プラグイン
DeepSeek-Harness プラグインを閲覧・絞り込み・インストールできます。
119 件のプラグインが見つかりました
dsh-novel-forge
watersxya/dsh-novel-forge
dsh Web GUI向けのAI小説制作ワークベンチ。小説構想をdocx/textから取り込み、LLMで巻・章を計画し、各章3000–4000文字で生成、自動AIレビューと作品全体監査を行い、完成本をMarkdown/TXTで出力します。
docindex
johnxu22786/docindex
workspace文書(MD/PDF/DOCX/TXT)のローカル意味検索インデックス。FTS5 BM25とローカル埋め込みを組み合わせ、行番号付きの引用を表示し、増分更新します。
dsh-chip-design-closure
renshaokai/dsh-chip-design-closure
Adds the Design closure agent preset and the chip-design skill for digital chip front-end work: architecture budgets, design specs, functional and acceptance point lists, RTL, timing closure and PPA. Ships three scripts — a 38-rule spec linter, a Markdown to docx/PDF converter, and a draw.io / Mermaid / WaveDrom figure renderer.
dsh-pure-search
silentlamb05147/dsh-pure-search
Local document search for DSH: eight kb_* tools that ingest Markdown, TXT, PDF, DOCX, HTML and JSON into workspace- and session-scoped indexes, returning matching passages with path, chapter and line-range citations; BM25 by default with optional dense retrieval, fully offline and host-only.
gongwen-writer
hexiaobai2012/gongwen-writer
Chinese official-document writing assistant for DeepSeek Harness: first-turn research and three outline candidates, GB/T 9704 Word rendering, live polished DOCX, paragraph and sentence review, official-source fact checking, official WeChat accounts, and project memory.
dsh-chat-lite
wth373737/dsh-chat-lite
A separate chat area for DeepSeek Harness: a sidebar panel and a phone-installable PWA over the same conversations, with a self-managed history library (day grouping, full-text search), attachments inline, and host-side text extraction for PDF, DOCX, PPTX and XLSX so the model needs no file tools. Conversations live in their own directory, not in a coding workspace. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-ppt-master
dashan-0079/dsh-ppt-master
Ships the PPT Master skill (upstream v6.8.0, MIT) byte for byte as a DeepSeek Harness bundle and registers it with ctx.skills as ppt-master. Adds a cross-platform CLI (doctor, install-deps, run) that handles Python discovery, UTF-8 stdio, a writable work copy and an isolated venv, so the skill turns PDF, DOCX, web pages or Markdown into natively editable .pptx decks.
mont-BidCopilot
royrao2007/mont-bidcopilot
Dual-mode tender and bid drafting engine: 32 mont_* tools with code-enforced compliance rules, a fact-source allowlist, three human gates with a tamper-evident audit chain, and pure-JS .docx export.
dsh-gov-doc-router
liuhange789/dsh-gov-doc-router
Checks Chinese government document drafts against GB/T 9704 formatting rules, auto-fixes deterministic issues, and exports a compliant .docx.
dsh-xiumi-studio
27synthesis/dsh-xiumi-studio
Turns a Word manuscript and its images into a laid-out WeChat article: live preview panel, filling the text and photos into an existing Xiumi template, generated covers, and publishing into the user's own Xiumi article library. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-duanju-slice
yanghangju/dsh-duanju-slice
Short-drama clipping workbench: given a drama folder, a script DOCX, an export folder and a content direction, it picks the matching lines, obtains their real time codes by streaming the episode audio to Doubao speech recognition (a Doubao voice API key is required), tightens the cut to the returned word timestamps, checks the boundary frames, and exports an editable Jianying draft plus an MP4 carrying the source dialogue, BGM and sound effects; trim points and volume can be revised in the same chat and every revision is kept as a new version.
stellar-shelf
zhang-1239/stellar-shelf
A local-first bookshelf rendered as a 3D starfield: galaxies group books by genre, star colour shows unread, reading and finished, and cover art appears as you approach. Imports EPUB, PDF, TXT, MOBI, AZW3, DOCX and Markdown, opens them in a full-screen reader with six display modes and eight Chinese fonts, and stores highlights and notes in local SQLite.
dsh-onlyoffice
dake6767/dsh-onlyoffice
DSH web plugin: open .docx/.xlsx/.pptx from the sidebar file manager in an embedded OnlyOffice editor (static SDK, no Document Server).
dsh-resume-studio
zwh0714/dsh-resume-studio
Resume workshop: one JSON renders HTML, DOCX and PDF through three presets that can be restyled with theme tokens (accent, font size, line height, section style) instead of hand-written CSS. It fits the page count you ask for and checks the writing (number coverage, bold density, entry length, date format). DOCX is the master and the PDF is converted from it, so both paginate identically; sections can be timeline, project, list or paragraph, named anything you like, and existing .doc/.docx/.odt resumes can be imported first. A4 or Letter, Chinese or English.
dsh-r-workbench
hougelangley/dsh-r-workbench
R data workbench with six tools: ingest CSV/TSV/text, Excel and xlsx-compatible WPS .et, ODS, JSON/NDJSON and ZIP files; clean and infer types; score whether the data can support analysis (PROCEED, CONDITIONAL or STOP); run group comparisons, correlations, association tests and calendar-month trends with effect sizes and BH correction; and write self-contained HTML, Markdown, Quarto source or DOCX reports. STOP blocks analysis and reporting.
dsh-hwp-translate
sanshui258/dsh-hwp-translate
Translates .hwp/.hwpx (Hangul) and .docx documents into the language the session model writes - Chinese is the common case, but Korean to English or English to Korean works the same way - keeping tables, bullets, indentation and font size, and writes the result beside the original as *_zh. hwp_extract returns the document segments as JSON (50 per page by default, 200 max, next_offset for pagination); hwp_apply takes {segment id: translation} and returns the output path with applied and missing counts. The plugin never calls an API and accepts no API key; its bundled 10 MB translator only reads and writes the file locally. Windows only: .hwpx and .docx are parsed in pure Python, while legacy .hwp drives the installed Hangul over COM and requires allow_hangul.
METIS_ACADEMIC
tzukwan/metis_academic
AI-assisted research workbench with editable step workflows, on-demand skill binding, a live execution graph and in-project document review (needs a local Python with python-docx, python-pptx, openpyxl and PyMuPDF), while keeping existing projects on their original configurations. Requires DSH 0.2.2 or later.
dsh-plugin-thesis-format (dsh-plugin)
zx310610/dsh-plugin-thesis-format
Checks thesis formatting in .docx and .doc files against a YAML spec, covering fonts, line spacing, margins, heading numbering, captions and references. Includes one built-in spec for Bengbu College of Technology and Business, and custom specs are supported.
dsh-docx2md
stallenlu/dsh-docx2md
Converts formula-bearing Word documents into Markdown with LaTeX, handling OLE equation objects, native Word OMML equations and image-based formulas; keeps equation numbers and structure. Needs Python 3.9+ (or uv); OLE and image formulas are transcribed by a vision-capable model from rendered images, and rendering needs Windows or LibreOffice.
dsh-formula-docx
red-rayux/dsh-formula-docx
Converts Markdown into .docx with native Word equations (OMML), then exports a PDF to verify every formula renders. Needs Python 3.9+ with lxml, latex2mathml and python-docx; the PDF check also needs pymupdf and Word or LibreOffice.
dsh-doc-read
dcd887/dsh-doc-read
Token-efficient document reader for DeepSeek Harness: outline / ranged read / grep for PDF, DOCX, XLSX, TXT.
dsh-local-kb
hql6662/dsh-local-kb
Local full-disk knowledge base: indexes documents from C:/ and E:/ into a SQLite FTS5 trigram index over filename, body, and path, with a searchable DSH sidebar panel, no-keyword browse, usefulness/topic tags, and a token-efficient kb agent tool. Windows only; building the index needs a system Python 3 with PyMuPDF and python-docx (plus python-pptx and openpyxl for PPTX/XLSX), and no prebuilt index ships with the plugin.
dsh-kit (dsh-rulebook)
474885697-alt/dsh-kit
Extracts chapters, numbered clauses, keyword tables and numeric values from a docx, txt or md rulebook into JSON, and flags duplicate clauses and missing values.
dsh-article-annotator
elycheng/dsh-article-annotator
Article Review page in DSH's native right sidebar: turns Markdown, Word, PowerPoint and PDF articles into sentence-addressable text, lets you comment on any sentence, and hands the open review to the agent as a composer draft. Six agent tools let the model read every comment, revise the article (in place for Markdown, as a sibling <name>.revised.md for binary formats), resolve the comments, and record recurring wording preferences into a long-term writing-style memory injected into later prompts. Extraction includes a dependency-free DOCX/PPTX reader; PDF text extraction runs locally through the host's Python + pypdf (or poppler's pdftotext) and is unavailable without one of them. No network calls, no telemetry.