Plugins
Navegue, filtre e instale plugins do DeepSeek-Harness.
216 plugins encontrados
dsh-typing-practice
yishan/dsh-typing-practice
English, Chinese and Cantonese typing practice with Pinyin and Jyutping hints, timed or passage modes, local conversation excerpts and local records.
dsh-agent-lab
limtide/dsh-agent-lab
Records a session as a run, replays it in an isolated workspace copy with another model or prompt, diffs the two trajectories side by side, aggregates runs into a task × variant matrix, and gates regressions with task assertions and a CI exit code.
dsh-eval-harness
ltj002/dsh-eval-harness
Agent application development evaluation skill (skill bundle) for DeepSeek Harness: offline/online suites judged from audit side effects, baseline diff with zero tolerance for safety regressions, and mutation tests proving the evaluators themselves catch regressions. Framework-agnostic - needs a callable chat endpoint and queryable tool-call records. DSH host compatibility is deliberately undeclared.
dsh-qingshi-plugin
qq1003240666/dsh-qingshi-plugin
Qingshi diary and family-tree assistant: reads and writes career records, resolves relatives by kinship term, and drives the real H5 pages in a desktop window.
dsh-cost-voice
gongfpp/dsh-cost-voice
Dabaifan Arrival Voice Announcements speaks the estimated spend per turn with the bundled Dabaifan voice by default; Alipay is optional. Amounts come from dsh-cost-meter or model-price estimates, not payment records. No runtime TTS service. Code is MIT; the bundled Alipay clips come from Reathin/XVoice (no licence), the Dabaifan voice is a MiMo clone and the icon is a fan-made meme, all for personal, non-commercial use with this plugin only.
dsh-rigui
avenyq/dsh-rigui
A personal life workbench as a sidebar panel: sleep, meals, workouts, spending, weight, schedule and to-dos share one page of cards that react to one another, and one sentence typed at the top is turned into structured records by the model configured in DSH. Records and card layout stay in local browser storage.
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.
dsh-dailyboard
ginoxiang/dsh-dailyboard
DailyBoard — a daily work task board for the DSH Web GUI with a one-month calendar of colored timeline bars and day tasks, a daily checklist, a seven-day week view with completion checkboxes and drag-to-reschedule, a draggable 24-hour day timeline, ordered per-day subtasks, weekly and every-N-days recurring tasks with per-occurrence result records, a long-term progress view opened from the calendar header, per-day completion for long-term tasks, tasks that can be marked “For others” by choosing one of the added recipients (shown as note + email), a collapsible daily email reminder that can be pushed to WeChat and can remind other people such as partners or relatives (each extra recipient has an email, a note and its own send time), AI task extraction from natural language with smart date parsing (single dates become day tasks, “this week/month” starts from today, Enter extracts, indented lines become visible subtasks that can be promoted), completion rewards on the calendar (completed days turn solid green with a large check, plus “N days this month · X-day streak” stats), and CSV export with an auto-generated records.csv mirror, and a specific-day all-day strip that lets long-term tasks be dragged onto the 24-hour timeline to create draggable scheduled blocks. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-agentic-pet
beyondgjc/dsh-agentic-pet
A model-driven desktop pet for dsh, derived from PC2005-cloud/dsh-pet (MIT): a transparent always-on-top companion that follows your agent sessions, races the Web UI to answer approvals and questions, and runs an autonomous inner voice — world-clock and self-scheduled wakes, dreams, and bond-anniversary milestones, speaking through pet_say/pet_do, with lines read aloud through BreezeBlue TTS using your own API key. Memory is a per-pet continuity journal — an append-only hash chain, rotation into an archive, self-written stage summaries, and keyword recall with tag clues — alongside letters, a shared living-room board, pet-to-pet messages, an affection ledger, and an interactions audit that records how every approval and question actually ended. Memory and ledgers live in ~/.dsh/whale598/<petId>/; the settings page adds per-pet switches and a tool-call audit dashboard (all-time / last 30 days). It uses its own /whale598 route and data directory, so it is a separate pet from dsh-pet rather than a replacement for it. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-claimcheck
daphne999/dsh-claimcheck
Runs project check commands itself and records the real exit codes, pins the result to a git or file workspace fingerprint, expires the evidence when the tree changes, and reminds the agent to verify before claiming completion.
dsh-plugins (steward)
zou240/dsh-plugins
Turns a stated rule into a checkable intake card and writes it into the right AGENTS.md, and keeps project plans, a rule ledger, project records, handoffs, a change log and a timeline.
dsh-codex-runner
halftin/dsh-codex-runner
Runs local Codex CLI tasks from DSH on Windows with background execution, progress queries, follow-up instructions, completed chat records, and optional supervision; requires Node 22.23.4+, DSH >=0.2.1-rc.3 <0.3.0, and an installed, authenticated Codex CLI.
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.
mindforge-guard-labs-dsh-evidence-check
veeduzyl-hue/mindforge-guard-labs-dsh-evidence-check
Deterministic review of user-declared synthetic AI-agent claims against structured events, snapshots, authorization, policy and coverage records; returns bounded verdicts with reasons and evidence references.
dsh-fengniao-company-search
keyblues/dsh-fengniao-company-search
Look up Chinese companies inside the conversation: name a company and get its business registration, shareholders, executives, outbound investments and registration changes, plus judicial and operating-risk records such as enforcement, dishonest judgment debtor, consumption restriction, abnormal operation, serious illegality and administrative penalties (11 dimension groups). Results render as conversation cards with fields and the raw payload on expand, and the API key is saved from the plugin page into the Harness credential store.
dsh-session-cleanup
lucascaleb-ggg/dsh-session-cleanup
Batch session cleanup for DeepSeek Harness — pick a workspace, see which sessions are archived, and permanently delete logs, projection caches and workspace records.
dsh-fish-notes
yeahmahao/dsh-fish-notes
Registra notas curtas do agente sobre o que pesquisou ou pensou e as lista em um painel lateral.
dsh-namecheap-mcp
2000lla/dsh-namecheap-mcp
Conector MCP do Namecheap para DeepSeek Harness: oferece domínios, registros DNS, servidores de nomes e contatos como ferramentas nativas do agente.
dsh-audit
shark00i/dsh-audit
Audita plugins do DeepSeek Harness: verificação pré-instalação somente leitura que classifica cada pacote de S a D, além de monitor runtime que registra início/fim de plugins, chamadas sensíveis a ferramentas e estimativas de tokens por plugin no painel Settings.
dsh-agent-manager
dogbotowo-oss/dsh-agent-manager
Gerencia subagentes e colegas do Agent Teams no DeepSeek Harness: interrompe instâncias ativas e depois realmente as remove, aposentando registros do catálogo e roster com tombstones de log que preservam a sequência e movendo diretórios de sessão para uma lixeira recuperável. Inclui ferramentas de modelo, painel no cabeçalho da conversa e CLI offline.
dsh-window-size-lock
koewen/dsh-window-size-lock
Somente Windows (vincula user32.dll via koffi; inativo no macOS/Linux). Memoriza tamanho e posição da janela principal do DeepSeek Harness e restaura ambos a cada início, reafirmando-os durante um período de tolerância para superar o layout padrão. Movimentos/redimensionamentos manuais estáveis viram o novo bloqueio; estados minimizado, maximizado ou tela cheia nunca são salvos, nem o retângulo padrão definido pelo DSH. Continua visível ao trocar de monitor. Compatível com DSH 0.2.1-rc.3+.
dsh-capability-gateway
xiaomao361/dsh-capability-gateway
Oculta do catálogo voltado ao modelo as skills e os servidores MCP de terceiros habilitados por opt-in e os disponibiliza por uma única capability tool: pesquisar por intenção, ler o schema ou as instruções da skill e então chamar. Um journal local registra apenas metadados, nunca o texto da consulta nem os argumentos.
dsh-ccswitch-usage
lyaqanyi/dsh-ccswitch-usage
Registra o uso de tokens do DeepSeek Harness no CC Switch, uma linha por chamada de modelo, compartilhando o ledger de deduplicação do próprio importador DSH para evitar dupla contagem. Na primeira execução, completa os registros de uso do CC Switch a partir dos logs de sessão existentes.
dsh-domain-proxy
heywalter/dsh-domain-proxy
Escolhe hostnames API dos provedores configurados ou os adiciona manualmente para encaminhar solicitações Fetch/Undici correspondentes do backend DSH por um proxy HTTP(S) local existente; outras rotas permanecem iguais. Registros opcionais em memória mostram destinos reais, espera até o primeiro conteúdo, taxa de tokens e uso, sem salvar prompts, respostas nem chaves API.