プラグイン
DeepSeek-Harness プラグインを閲覧・絞り込み・インストールできます。
128 件のプラグインが見つかりました
dsh-prompt-optimizer
windrover/dsh-prompt-optimizer
composer の input tools 行に prompt optimizer を追加:category と template を選び、✨で下書きをその場で書き換えます。ワンクリック undo、Basic/Context/Image category、実行キャンセル、経過時間と token 使用量表示に対応。task 指示の書換え、段階計画、安全性調査の枠組み、system prompt role card、text-to-image/image-to-image prompt を含む15 template を同梱。Context template は照応解決に直近の会話ターンを読みます。host model service 経由で呼び出し、設定で model と budget を公開します。出力 guard はユーザー指定制約の保持を確認し、自動再試行ではなく警告します。dsh 0.1.7 と0.2向け。
dsh-agent-instructions-editor
mari23333/dsh-agent-instructions-editor
DeepSeek Harnessの設定から、グローバルAGENTS.mdとプロジェクトのAGENTS.md/CLAUDE.mdカスタム指示を編集します。プロジェクト階層を検出し、バイト予算を表示し、保存時の競合を処理します。
dsh-personalization
crazy-l118/dsh-personalization
DeepSeek Harness(dsh)向けのパーソナライズ機能です。アシスタントに自分が何者か、アシスタント自身の役割、望ましい振る舞いを教えます。dsh Settings に Personalization ページ(カスタム指示、ニックネーム、ペルソナ)を追加し、内容を各 agent… に挿入します。
dsh-instruction-memory
hero476/dsh-instruction-memory
DSH設定UIで編集した継続指示を、以後の各ターンのシステムプロンプトに注入します。
dsh-sightline
charlie-wang-03/dsh-sightline
同じworkspaceでDeepSeek Harness、Codex、Claude Codeの指示レイヤーを比較します。
agent-loop-workflow
lesliewylie/agent-loop-workflow
DeepSeek Harness 向けのプロジェクト非依存なマルチエージェント協調プロトコル:暴走ループを止めるループガード、6 フィールドのハンドオフ形式、リスク階層別のレビュールーティング、固定の verify→commit→push→review→close 手順。同じルールを各エージェントに貼り付ける代わりの 1 つのスキルです。
dsh-inspector
cocosgt/dsh-inspector
現在の dsh セッションの実行中の指示チェーンとプロジェクトスキルを検査・管理できます。その場での作成・編集にも対応し、表示されている内容がそのままモデルに渡されます。
dsh-session-tidy
349840432m-dev/dsh-session-tidy
One-click tidy for the DSH session list: archive blank sessions and sessions inactive for N days, keep the newest N per workspace, clean truncated or instruction-prefixed titles, and disambiguate duplicate titles — with a preview sheet, selectable presets, and batch undo. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-github-push
imcaibaicai/dsh-github-push
Pushes a local folder to GitHub on one instruction: proxy autodetection, the token read from the OS credential store and scrubbed from every log line, a pre-push secret gate, and SHA read-back verification of the remote branch.
dsh-wechat-assistant
huangzihengcmd/dsh-wechat-assistant
Drive DeepSeek Harness from WeChat: scan a QR code to sign in, send instructions in WeChat, and the agent reply lands back in the same chat window. Several agents can share one WeChat account, each with its own model, preset and context, switched from the chat with /use. Only the configured owner WeChat account can drive the agent; other senders are rejected by default and require explicit approval.
dsh-quickjot
spankingsnail/dsh-quickjot
随手记 lets AI turn a sentence into a note, a to-do or a dated event. No need to choose a type, fill out a form or pick a date first: give your instructions in a conversation or open 随口记, and AI organizes the item from what you say, asking for clarification when information is unclear. When plans change, keep talking: “move it to tomorrow at ten”, “mark it complete” or “add the work tag”, without finding the item again and editing each field. Items stay on your machine and are shared across conversations, with in-app reminders and WeChat notifications through DSH-IM.
dsh-tts-voice
pandaman0759/dsh-tts-voice
End-of-turn voice summary: the model calls voice_say once before finishing a reply so the conclusion is spoken through Breeze TTS, with Chinese bracket audio tags (laughter, sighs, pauses) and optional performance instructions. Audio is synthesized host-side and played from browser memory without ever touching disk; the character limit is a writing target for the model, not a cut-off, so long lines still play in full. The API key stays in the credential store, and an optional daily Breeze check-in is included. Needs a Breeze API key and sends the spoken text to the Breeze service; its HTTP routes (including the settings route that stores the key) have no DSH access check.
dsh-agents-md-presets
salvare013/dsh-agents-md-presets
Named AGENTS.md presets for DSH: save instruction sets under $DSH_HOME/agents-md-presets, apply one to the current conversation workspace, edit bodies in your own editor, and keep one rolling backup of the file being overwritten.
dsh-chinese-reasoning
yingshuozhang/dsh-chinese-reasoning
Makes a DeepSeek Harness agent reason in Simplified Chinese: each turn it appends one runtime-context instruction at the end of the conversation, and it can keep a stable declaration in the system prompt as well. Settings pick Simplified Chinese or off, and whether that declaration is included.
dsh-gpt-adapter
lxjmaster/dsh-gpt-adapter
DeepSeek Harness plugin for GPT models and Codex instructions, skills, plugin resources, and MCP configuration.
dsh-sync
anime-fan-5903/dsh-sync
Synchronizes native DSH instructions, user Skills, and reviewed portable settings across devices through Microsoft OneDrive, with optional cloud encryption and explicit conflict resolution; conversations and credentials are excluded.
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-plugin-antigravity-agents
domush/dsh-plugin-antigravity-agents
Native Google Antigravity agents loader and subagent orchestration engine with model selection and Web UI settings integration. Loads agent definitions from ~/.agents/agents and the workspace's .agents/agents; the selected main agent's instructions go into the system prompt, and a matching agent's instructions are prepended to DSH's own subagent and spawn_teammate calls. Settings are written to .agents/agents/settings.json in the workspace.
dsh-broadcast
yyhy110421/dsh-broadcast
Sends one instruction to a chosen group of existing DSH sessions at once, with attachments, optional answer collection and up to eight temporary subagents.
dsh-prompt-boost-model
amyaxy/dsh-prompt-boost-model
Prompt enhancement for the DSH composer, with a model picker that lists the models the host actually offers: a Boost button beside the composer sends the current draft to a model on the Host, shows the rewrite in a before/after overlay, and replaces the draft only when you confirm. While boosting, the button glyph becomes a spinning arc; once a rewrite is applied the same button becomes an in-place Undo that restores the original draft and then returns to its idle state. Settings hold the enable switch, a provider/model choice rendered as a grouped dropdown built from the live provider list (including configurable providers that are not set up yet) rather than free-text fields, temperature, output limit, timeout and optional custom instructions. Empty or reasoning-only model answers are reported with their real cause instead of a generic failure, and the Host endpoint only answers loopback requests from the same origin.
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 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 with light profiles, sections may live outside the hub root), 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-draft-studio
wufeng0105/dsh-draft-studio
You type half a thought — "make me a scraper for Douban" — and the AI has to guess the rest. Click one button beside the input box and that line becomes a full instruction it can actually follow: what to build, what to output, what the limits are, how you'll know it's done. It never picks for you: where you haven't decided something (which library, which format), it lists the options instead of choosing one. The result is still a draft — never sent, and one click or Ctrl+Z puts your original back. Four presets (general / code / writing / translation), each one editable text you can rewrite to taste, and you choose which buttons appear. Optional: read the last few turns of the conversation so "that thing I mentioned" resolves correctly; use the current session's model or pin a specific one. Pure JS, no build, no bundled dependencies.
dsh-session-manager
tsechiyuan/dsh-session-manager
Session manager and session settings for the DSH sidebar: sessions grouped by workspace with archive filters, title search, batch archive and a read-only transcript preview; global and per-workspace name, occupation and instructions injected into the system prompt; optional recent-only and hide-workspace filters for the sidebar.
dsh-workspace-rules
winson-young/dsh-workspace-rules
A settings page that edits the current project's CLAUDE.local.md, the private per-project instruction file DSH's built-in loader reads at the start of a session; the file stays out of git.