Plugins

iPolloWork HyperFrames Video Studio and 27 editable video templates as a native DeepSeek Harness conversation view.

🐋 Carnet baleine — le rapport annuel de votre agent : génère des rapports quotidiens/hebdomadaires/mensuels/annuels à partir du journal d'événements de session, sur n'importe quelle période, en lecture seule sans réécriture.

Skills Superpowers pour DeepSeek Harness : skills de TDD, débogage, planification et collaboration adaptés de obra/superpowers

DSH × Univer integration with a bundled collaboration Gateway and Viewer: inline previews, live floating Worktree windows, and session-end review actions in DeepSeek Harness.

Expert-mode agent preset for DeepSeek Harness (v0.3.0, bilingual EN/ZH): a chief coordinator plus 11 domain-expert subagents with automatic task delegation. Features: Five-Anchor constraint (review/convergence/anti-drift/collaboration-check/resource-awareness per turn), Near-distance Guidance (identity/task/output template per expert), expert persistence, cross-expert communication protocol, cross review, and experience pool. Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance.

Relais de messages multi-agents axé loopback : un courtier authentifié par HMAC plus un plugin dsh (relay_send/recv/peers/history), des clients CLI et Python sans dépendance, protocole de fil v1.0.

Deep-collaboration writing agent for DSH: per-user writing-style learning from edit pairs, clarify→outline→section-writing→red-team→reader-gallery flow, project-to-report synthesis (lab report / product intro / survey / README), 41 MCP tools, and web selection-improve UI with in-app file preview.

LAN P2P Collaboration Plugin.局域网内协同插件

A project-agnostic multi-agent collaboration protocol for the DeepSeek Harness: loop guards that stop runaway agent loops, a six-field handoff format, risk-tiered review routing, and a fixed verify→commit→push→review→close sequence. One skill instead of the same rules copy-pasted into every agent's instructions.

Deep-collaboration writing agent for DSH: per-user writing-style learning from edit pairs, clarify→outline→section-writing→red-team→reader-gallery flow, project-to-report synthesis (lab report / product intro / survey / README), 41 MCP tools, and web selection-improve UI with in-app file preview.

Minimal room-based real-time code collaboration plugin for DeepSeek Harness. Install it, enter a room number and password, then collaborate with Yjs.