality relies on events.jsonl and four-stage growth. Among the three-layer memory, only the growth layer defines "who she is". The same identity can speak in DSH sessions as well as via QQ, Bilibili private messages, and optionally Douyin. Channels are disabled by default with visibility and whitelist constraints. It introduces installation commands, memory models, social layer gates, and typical usage, and reminds that plugins run with DSH process permissions.
Read Moredsh-island: DeepSeek Harness Desktop Dynamic Island
dsh-island is a community-maintained desktop plugin for DeepSeek Harness (Windows, requires Harness 0.2.1-rc.5) that provides a task status bar similar to the Dynamic Island at screen edges. When expanded, it allows users to view plan progress and context usage, stop tasks, approve permissions, respond to agent questions, and continue messaging without opening the main window. It also includes usage statistics and cost estimation based on official pricing. To install, add dsh-island from the Harness plugin page, or run `dsh plugin --profile desktop add dsh-island` after exiting the system tray. Licensed under MIT, currently at version 0.6.1.
Read MoreExam Question Analysis Generator: Reverse-Engineering Answers into Two Sets of Exam Paper Files
The Exam Question Parser (@user_015022d9/exam-question-parser) is a community-sourced education category Skill, version 1.0.0, requiring no API Key. It targets scenarios where existing answers and format requirements need to be transformed into exam papers: first parsing answers (extracting correct answers, identifying knowledge domains and concepts, annotating difficulty levels, extracting solution approaches and common pitfalls), then assigning question types based on concept nature (multiple choice/multiple selection/fill-in-the-blank/experimental/essay) and composing academic Chinese question stems, constructing distractors based on common errors from the original analysis, and allocating scores according to format requirements. It subsequently calls scripts/generate_exam_docs.py to generate a question file (exam structure table + grouped questions, with no trace of answers) and an answer file (answer key table + detailed question-by-question analysis), then directly displays both files for review. Trigger phrases include "generate questions from answers", "generate exam questions", "create exam", "reverse-engineer questions from answers", "generate exam from answers", etc. On SkillHub, it has a rating of 100000, 1284 downloads, and 0 installations.
Read MoreFact-Checking: Installing a Provenance Firewall for Agents
Fact Check (@user_b8060655/cue-fact-check) is an Agent Skill released by community developer user_b8060655. Categorized under knowledge-management (Version 1.0.1), it requires a user-provided Cue backend API key. Designed for journalists, editors, and researchers, it systematically deconstructs factual claims found in press releases, social media posts, research reports, policy interpretations, and AI-generated content. It traces sources hierarchically according to a credibility structure: T0 official sources → T1 authoritative media → T2 industry media → T3 supplementary sources. By employing a firewall mechanism to eliminate circular reasoning, it provides deep links for every conclusion and applies a four-tier rating system: ✅ Fact accurate / ❌ Fact error / ⚠️ Bias / ⚪ Unverifiable. The tool focuses on identifying temporal displacement, detail discrepancies, recycled news, and manipulated content. It is not suitable for subjective opinion disputes, personal privacy investigations, verification of real-time breaking news, or legal evidence authentication.
Read MoreCinematic AI Short Drama & Comic Pipeline: The "Prompt Skill" Workflow for One-Stop Production
Released by Woda Technology on SkillHub (coordinates: @woda/ai-maju-duanju, version 1.0.0, category: content-creation, metrics: rating 100,000, 1,481 downloads), this Skill is positioned as an integrated workflow for AI short dramas. It accepts input in the form of novels, plot synopses, or story ideas to generate an end-to-end, ready-to-use production package. This includes a cinematic production document (`script.html` featuring a three-sentence storyline, "Save the Cat" beats, and character/scene/visual tone definitions), a film-style "STYLE LOCK" visual scheme, an asset package of image prompts for character face locks/setting sheets/storyboards/props, a complete storyboard set of video prompts (anchored second-by-second for character/environment/style/camera/audio/timeline, including English text and recommended duration), and a production manual covering the entire process from script to final cut. All terminology is derived from a built-in 10-chapter library of film and television prompt terms (film/master styles, lighting, color, shot types, camera movement, sound, acting, editing) without fabrication, ensuring stylistic consistency and professional reproducibility. It is suitable for AI short drama creators, novelists, and short-form video content teams. Official URL: https://api.skillhub.cn/woda/ai-maju-duanju.
Read Moredsh-telegram-relay: Relay DSH Q&A, Approvals, and Round Summaries to Telegram
dsh-telegram-relay is a DSH client plugin maintained by sflaer that launches a loopback control panel on the host side and forwards ask_user_question prompts, tool approvals, turn summaries, and sub-agent notifications via a Telegram Bot. Both the Web UI and Telegram can respond simultaneously, with the first response taking effect. It supports ru/en/zh and uses long polling, eliminating the need for a webhook. Based on the official README, this article covers installation for desktop and web profiles, bot binding, whitelist and sub-agent toggles, cordis.patch.yml configuration options, and security considerations.
Read More