CATEGORY
Verified manifests and exact versions in this category.
@pulse-computing/dsh-tick-loop
Give an agent another step without giving it another task.
dsh-expert-mode
DSH agent preset: chief coordinator + 17 domain-expert subagents with taskboard scheduling, quality gates, and real inter-expert communication bus (专家模式)
@leechen298/code2skill
Generate and review portable Function, MCP, and Agent Skill packages from existing code.
luxueliu-agent-discipline-skills
AI isn’t lacking intelligence, but discipline: pre-delivery self-checks, course correction when going off track, systematic debugging, and multi-agent handoffs. 4 single-file SKILLs, copied into ~/.dsh/skills/ upon installation.
dsh-workforce
Project-scoped organization and long-lived AI workforce layer for DeepSeek Harness
dsh-generative-ideas
Roadmap ideation for DeepSeek Harness: generate and compare distinct roadmap options via headless agent runs, pick the one that fits, export as goal.md, and dispatch it to an agent in the chosen workspace.
dsh-capability-index
Pre-flight plugin-library check for DSH agents: per-step trigger-table hints injected into the runtime-context snapshot, so suitable plugins get used predictably instead of opportunistically
dsh-agent-evolution
Preset-composed Agent experiments for DeepSeek Harness
dsh-reviewed-development-orchestrator
Reviewed five-stage software-development orchestration for DeepSeek Harness
dsh-strength-refine
Highest agent preset for DeepSeek Harness: decomposes any need into a hierarchical capability map whose leaves all carry definite, operational acceptance criteria, and argues why the set fully covers the need — installable as a dsh plugin.
dsh-media-forge
Media Forge: agent + skills workflow for media-generation APIs, with a sidebar panel for loading saved generation skills into a conversation
dsh-agent-factory
Preset-aware agent runs and baseline/candidate experiments for DeepSeek Harness
dsh-auto-model-switcher
Prioritizes Chinese models, automatically switches models by task type, and supports a visual configuration panel
@deepdeck-apps/video-sherlock-app
Video Sherlock — agent-driven video evidence dashboards for DeepDeck
dsh-subagents
Focused child-agent delegation (scout, researcher, worker, reviewer, oracle, delegate) and multi-agent workflows (council, parallel review, review loop) for DeepSeek Harness.
dsh-plugin-monitor
Event monitor for DeepSeek Harness — background processes and WebSocket streams whose output lines wake the agent as asynchronous events.
dsh-humanized-deepseek-maid
Gives the DeepSeek Harness agent a configurable humanized whale-girl maid persona (address, self-name, speaking mode), an immersive no-plugin-meta rule, and a lightweight layered memory with query-triggered recall.
@limuyang2/dsh-agent-team
Multi-agent team management plugin for DeepSeek Harness
dsh-plugin-dew
See what your other coding agents are doing from inside DSH: Claude Code, Codex, Cursor and DSH sessions, their state, and their scheduled tasks.
dsh-state-graph
StateGraph orchestration engine as a DeepSeek Harness plugin: declarative directed state graphs with conditional routing, loopback, iteration guards, and a trajectory event stream.
@blue/dsh-telegram-bot
DeepSeek Harness plugin: connect a Telegram bot to your dsh agent via long polling. One agent per chat, multi-turn context, whitelist access, and agent-preset mounting so the bot gets the same tools as a Web GUI session.
fusion-symphony
Multi-Model Fusion Orchestrator (MoA) over registered DeepSeek Harness LLM providers: conductor-led fan-out, evidence ledger, verify/synthesize loop, zero training.
dsh-seed-society
Yogacara eight-consciousness agent society for DeepSeek Harness: auditable double-loop runtime bridge, mneme memory consolidation tuning, MCP society tools, and six seed skills
zhenxin-ai-video-manager
真的爱你: Local intelligent video manager Agent Skill. Say “真的爱你” to take over the entire editing workflow, from footage analysis to final delivery.
dsh-paper-survey
Literature Review Agent — Interpretation first: interpret each paper using a fixed framework → user confirmation → generate a literature review PPT with an A/B two-page structure. 3 skills: paper-survey / paper-interpret / paper-deck.
dsh-subagent-cassette
Deterministic VCR-style recording and replay for concurrent DeepSeek Harness subagent calls.
dsh-agent-plugin-bridge
Generic Agent Plugins 1.0 → DeepSeek Harness bridge: discovers plugin.json packages, registers skills and MCP servers.
@longnb47/dsh-agent-gateway
MCP stdio gateway exposing AI CLI agents to DSH as MCP tools
dsh-math-olympiad
DSH skill bundle: competition math (IMO/Putnam/USAMO/AIME) solved with a pure-reasoning pass, an adversarial verifier in a fresh subagent context attacking concrete failure modes, and calibrated confidence output (high / medium / honest "no confident solution"); optional LaTeX→PDF rendering.
@mkaliezz/dsh-agent-doctor
DeepSeek Harness health and safety diagnostics for effective tool surfaces, approvals, and AgentFuse composition
