Plugin
Sfoglia, filtra e installa i plugin di DeepSeek-Harness.
70 plugin trovati
kingdee-portal
littlebeaverstudio/kingdee-portal
Local Kingdee Cloud (金蝶云星空) business portal for DeepSeek Harness: open the operations dashboard in the sidebar with your own Kingdee account; data stays on your machine. Needs Python 3.10+ with Flask and requests (pip install -r requirements.txt) and a local clone of this repo linked into the profile; verified on Windows with DSH Desktop only.
dsh-handshake
zhangyong0010/dsh-handshake
Hand off local development tasks between Codex and DeepSeek Harness with original requirements, project agreements, workspace checks, and a relay board. Needs the Codex desktop app (or a codexBinary path in the settings); verified on macOS only.
dsh-evolve-preset (dsh-evolve-preset)
taoziliyouchong/dsh-evolve-preset
An agent preset that adds a working mode to DeepSeek Harness: the mode text has the model analyze requirements and plan before acting, open a gate document, and reply in a fixed three-block shape. The task tree and session-start profile injection are separate companion packages in the same repository, installed from a clone with scripts/install.mjs; only the term dictionary (dsh-term-dict) comes with this package, and without the task tree the model writes its own alignment bar. Needs DSH 0.2.1-alpha.1 or later.
dsh-elysia-memory
1148462398-hub/dsh-elysia-memory
Elysia's memory plugin for dsh. One shared, human-editable MEMORY.md across every session: two-disk mirror, history snapshots, cross-process write lock; entries tier between the main file and a searchable archive by hit frequency; retrieval is keyword co-occurrence plus BM25. Nine sections (persona, requirements, corrections, lessons, methods, requests, sessions, method library, ingested docs) plus a dedicated self-identity section for a character's own self-cognition, injected above the persona. Ships an opt-in memory pack (packs/elysia: 61,903-char identity + 2,482-char persona, distilled from 1,696 officially-confirmed voice lines and 112,175 dialogue lines) that is off by default, backs up before writing, only touches identity/persona, and can be uninstalled. Also opt-in voice playback through a local GPT-SoVITS engine, a skills library, and a sticker library that sends a fitting sticker at the right moment. On by default: after every reply a bubble with an avatar pops up (voice.bubble: false turns it off), and unless the agent already spoke itself it costs one extra small-model request. Opt-in voice playback needs a local GPT-SoVITS engine (about 27 GB, installed separately, NVIDIA GPU required; the plugin downloads about 200 MB of weights) and is Windows-only; the automatic second-drive mirror is Windows-only too (elsewhere set mirrorPath, otherwise there is no mirror).
dsh-xhs-style
refreshing-czq/dsh-xhs-style
Adds a requirements-discovery gate before product selection, version choices and competitive analysis: 2–3 clarification rounds with 2–4 decision-changing questions, validation of real pain points and hard constraints, comparison of original, alternative and minimum-cost routes, and a confirmation card before research and copywriting. Confirmed reports keep the Xiaohongshu-style structure, concrete steps, audited images and source links. Ordinary lookups and explicit user skips bypass the questionnaire. Host-only static prompt sections with no config, client UI or dependencies.
dsh-elysia
1148462398-hub/dsh-elysia
Elysia's memory plugin for dsh. One shared, human-editable MEMORY.md across every session: two-disk mirror, history snapshots, cross-process write lock; entries tier between the main file and a searchable archive by hit frequency; retrieval is keyword co-occurrence plus BM25. Nine sections (persona, requirements, corrections, lessons, methods, requests, sessions, method library, ingested docs) plus a dedicated self-identity section for a character's own self-cognition, injected above the persona. Ships an opt-in memory pack (packs/elysia: 61,903-char identity + 2,482-char persona, distilled from 1,696 officially-confirmed voice lines and 112,175 dialogue lines — not written by hand, measured) that is off by default, backs up before writing, only touches identity/persona, and can be uninstalled. Also opt-in voice playback through a local GPT-SoVITS engine, a skills library, and a sticker library that sends a fitting sticker at the right moment.
dsh-yunxiao-taskboard
btboys/dsh-yunxiao-taskboard
DeepSeek Harness plugin: Aliyun Yunxiao requirements and defects kanban by status, with detail drawer, image preview, one-click session dispatch, Req/Bug creation, and native tools for status transitions, work item creation, project member lookup, change-
dsh_resume_warehouse (resume-warehouse)
bababoooi/dsh_resume_warehouse
Local-first resume warehouse for DeepSeek Harness: package your work into reusable bullets, import an existing resume into a template, analyse a job description (including the school-tier preference it implies), assemble a tailored Chinese or English resume and export a PDF named position-name-school. The whole app ships inside the npm package — server/, web/, skills/, scripts/, requirements.txt, no git clone needed — and one tool starts, stops and health-checks it; the first start installs the dependencies into app/.venv. Needs Python 3.10+ and macOS or Linux (bash). Nothing leaves the machine except the LLM calls you confirm.
dsh-reqtrace
xingyanghaifu/dsh-reqtrace
Requirement-to-evidence audit for DSH sessions: maps each requirement to tool calls, files and commands, records per-requirement verification, and sends missing items back to the agent.
search-school-sci-skill
liu-daniel7/search-school-sci-skill
Measures one university department's research output: matches author affiliation strings against a college's known name variants (detecting same-named departments at other universities), backfills papers that only name the university by faculty author IDs, classifies each paper by journal tier (CAS partition with Top flag, JCR quartile, CCF, Chinese core via a CNKI export merger), splits staff from student first authors, and writes a workbook with a dashboard sheet, a filterable paper list, a teacher-by-direction matrix and per-teacher statistics. Student authorship is inferred from affiliation and staff lists, not verified against enrolment records. Requires Python 3.9+ with pandas and openpyxl (pip install -r requirements.txt); papers come from the OpenAlex API, whose free per-IP quota is limited, and Chinese-journal coverage needs a manual CNKI export.
dsh-gitee-enterprise
cnhuashao/dsh-gitee-enterprise
Workbench degli elementi Gitee Enterprise nella barra laterale Harness: esplora progetti, attività, requisiti e bug; consulta dettagli, sottoattività, commenti e Markdown; crea o modifica elementi e richiamali con @.
dsh-shared-memory
1148462398-hub/dsh-shared-memory
Memoria Markdown condivisa da tutte le sessioni DSH: persona, requisiti, correzioni, lezioni, metodi, richieste, sessioni, libreria di metodi e documenti importati. Viene replicata su un secondo disco con snapshot delle versioni e blocco di scrittura tra processi. Le voci passano dal file principale all’archivio ricercabile in base a frequenza e rilievo ripetuto; ricerca tramite co-occorrenza di keyword e BM25. Include playbook SKILL.md con esecuzione facoltativa e protetta di `run.mjs` e una libreria in cui l’utente importa immagini, classificate per umore dal plugin che invia automaticamente lo sticker adatto al momento giusto.
ppt-assistant
yujpvc/ppt-assistant
Preset PowerPoint end-to-end per DeepSeek Harness: creazione di deck modificabili, modifiche che preservano i template, rendering e controlli qualità strutturali. Richiede Python 3.10+ e installazione delle dipendenze in `requirements.txt`; rendering anche LibreOffice e pdftoppm, OCR di scansioni Tesseract.
dsh-project-supervisor
midnight-1991/dsh-project-supervisor
Beta: supervisore di progetto per DeepSeek Harness. Regole permanenti e pannello Web (tre interruttori, modalità di assegnazione) suddividono un obiettivo in dialoghi paralleli tra compagni, verificano le basi ingegneristiche, raccolgono requisiti dei nuovi progetti e proteggono i principianti. Le regole permanenti provengono da un passaggio separato e facoltativo dell’installer del kit repository.
dsh-code-team
kkomia/dsh-code-team
Preset Project Development Mode e bacheca di sviluppo in chat per DeepSeek Harness: la conversazione lead chiarisce i requisiti e delega all’Agent Team; una bacheca flottante segue ogni richiesta di modifica nelle fasi di assegnazione, esecuzione, test e accettazione, con 7 strumenti dedicati.
scenes-skill-creator
wasteoneslife/scenes-skill-creator
Console di creazione skill per Web UI: recupera le skill ufficiali di authoring e passa i requisiti a Huawei Cloud, a un creator generico o a un creator REST API. Valuta la skill generata con una rubrica su 10 e restituisce le detrazioni dettagliate al creator finché raggiunge 8,5/10.
local-solution-first
shenhe3939-debug/local-solution-first
Skill di riuso basato su evidenze per DeepSeek Harness: prima di implementare, portare, scegliere dipendenze o risolvere problemi di un tool, cerca per livelli soluzioni esistenti nel progetto e nella macchina locali. Decide il riuso con prove verificabili, lo rifiuta se requisiti essenziali o rischi non sono soddisfatti e segnala ciò che non ha potuto verificare. Il bundle DSH registra la skill in ctx.skills.
dsh-scan2md
qiujiyuantiantian/dsh-scan2md
OCR di PDF scansiti e composti solo da immagini in Markdown. Poiché un libro richiede circa un’ora, ogni pagina ha un checkpoint per riprendere dopo un’interruzione; un log mostra l’avanzamento e il rapporto qualità segnala pagine vuote e righe a bassa affidabilità. Richiede Python 3.10+ e `pip install -r requirements`; al primo avvio scarica il modello OCR.
dsh-ocr
zirscard/dsh-ocr
Registra due tool per DeepSeek Harness. `doc_ocr` converte PDF scansiti e immagini in testo per pagina, tabelle finanziarie con verifica del bilancio e corrispondenze di clausole contrattuali tramite RapidOCR locale o Zhipu GLM-OCR cloud. `doc_preprocess` trasforma una directory di file grezzi in una knowledge base Obsidian con pipeline a sette fasi, routing backend e salto incrementale basato su sha256. I numeri che non tornano vengono segnalati, non inventati. L’engine locale richiede Python con rapidocr-onnxruntime, pypdfium2 e Pillow (`pip install -r requirements.txt`); GLM richiede ZHIPU_API_KEY.
dsh-skill-creator
wasteoneslife/dsh-skill-creator
Console Web per creare skill: recupera gli skill creator ufficiali, invia requisiti a creator Huawei Cloud/generic/REST API e valuta su rubrica da 10, restituendo detrazioni dettagliate finché raggiunge 8,5/10.
dsh-deploy-master
olympianz/dsh-deploy-master
Plugin DSH per automatizzare la pubblicazione di un progetto locale: crea e pubblica un repository GitHub (git init/commit/push + topics + tag + release), sincronizza requisiti/progresso con Linear, pubblica su npm e annuncia nelle Discussions della community.
DSH-Project-Initialization
lorvaste/dsh-project-initialization
Preset agent che trasforma un’idea in una riga in requisiti, piano tecnico e base di manutenzione; ogni fase viene riformulata e confermata da te prima di procedere. Nessun preset di scenario: carica in base al contesto 73 skill atomiche (6 principali, un dispatcher di verifica e 66 sub-skill).