Plugins
Navegue, filtre e instale plugins do DeepSeek-Harness.
91 plugins encontrados
dsh-prompt-optimizer
alive114514awa/dsh-prompt-optimizer
Aprimora prompts com perguntas guiadas e prévias editáveis usando Harness AI ou Codex nativo em Web, desktop e TUI; só aplica rascunhos após confirmação do usuário.
dsh-input-optimizer
xkjxziochu/dsh-input-optimizer
Reescreve o rascunho do compositor DSH como prompt mais claro e executável usando as rotas LLM do próprio harness, mostrando a comparação original/otimizada antes de aplicar.
ai-input-enhancer
zhengzeyong9527-droid/ai-input-enhancer
Adiciona otimização de prompts e controles para cancelar e desfazer ao compositor do DeepSeek Harness.
dsh-dynamic-thinking-chain
lovelydazai/dsh-dynamic-thinking-chain
Permite que o DeepSeek Harness pense dinamicamente como uma pessoa e avalie automaticamente a dificuldade das tarefas para escolher uma cadeia de raciocínio adequada.
duo (dsh-plugin)
cz-zl/duo
Plugin de avaliação limitada de agentes para DSH: compara o original com um prompt candidato ou alterações de configuração compatíveis, usando verificações fornecidas pelo usuário; registra evidências e custos e deixa a adoção a critério do usuário.
dsh-prompt-refiner
glh5835/dsh-prompt-refiner
Plugin “Refinador de prompt” para o compositor do DeepSeek Harness: transforma um rascunho vago com um clique em prompt estruturado (objetivo/contexto/etapas/requisitos/[suposições]). O custo pode ser roteado a outro modelo (é possível trocar o padrão por um otimizador mais barato); armazena resultados em cache e registra uso de tokens. A versão estática é a principal; a dinâmica pode ser testada sem instalação.
neoxider-mcp-hub
neoxider/neoxider-mcp-hub
Uma ferramenta MCP em vez de todos os esquemas: broker de capacidades sob demanda que reduz em 94,4% o contexto residente de ferramentas, conforme a medição indicada. Pesquise, inspecione, habilite e chame servidores MCP e Skills quando necessário.
dsh-agent-hub
jax629321/dsh-agent-hub
Console de orquestração multiagente em chat de grupo para DSH: decisão autônoma, distribuição de tarefas, verificação e otimização iterativa de trabalhos longos. Inclui backend próprio e instala com `dsh plugin add`.
isingq-toolkit (dsh-plugin)
ising-tech/isingq-toolkit
Plugin nativo do DeepSeek Harness para IsingQ: modelagem e validação QUBO guiadas no dispositivo e, em seguida, resolução remota confirmada pelo usuário.
multisim-mcp
yxy050208/multisim-mcp
Plugin do DeepSeek Harness para geração, simulação, otimização de circuitos e relatórios de laboratório no NI Multisim via MCP
zzy-dsh-prompt-optimizer
zhengzeyong9527-droid/zzy-dsh-prompt-optimizer
Adiciona controles de otimização de prompt, cancelamento e desfazer ao compositor do DeepSeek Harness.
dsh-dcp
chiro2001/dsh-dcp
Plugin de gerenciamento dinâmico de contexto para o DeepSeek Harness (Dynamic Context Pruning for dsh), inspirado no opencode-dcp.
dsh-prompt-optimizer
lklkuu/dsh-prompt-optimizer
Adds an Optimize button to the composer. One click rewrites the current draft with the model you already selected, using the "basic optimization" prompt from linshenkx/prompt-optimizer (41.5k stars) verbatim, and writes the result straight back into the input box without adding a chat turn. A running rewrite can be cancelled by clicking again; requests time out after 150 seconds and the previous draft stays one click away. English and Chinese copy, no runtime dependencies, no stored credentials, no port of its own: the route rides DSH's authenticated /api mount.
dsh-prompt-template
calmandfocused/dsh-prompt-template
Rewrites the composer draft in three modes (system prompt, user prompt, iteration), keeps {{variable}} placeholders verbatim, and exposes the same operation as the optimize_prompt agent tool.
dsh-plugins (github-manager)
feahter/dsh-plugins
Sidebar GitHub panel plus github_* agent tools: list your repositories, inspect issues and pull requests, and create, update or comment on issues.
dsh-plugins (dsh-360)
feahter/dsh-plugins
Health check for a DSH profile: scores skills and agent instruction files, subagent definitions and presets on one shared 18-bucket S–E grade scale, with a sidebar panel, four dsh360_* tools, and a backup with undo for every write.
dsh-plugins (realtime-voice)
feahter/dsh-plugins
Continuous dictation for the composer using a local SenseVoice ONNX model on CPU: recognised text appears while you speak, a pause ends the sentence and writes it into the input box, and audio never leaves the machine.
dsh-mcp-lazy
liuhange789/dsh-mcp-lazy
On-demand MCP tool loading. Only the mcp__* tools listed in the coreTools whitelist (max 5) stay in a session's tool set; every other MCP tool definition is actually removed from the request through the session-scoped tools.restrict() API and comes back only after the model calls lazy_load_tool. A tools/pre-execute gate turns calls to unloaded tools into a load-it-first error, and activation resets when the session ends.
dsh-plugins (archive-rsi)
feahter/dsh-plugins
Session archive with tags, notes and per-session metrics, plus a Plan-Do-Check-Act loop over the archived sessions that produces prompt and AGENTS.md rules and re-measures them on later sessions. Runs locally without calling a model.
dsh-plugins (mind-canvas)
feahter/dsh-plugins
Infinite-canvas mind map in the sidebar: grow nodes with Tab, tidy a branch into a tree, ask the assistant to expand a node into child ideas, and export to Markdown, OPML, FreeMind, JSON or PNG.
dsh-tool-index
gunjanpatel359/dsh-tool-index
Sends deferred MCP tool definitions as an index of names, parameter signatures and one-line summaries grouped by server, with tool_details returning a full schema on request and call_tool running the real tool. Reading a schema or running a tool does not change the model-visible tool list, so the prompt cache is not invalidated.
dsh-prompt-library
heartqwq/dsh-prompt-library
A searchable library of 60 Chinese task templates with variables, examples, sources and Skill methods, plus draft-safe prompt optimization using a configured DSH model.
dsh-memory-router
dcd887/dsh-memory-router
Intercepts DSH tool results before the model reads them: dedupe cache for repeated calls, a declarative decision graph that replaces large outputs with structured digests, an injection gate, and an honest token ledger that includes a negative-return account for over-compression. Measured 1400-1600 tokens saved per hit; the cumulative ledger is currently negative and the README says why, including that it cannot skip model turns.
dsh-token-panorama
jiuwu02/dsh-token-panorama
Shows where every session's tokens go: lifetime totals, cache hit rate, peak/off-peak cost, a calendar heatmap, a trend chart, per-model and per-workspace breakdowns, and a session tree revealing subagent sessions, with CSV/JSON export. Also ships context clear/compact actions and a prompt optimization button.