メインコンテンツへスキップ

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。

1519 件のプラグインが見つかりました

H

dsh-ross-ai-assistant

hidden-seed/dsh-ross-ai-assistant

Unofficial DSH fork of the AMD Ross AI Assistant. Upstream skills snapshot 2026.10.1; adds the DeepSeek Harness bundle, Settings page, and install docs.

0一昨日スキルMIT
D

dsh-deepsight

deeparchi-ai/dsh-deepsight

Adds a deep-research agent preset with the DeepSight methodology skill bundled, plus three tools that set an evidence contract, audit claim tiers along the provenance chain of every action item, and summarize the persisted ledger. Delivery is blocked while an action basis derives from unverified estimates or an unresolved conflict.

04 日前スキルMIT
D

dsh-ppt-master

dashan-0079/dsh-ppt-master

Ships the PPT Master skill (upstream v6.8.0, MIT) byte for byte as a DeepSeek Harness bundle and registers it with ctx.skills as ppt-master. Adds a cross-platform CLI (doctor, install-deps, run) that handles Python discovery, UTF-8 stdio, a writable work copy and an isolated venv, so the skill turns PDF, DOCX, web pages or Markdown into natively editable .pptx decks.

03 日前スキル
Q

dsh-hsr

qui11zxy/dsh-hsr

Query Honkai: Star Rail data as agent tools: character stats, skills, Light Cones, relic sets and current endgame stages. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

03 日前ツールと機能MIT
L

dsh-caveman

lornatang/dsh-caveman

Caveman skills and tools for DeepSeek Harness: response styles, recoverable tool-result compression, model routing, browser tools, and delegation.

0一昨日使用量と課金Apache-2.0
N

dsh-xiaochajian-shizhong

novajin0826/dsh-xiaochajian-shizhong

Adds a Skills group to the composer + menu with enable/disable filtering, and a manager panel that searches, toggles, deletes and batch-manages installed skills. Choosing a skill inserts its slash command into the draft without sending. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

04 日前UI拡張MIT
G

dsh-workspace (dsh-plugin-airlock)

gabrielbav/dsh-workspace

Puts every plugin, skill and subagent bundle through 6 security scanners (Cisco Skill Scanner, SkillScan, Cisco MCP Scanner, OSV-Scanner, Trivy, Gitleaks) and an optional LLM judge on your own DSH model, in a quarantine with install scripts off, checking for prompt injection, MCP tool poisoning, vulnerable dependencies and leaked secrets; then it installs, asks you, or blocks, and confirms the installed files are the ones it scanned. Works on stock DSH.

05 日前セキュリティと権限MIT
H

dsh-gameart

highho/dsh-gameart

ComfyUI game-art production lines: 12 seeded pipelines (SD1.5 and SDXL) for character concepts, sprite alpha, expression diffs, lineart colorize, 3-view turnaround, prop icons, seamless tiles, HD upscale, backgrounds, nine-slice UI, layered character parts and FX, driven through 7 tools plus 3 agent presets and 6 skills.

08 日前ワークフローと自動化MIT
Y

dsh-expert-role

yjnmedia/dsh-expert-role

Expert Library (also called Expert Role or Private Think Tank). Domain knowledge libraries for agents: each expert is a folder with SKILL.md, a manifest and references; only its name and one-line description sit in the skill catalog until the model loads it, so a large corpus stays out of the context. Ships two experts (design, DSH plugin) that are copied into the library on first start, fill-only and never overwriting yours. 12 tools create experts, move material in, find documents, plan and record research, dispatch steps to child sessions or open a standalone workspace. A gap list shows which questions went unanswered, a five-star maturity score uses structure, coverage, content, freshness and research closure (the fifth star also needs real usage), and a panel shows per session which expert was loaded and which file was read. It reads and writes files under the expert root; its HTTP routes accept local requests only; dispatching steps or opening a workspace creates child sessions and spends tokens.

0一昨日スキルMIT
O

dsh-incidental-learn

oxmumu3/dsh-incidental-learn

Captures engineering and product trade-offs from daily Agent turns into a local skill ledger with collapsible postscript cards, automatic background staging, right-sidebar drills, and four-tier mastery checkpoints.

0昨日スキルMIT
M

my-dsh-skill-hub

myhylijp/my-dsh-skill-hub

Skills panel: one shared external skill pool plus per-agent-preset authorization of pool skills and built-in system skills.

0一昨日スキルMIT
J

dsh-ai-study-kit

jerryjiao/dsh-ai-study-kit

Registers five user-invocable study-coach skills for DeepSeek Harness: ask-coach (learning-state probe plus the F1-F13 flows: bootstrap, new theme, daily study, wrong-answer recap, podcast, lesson authoring, content edit, verify, deploy, coaching, exam sprint, knowledge-graph projection, upgrade), study-coach, study-doctor, study-recap and study-podcast. Ships a copyable quiz-site template (kit/ snapshot, v0.28.0) that the bootstrap flow copies to ~/study-kit; every skill is slash-command only and does not participate in model auto-invocation.

04 日前スキルMIT
F

residency-history-taking-internal-medicine

flying-ovaltine/residency-history-taking-internal-medicine

Residency OSCE history-taking trainer for internal medicine. It plays the standardized patient while you interview, then switches to examiner and scores the interview against the official 100-point rubric with itemized deductions; ships 32 internal-medicine case scripts and an append-only training log.

03 日前スキル
X

dsh-ai-diagrams

xuedipiaofei/dsh-ai-diagrams

Editorial diagrams in chat: the agent draws a self-contained HTML/SVG diagram (50 types, on the cathrynlavery/diagram-design skill), it renders inline with SVG/PNG export, redraws draw.io/Mermaid/Excalidraw sources and can match a site's brand. No Python, no Playwright.

03 日前ツールと機能Apache-2.0
W

dsh-opticforge

wbmgggg/dsh-opticforge

KB-first optical-engineering task assistant. opticforge_assist aligns a concrete problem with the 40-section / 324-entry knowledge base before any web search. 3.1.1 activates up to three topic playbooks (16 cards, 98 dimension declarations), retrieves evidence per required dimension, and returns a dimension-by-source coverage matrix, a gated plan with dimension IDs and cross-check steps, formula cards, a five-section report outline and acceptance checks. Answers explain principle -> formula/criterion -> approach -> steps, and never expose KB layer or entry IDs; sources are named as documents, standards, manuals or URLs. web_gate allows external search only for declared KB gaps, standard versions, vendor parameters or price timeliness. opticforge_verify checks KB alignment, present-only citations, dimension evidence, cross-relations, source tiering, KB conflicts, 30-day freshness and five-section presentation, and reports an adoption gate. Includes 308 concept cards, 6 generic dimensions, 19 formula cards and the opticforge-task DSH Skill. 308 entries are citable; 16 declared gaps remain, limited to A03, C01 and E01 verbatim sources. Five tools, zero runtime dependencies, no calculator, no network access and no action execution by the plugin. npm publication is on hold; install from GitHub with node scripts/install-local.mjs.

04 日前ツールと機能MIT
S

dsh-prompt-library

super-qaq/dsh-prompt-library

Prompt library for the agent and the composer: save prompts, search and filter by tags, insert into the draft or copy, import prompts from a link with the default model, and track skill or plugin dependencies.

04 日前ツールと機能MIT
K

brewpage-publish-plugins (deepseek)

kochetkov-ma/brewpage-publish-plugins

Publish HTML pages, static sites, Markdown, documents and AI artifacts to BrewPage and get a shareable HTTPS link; bundles the BrewPage skills and the brewpage-mcp server.

0昨日ツールと機能MIT
H

dsh-plugin-trim

haidai233/dsh-plugin-trim

Trims the tool surface per session. Each session owns a profile — a tool whitelist — applied through `agent.ctx.tools.restrict({ allow })` on that agent scope only, and switching one session never touches another; `full` is the built-in no-restriction profile. The provider only picks the default: a session created or switched onto a local provider (explicit `localProvider`, `routes`, a loopback/private baseURL, or a local-ish id) gets the `local` profile, a cloud one gets `full`, and the re-plan runs on model-selection events plus one delayed pass because the projection can land after the event. Profiles are editable from the panel and persisted under `~/.dsh/plugin-trim-state.json`; an explicit per-session choice overrides the provider default until cleared. A separate, opt-in layer physically disables whole plugin entries through `pluginManager.setPluginEnabled` — that one is profile-scoped by API and the panel labels it as such rather than pretending it can be per-session. A `tool_trim` tool exposes list/status/profile/set/apply/restore to the model. The panel is served by a loopback-only HTTP server the plugin starts on its own fixed port — `http://127.0.0.1:12256/` (auto-bumps on collision, configurable) — because the DSH port changes on every restart and a locally linked package gets no market card in the sidebar; it lists live sessions with their profile and tool count, an editor per profile, a provider picker limited to providers declared in the profile or currently in use, and the full plugin list with search and paging. Two implementation details worth knowing: `tools.restrict()` is an intersection and cannot widen, so the old restriction is released before the visible set is read — otherwise switching to a bigger profile would shrink instead of grow; and every disposer is registered on `ctx.effect`, without which a hot reload leaves an unremovable restriction behind. Measured on a 12GB laptop GPU with a 27B model and a fully resident 256K cache, same conversation: 105 tools / 56,306 prompt tokens / 22.5 tok/s decode, 62 / 34,207 / 43.0 after disabling three tool-heavy plugins, 14 / 12,890 / 66.8 after a session moved to the local profile, with prefill rising from 487 to 1,310 tok/s. Restricting also drops the skill catalog injection, roughly 4.3K more tokens. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

05 日前ツールと機能MIT
B

shiliu-ai (dsh-plugin-shiliu-ai)

bigbrain-work/shiliu-ai

Connects Shiliu AI's remote MCP tools for public short-video lookup, transcript extraction, and account balance checks.

04 日前ツールと機能MIT
Y

dsh-butler

yutouaa/dsh-butler

One dedicated butler session per workspace. A workspace-menu item enables it, creating (or reusing) a session titled "管家" in that workspace. From that session, four tools list what the other sessions in the workspace are doing, digest their memory and skills in one call, name sessions by role, and dispatch a task to a session by role name, unique title or id. Dispatch uses the host in-process delivery with the scheduled-task service as the fallback. Other sessions in the workspace are refused. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

05 日前セッションとメッセージMIT
C

dsh-workspace-isolate

cyberyui/dsh-workspace-isolate

Per-workspace plugin and skill gating for DSH. Arm one workspace to freeze its exact plugin and skill set, and every other workspace automatically loses what that workspace does not use.

0一昨日セッションとメッセージMIT
T

dsh-plugin-turn-usage

threadripper123/dsh-plugin-turn-usage

A per-turn footer listing the tools, MCP servers, knowledge bases, and skills a turn used.

05 日前使用量と課金MIT
Z

dsh-skill-catalog-refresh

zheqiu2023/dsh-skill-catalog-refresh

Keeps the slash skill menu of open sessions in sync with the skills installed on disk, so a new skill appears without starting a new conversation.

03 日前UI拡張MIT
R

dsh-skill-pool

rj-yejianping/dsh-skill-pool

Skill pool for DSH: import skills from files, ZIP, GitHub or GitLab, auto-group them by repository, and set each skill's Agent-mode and workspace scope from a settings panel, with a global switch per group. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

0昨日MCPとコネクタMIT