Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

234 plugins found

L

dsh-project-compass

lpeixin/dsh-project-compass

Static codebase analysis for onboarding: scans a project, builds a dependency graph, and writes evidence-cited architecture, module, key-flow and getting-started docs, plus project-level Q&A over a local retrieval index (no network or LLM by default; LLM narrative is optional and off unless enabled).

621 days agoDev & Plugin ToolsMIT
X

dsh-reverse-mode

xingxue-ux/dsh-reverse-mode

Reverse-engineering agent preset. Mounts REA (rea-agents) as MCP tools for native binaries, JavaScript/Electron apps, managed assemblies, archives and installers — the full 170-tool catalog by default — but only inside sessions that select the preset; other presets load nothing. Ships an install-time check that reports which native analysis engine (Hopper, Ghidra, IDA) is present and prints the env snippet to wire one in. A fork of dsh-rea (JeremyWangCY, MIT) retargeted as an agent preset; do not install it together with dsh-rea.

62 days agoTools & Capabilities
7

dsh-fact-check

7starsseeker/dsh-fact-check

Skill that types the request before it searches: it splits a question into premises, definitions and analysis units, decides which report skeleton fits (verdict, explainer, causal mechanism, comparison, survey map, metric card), confirms the direction and runs a feasibility check, then emits that skeleton instead of forcing every question into a true-false verdict — in Chinese or English. Evidence gathering never trusts model memory: it searches domestic and international ecosystems in parallel, routes each point to the primary-source ladder for its domain (policy, academic, medical, financial, disaster, food safety, science, education, sports, entertainment, judicial, and more), fetches primary pages, grades sources by type, re-searches with debunking keywords, and keeps every statement bound to a full URL and citation position. Three factual judgements can be routed to a TypeSafe Jev (System One) decision model when a key is configured, falling back to the skill's deterministic rules when it is not; a model verdict can only lower a confidence tier.

66 days agoSkillsMIT
L

dsh-trace-insight (standard)

liu-bot24/dsh-trace-insight

Read-only trajectory review in a resizable conversation sidebar, with rule analysis, optional model explanations, evidence navigation, and same-range run comparison.

628 days agoDev & Plugin ToolsMIT
T

deep-structural-analysis-skill

tetckx/deep-structural-analysis-skill

Multi-lens structural analysis skill: adversarial-first analysis across 16 lenses in 4 categories with 10 structural tools, confidence calibration, and fact-bound layered output.

63 months agoSkillsMIT
E

dsh-sentinel-scanner

eligahyu/dsh-sentinel-scanner

Static security scanner for DSH plugins: read-only audit (exec, credentials, exfiltration, obfuscation, install scripts, bundle manifest) with a 0-100 risk score.

6yesterdaySecurity & PermissionsMIT
C

dsh-plugin-codegraph

cc19990113/dsh-plugin-codegraph

Structural code intelligence for DeepSeek Harness — gives the agent codegraph and codegraph_index tools to find where a symbol is declared, what calls it, what a change reaches, and how one symbol reaches another, from a tree-sitter index it builds itself

63 months agoTools & CapabilitiesMIT
S

dsh-market-lens

suifei/dsh-market-lens

HuanJing Stock Board - a pure "slacking-off" stock watcher: read-only delayed quotes for A-shares, HK and US, a flat dot-matrix LED exchange hall, watchlists, candlestick charts, news, financials and price alerts. For market analysis and trading use professional software - professionals do professional things; this is just a simple way for retail investors to glance at their own stocks.

57 days agoDev & Plugin ToolsMIT
T

dsh-plc-decode

taoziliyouchong/dsh-plc-decode

Read PLC projects inside DSH — decode CoDeSys .project and Delta .dvp (both need Python 3.9+ on PATH) and Siemens S7-200 SMART .smart/.smartlib into readable reports and structured data, plus project diff, address audits, element-level read/write analysis and ladder-logic reconstruction.

53 days agoTools & CapabilitiesMIT
N

npm-safe-fordsh

nisconder/npm-safe-fordsh

DeepSeek Harness plugin that blocks risky npm installs with metadata and deep supply-chain scans

53 months agoSecurity & PermissionsApache-2.0
A

logicprobe

amethystluna/logicprobe

Claim-verification skill that checks design documents and plans against codebase facts, escalating behavioral claims to executable logic-primitive verification for state machines and data models, with before/after regression, domain constraints, and concurrency risk mining.

54 days agoSkillsMIT
M

dsh-tradingagents

megatronyy/dsh-tradingagents

A-share multi-agent analysis behind /trading-agent, ported from TradingAgents-AShare, running 14 roles (analysts, bull/bear debate, risk review, trader) through the harness LLM route.

53 months agoTools & Capabilities
C

dsh-shell-command

chplus0/dsh-shell-command

Claude Code-style shell integration: /! for single-command analysis and /terminal for interactive PTY sessions with on-demand history reference.

5last monthTools & CapabilitiesMIT
Z

dsh-subagent-agy

zem17/dsh-subagent-agy

Google Antigravity CLI (agy) as a DSH product subagent: delegate tasks to a Gemini coding agent with your Antigravity login (no API key), with conversation follow-ups, background streaming progress, image analysis by path, and a pop-up login window.

53 months agoWorkflow & AutomationMIT
W

visual-review

wang-bool/visual-review

Renders pasted/uploaded images inline in the DSH Web chat and gives text-only models vision: the model-invokable visual_review tool calls any OpenAI-compatible multimodal API first, falling back to a local Qwen3-VL worker.

53 months agoVision, Voice & MultimodalMIT
W

dsh-plugin-doctor

white-sand-grand/dsh-plugin-doctor

Community search, similarity analysis, and install/dedupe/build-it-yourself decisions for the dsh-plugin ecosystem.

53 months agoDev & Plugin ToolsMIT
Z

dsh-video-downloader

zimai233/dsh-video-downloader

Detect and download media from Bilibili/YouTube/Douyin/Xiaohongshu with quality and format analysis.

53 months agoTools & CapabilitiesMIT
O

dsh-tool-stat

omdsh-dev/dsh-tool-stat

Descriptive statistics, percentiles, frequency distributions, and correlation.

52 months agoTools & CapabilitiesMIT
H

DSH-Video2Agent (dsh-video2agent)

harm0ny-ai/dsh-video2agent

Your agent has browsed countless web pages — now let it watch video. Video2Agent lets an AI agent understand video and answer directly: ask Bilibili or local videos what was said, which one is better, whether it is worth watching. Cross-video search returns the video and timecode, exact-frame evidence at a timecode, and 1-10 video batch analysis; local-first, with optional cloud ASR/OCR and Bilibili login. Needs Python 3.11+, FFmpeg and the CLI (pip install video2agent); the plugin settings page checks and installs the environment.

4yesterdayVision, Voice & MultimodalApache-2.0
F

dsh-free-xianyu

fouxiuan/dsh-free-xianyu

Hosts the ai-goofish-monitor scraper for the Xianyu second-hand marketplace: managed backend lifecycle, thirteen goofish_* agent tools, a sidebar panel, and AI listing analysis through the dsh-our-free-model gateway by default.

44 days agoTools & CapabilitiesMIT
Z

dsh-go-sensei

zhuang-a/dsh-go-sensei

Go (weiqi) review coach: parses SGF records, backfills winrate and score analysis with a bundled KataGo engine, explains the costly moves in the chat, and writes the commentary back into an SGF copy; a web panel shows the board with problem moves, AI choices and variations.

4last monthTools & CapabilitiesMIT
A

dsh-graft-plugin

adithyanraj03/dsh-graft-plugin

Shows which graft index a dsh session is serving and whether it still matches the code, and gives the model graft_ask, graft_grep, graft_callers, graft_skeleton and graft_map as native tools.

47 days agoTools & CapabilitiesMIT
L

dsh-issue2pr

longsasasasasa/dsh-issue2pr

Verifiable issue-to-PR delivery chain: an 11-stage pipeline (analysis, search, code understanding, hypothesis, planning, implementation, patch ledger, tests, review, failure classification, PR build) with 4 human review gates, GitHub/GitLab/CodeArts credential connections, a 5-page workbench and a draggable AI assistant panel.

42 months agoWorkflow & AutomationMIT
R

dsh-douyin-oem-touliu-report

ruiyukirin/dsh-douyin-oem-touliu-report

Douyin local-promotion OEM ad daily/weekly report automation (Author: Kirin): collects 3 data sources (laike leads, plan-level delivery, video analysis) via a one-time Edge login, computes metrics, builds A4-style docx reports, supports free-choice scheduled run times and email notifications.

43 months agoSkillsMIT