Plugins
Browse, filter, and install DeepSeek-Harness plugins.
839 plugins found
coding-coach
xiehuan123/coding-coach
面向非开发人员的 35 个技能 bundle(DSH profile bundle,非 Agent 预设):编排 + 工程 + 产品 + 界面/上线。dsh plugin add coding-coach 即可把技能装进任意 profile;完整「编程教练」Agent 见仓库 dsh/coding-coach 目录。
dsh-project-organizer
caoqinnan-web/dsh-project-organizer
Rename project conversations into clear, content-based Category|Topic titles.
useful-dsh-plugins
lishize20040802-rgb/useful-dsh-plugins
DeepSeek Harness dual-face plugin: a visual plugin manager tab in Web Settings — enable/disable any plugin row, check installed plugins (including official @deepseek-ai/* rows) against the npm registry, update them, repair pristine files, and update the h
dsh-governance
tappass/dsh-governance
The authority layer for agentic AI, as a DeepSeek Harness plugin. Governs every tool call against your business rules via the TapPass /v1/govern policy decision point.
dsh-inspector
cocosgt/dsh-inspector
Inspect and manage the live instruction chain and project skills for the current dsh session, with in-place creation and editing — what you see is what the model gets
dsh-yali-image-generator
pptt121212/dsh-yali-image-generator
DeepSeek-Harness 图像生成插件。申请 Yali AI API Key:https://api.yaliai.com/
deepsee
chang416/deepsee
DeepSee: DeepSeek Harness vision, multi-model routing, and Gemini visual self-checks before delivery
dsh-failure-capsule
yiharvest/dsh-failure-capsule
Local-first failure evidence capsules for DeepSeek Harness sessions
design-playbook
bandersnatch0x/design-playbook
Design I/O for coding agents: controllable UI generation via declarations (spec/domain/craft/design/components/template) and contracts (skill/evaluator). Use for product UI—console, dashboard, agent-ops, CJK-first apps.
dsh-repro
evilirving/dsh-repro
/repro exports a minimal, secret-scrubbed, replayable problem bundle: the session log, failed commands, and Git diff.
dsh-prompt-profile
bramblexu/dsh-prompt-profile
Reusable Markdown prompt profiles for DeepSeek Harness with per-turn model selection, argument substitution, and state restoration.
dsh-pain-point-check
iccuse/dsh-pain-point-check
Enforced pain-point gate: after two non-converged experiments it injects the three questions, denies non-investigative tool calls until answered, and blocks same-direction retries.
muretai-dsh-skill
muretai/muretai-dsh-skill
Puts the agent on the Muretai network: its own identity, invite-based introductions, signed end-to-end encrypted messaging with agents owned by other people, and an inbound-mail wake that lets it reply on its own.
dsh-notify-bark
pc439527/dsh-notify-bark
Bark push notifications to iPhone: turn completion, waiting-for-input, and approval events sent from the DSH Host.
dsh-figma-to-lottie
zimai233/dsh-figma-to-lottie
Compile SVG paths and keyframe specs into self-contained Lottie JSON animation files.
dsh-docker
jesse-njx/dsh-docker
Typed, guarded container control: ps/logs/inspect/exec/start/stop and compose up/down with JSON output, project-aware targeting, and approval-gated destructive ops.
dsh-apple-mode
jihongboo/dsh-apple-mode
Xcode AI integration for DSH: 26 Xcode MCP tools (mcpbridge) + Apple platform skills + Xcode Intelligence-style persona (agent preset or global bundle).
dsh-memoria
jiayan-xu/dsh-memoria
Vector + graph memory backend: observe/remember/search/recall tools against a local memoria server, fusing HNSW semantic recall, FTS5 keyword search, and knowledge-graph signals via RRF ranking, with automatic turn-end persistence and per-agent namespace isolation.
dsh-balance
geekricardo/dsh-balance
Composer-dock balance/usage readout for DeepSeek, Kimi Coding, OpenCode Go, Zhipu, MiniMax, OpenRouter and OpenAI Codex — provider-based, 2s polling, 5min cache.
dsh-when
zhijiangtang/dsh-when
Parses natural-language relative time (e.g. "in 2 hours") into ISO timestamps, fail-fast.
dsh-workloads
yewenyell-lang/dsh-workloads
Workspace-owned durable process supervision, readiness checks, and a Runtime Center for DeepSeek Harness.
dsh-perm-guard
a903067276-rgb/dsh-perm-guard
Auto-approval permission guard: a middle tier between workspace-write and danger-full-access — auto-allows safe operations inside trust directories, always asks a human for destructive ones, with 11 per-category switches and an audit trail.
dsh-safeguard
zhijiangtang/dsh-safeguard
Pre-execution guardrail: vetoes dangerous shell commands and blocks secret/credential leaks before they run.
dsh-workflow-isolate
linxiushen/dsh-workflow-isolate
Alternative WorkflowEngine provider for DSH 0.1.0-rc.7 that runs model-written orchestration in fresh QuickJS/WASM runtimes with a JSON-only host bridge and bounded memory, execution time, and child-agent fan-out.