Vai al contenuto principale

Plugin

Sfoglia, filtra e installa i plugin di DeepSeek-Harness.

70 plugin trovati

L

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.

04 giorni faStrumenti e capacità
Z

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.

09 giorni faFlussi e automazioneMIT
T

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.

09 giorni faFlussi e automazioneMIT
1

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).

011 giorni faMemoriaMIT
R

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.

08 giorni faIntegrazioni e accesso remotoMIT
1

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.

015 giorni faMemoriaMIT
B

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-

020 giorni faFlussi e automazioneMIT
B

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.

018 giorni faStrumenti e capacitàMIT
X

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.

017 giorni faMemoriaMIT
L

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.

022 giorni faCompetenzeMIT
C

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 @.

024 giorni faGit e code reviewMIT
1

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.

017 giorni faMemoriaMIT
Y

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.

0l’altro ieriStrumenti e capacitàMIT
M

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.

012 giorni faFlussi e automazioneMIT
K

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.

0mese scorsoFlussi e automazioneMIT
W

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.

0mese scorsoCompetenzeMIT
S

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.

0mese scorsoCompetenzeMIT
Q

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.

0mese scorsoCompetenzeMIT
Z

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.

015 ore faVisione, voce e multimodaleMIT
W

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.

0mese scorsoCompetenzeMIT
O

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.

03 mesi faFlussi e automazioneMIT
L

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).

03 mesi faFlussi e automazioneApache-2.0