Plugin
Sfoglia, filtra e installa i plugin di DeepSeek-Harness.
53 plugin trovati
dsh-agent-arena
leemancheung/dsh-agent-arena
Confronta agenti di coding in worktree Git isolati con convalida deterministica, punteggio e applicazione esplicita del vincitore.
dsh-shop-assistant
pengzhou267-ai/dsh-shop-assistant
Postazione per operatori e-commerce: anteprima CSV in batch con adattatori di colonne per marketplace, valutazione riproducibile dei profitti in sei dimensioni, snapshot delle pagine prodotto pubbliche, skill in cinese e knowledge base sostituibile sulle policy del negozio.
everything-search
liilip/everything-search
Global file search in DeepSeek Harness backed by the local Everything (voidtools) index through a bundled es.exe CLI: three entry points (sidebar panel, session header bar and a full-panel overlay), custom relevance scoring, a 50-entry collapsible history and 9 loopback-only HTTP routes. Degrades to an empty soft result, not an error, when Everything, es.exe or the host web server is missing. Windows only.
dsh-plugin-cdp
joansgwjbsu/dsh-plugin-cdp
Chrome DevTools Protocol automation driven through a managed Chrome instance, with rule collection from in-page popups, resume-to-posting match scoring, text dashboards for collected postings, and hot-swap of a long-running worker.
dsh-game-center
stallenlu/dsh-game-center
A panel plugin that keeps mini-games in one place and plays them in the same window. Ships with Tetris: a 10x20 board, seven pieces, a ghost piece and a next-piece preview, line and level scoring, three difficulty levels, and a best score kept in localStorage.
dsh-qqbot-muu
wuwo1979/dsh-qqbot-muu
Pacchetto QQ bot autonomo per DeepSeek Harness. Include memoria SQLite a due livelli con richiamo ippocampale, persona che apprende, livelli di gruppo, risposte locali rapide con arbitro, TTS, sticker, studio video con approvazione e pet desktop in 4 forme via invito (codice, un posto, protezione brute force). Il bridge c2c/gruppi nega per default: care risponde solo alle persone/gruppi scelti dal proprietario; impostazioni condivise con la persona. Disponibili anche allowlist, aperto o disattivato. L’inizializzazione compila solo valori assenti senza sovrascrivere modifiche. Esercizi di colloquio/quiz in chat, punteggio locale e conservazione configurabile. Richiede QQBOT_APPID, QQBOT_SECRET e Node.js 22.5+.
dsh-local-writing-suite
zz12hui/dsh-local-writing-suite
Aggiunge due strumenti di audit e quattro skill per testi cinesi medi e lunghi (anche narrativa) e revisione documentale: valuta sette dimensioni dello stile AI, segnala problemi bloccanti con numeri di riga e conserva su file lo stato di continuità dei manoscritti lunghi. Non installarlo insieme al vecchio dsh-deai-audit dello stesso autore: registra gli stessi nomi di strumenti.
dsh-tender-matrix
perrylink/dsh-tender-matrix
Verifica la coerenza aritmetica tra massimi, punteggi registrati e totale dei fattori nella matrice di valutazione. Riporta differenze, senza giudicare correttezza o equità della valutazione.
forge
mjxupup/forge
Quality gate Forge per DeepSeek Harness (dsh): gate di task, lettura prima della modifica, intercettazione dei pericoli bash e punteggio di qualità, guidati dalla CLI forge attraverso i punti di intercettazione tipizzati di DSH.
dsh-skill-eval
carlslin/dsh-skill-eval
Scores every skill 0-100 from real execution telemetry (load success, follow-up tool errors, user corrections, ignored loads and cost) with 95% confidence intervals, and turns that evidence into fixes the agent can act on.
dsh-memory-vault
07-dot/dsh-memory-vault
Recalls an Obsidian Markdown vault before each task: a per-agent prompt context is registered on agent creation and re-queried with the current task text, adding a standing profile plus the notes that match, while three tools read, write and audit the vault (inbox backlog, broken links, duplicate candidates, stale goals). Scoring is local n-gram matching with no embedding model, no external service and no runtime dependencies.
dsh-mode-router
guyeqiuchen/dsh-mode-router
Classifies each incoming message as chat or work by rule-based scoring and injects the matching answer protocol, with manual /chat, /work and /auto overrides and a mode_status diagnostic tool.
dsh-model-probe
vhow123/dsh-model-probe
Fingerprint configured DSH models without trusting their reported token counts: a 55-vector tokenizer reference, four greedy identity probes, refusal-prose and stop-vocabulary probes, and a local 18-item weighted intelligence battery scoring 0-100 with a tier and per-question evidence, plus animated or custom SVG and HTML drawing probes, quick SVG limits, concurrency controls, and latency and token metrics. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-echochat-plugin
verchiel666/dsh-echochat-plugin
Adds one tool, echo_judge, that scores 1-4 draft replies to an emotionally loaded message on three steps (perception, mental-state inference, response strategy), combines the steps with a cascade gate and step-level credit assignment, and names the weakest step to redo; scoring runs through ctx.llm of the running engine, so no API key is needed.
dsh-chronicle
zuoyunlai/dsh-chronicle
Daily chronicle for DeepSeek Harness: collects session events, closes the previous calendar day after midnight into a Markdown week file (LLM scoring adds a daily summary; rule scoring does not), and extracts durable facts — decisions, conventions, pitfalls — that merge across days and can be superseded. 10 tools, a read-only sidebar panel, rule export, and a standalone Obsidian vault; zero third-party dependencies.
dsh-kit (dsh-auto-skill)
474885697-alt/dsh-kit
Matches each new task against installed skills with deterministic keyword scoring and injects the best one without being asked; records effective operations as per-skill notes for later runs.
dsh-docwright
sharework-ai/dsh-docwright
A document generation plugin for DeepSeek Harness: JSON is the core output, structurally managing document content; unifies parameter definition and inheritance, material extraction, validation checking, and scoring across document generation, keeping output on-target, fast, and token-efficient; ships a built-in COSMIC scenario pack as a worked example plus a built-in guide for authoring new scenario packs.
zying-erp
chensuqi631-max/zying-erp
Adds a direct data channel (signed local API, no browser extension needed) for bulk ASIN collection, one-click listing through ifast.top, live freight quotes, saved seller-account logins, a headless-browser ASIN finder and variant colour detection. Amazon product research workbench for DeepSeek Harness: category, brand and follow-seller collectors driven through the local Edge browser, a product library with unified filters, an FBA/FBM/self-operated profit calculator, blue-ocean category scoring with candidate picks, trademark lookup, supplier image search and Excel export. Proprietary software: it installs and starts without a license, but every data call returns 403 until the author issues a device-bound license key. Needs Edge started with --remote-debugging-port=9222 and signed in to Amazon; starts a local backend on port 3088. The separate 智赢 collector browser extension is optional and adds size, weight, trademark and monthly-sales fields.
guster
lumos-789/guster
Audits and evolves agent context at four scopes: a single repository, a group of related repos, a knowledge hub, or the whole machine. Discovers projects, instruction files, skills, tools, knowledge, state, evidence and credential references; reports drift, duplicate facts, broken pointers, budget overruns, unindexed knowledge, stale state and unregistered credentials; scores each scope on its own dimensions; and turns findings into reviewable migration plans that are validated against the published schema before apply, confine writes to declared roots, and back up every file before moving it. The format contract is a versioned spec (CTX rules, markdownlint-style IDs) following open conventions — the AGENTS.md open format, llms.txt-shaped indexes, YAML front-matter note headers — now backed by published JSON Schema contracts (draft 2020-12) for the hub manifest and the plan JSON, plus an editor modeline that validates hub.yaml with zero configuration. The hub is declarative (schema 2, zones, sections may live outside the hub root) with machine-readable register/v1 project ledgers and knowledge/v1 note headers; a one-pass check command runs scan, doctor and score, and state writes are atomic and lock-protected; scoring stays honest about missing evidence — a waiver greens the gate, never the score. Ships a stdlib-only Python CLI plus two skills; credentials are referenced by path and never printed. Requires Python 3.9+ (stdlib only) and DSH 0.2.1-rc.2 or newer, below 0.3.0.
dsh-cat-star
zengchunhua-boost/dsh-cat-star
Cat beauty scoring plugin for the DSH Web GUI with CFA-style scorecards, a China-market price estimate, and an optional public leaderboard.
dsh-photo-picker (plugin)
uoiszero/dsh-photo-picker
A DSH workbench for picking photos from local folders on macOS and Windows: local dedupe, filtering and grouping; AI grid triage and scoring with an image-capable model you supply (the plugin bundles no model, credentials or quota); AI scene labels with manual correction, tunable edit recipes, human review, calibration, and export with scene/edit metadata.
dsh-typing-studio
654970/dsh-typing-studio
Esercizio di digitazione bilingue in cinese e inglese, con brani a tempo, valutazione compatibile con IME, feedback carattere per carattere e risultati salvati localmente.
dsh-tool-browser
yuehancn/dsh-tool-browser
Apre una pagina, attende il tempo necessario, estrae l’articolo leggibile e acquisisce uno screenshot. Playwright è facoltativo; se manca, usa il recupero statico e lo segnala nel risultato. Distingue una pagina in cui JavaScript non è stato eseguito da una renderizzata. Il contenuto viene scelto in base alla densità di prosa dei sottoalberi candidati, non ai nomi dei tag: l’articolo interno prevale sul contenitore che include più documento.
rainbow-fart-dsh
maybejustlikethis/rainbow-fart-dsh
Aggiunge alle sessioni DSH Web punteggi combo, riepiloghi delle attività, valutazioni per turno e incoraggiamento facoltativo basato su Jev.