Passer au contenu principal

Plugins

Parcourez, filtrez et installez des plugins DeepSeek-Harness.

128 plugins trouvés

W

dsh-prompt-optimizer

windrover/dsh-prompt-optimizer

Optimiseur de prompts dans la rangée d’outils de saisie du composer : choisir catégorie et modèle, puis ✨ réécrit le brouillon sur place avec undo en un clic. Catégories Basic, Context et Image ; annulation d’une exécution, affichage durée et tokens. 15 modèles couvrent reformulation de consignes, plan par étapes, cadrage de recherche de sécurité, fiches de rôle de system prompt, prompts text-to-image/image-to-image. Les modèles Context lisent les derniers tours pour résoudre les coréférences. Appels via le service modèle hôte ; Settings expose modèle et budgets. Un guard vérifie la conservation des contraintes utilisateur et avertit au lieu de relancer automatiquement. Adapté à dsh 0.1.7 et 0.2.

1il y a 28 joursAméliorations UI
M

dsh-agent-instructions-editor

mari23333/dsh-agent-instructions-editor

Modifie depuis les paramètres DeepSeek Harness les instructions globales AGENTS.md et celles du projet AGENTS.md/CLAUDE.md. Découvre la chaîne de projets, affiche le budget en octets et gère les conflits d’enregistrement.

1il y a 10 joursAméliorations UIMIT
C

dsh-personalization

crazy-l118/dsh-personalization

Plugin de personnalisation pour DeepSeek Harness (dsh) : définit qui vous êtes, le rôle de l’assistant et son comportement. Ajoute une page Personalization aux Settings de dsh (instructions personnalisées, surnoms, persona) et injecte le contenu dans chaque agent…

1il y a 2 moisAméliorations UIMIT
H

dsh-instruction-memory

hero476/dsh-instruction-memory

Injecte les instructions permanentes modifiées dans les réglages DSH dans le prompt système de chaque tour ultérieur.

1avant-hierMémoireMIT
C

dsh-sightline

charlie-wang-03/dsh-sightline

Compare les surfaces d’instructions de DeepSeek Harness, Codex et Claude Code pour un même workspace.

1il y a 3 moisDéveloppement et outils de pluginsMIT
L

agent-loop-workflow

lesliewylie/agent-loop-workflow

Protocole de collaboration multi-agents indépendant du projet pour DeepSeek Harness : gardes de boucle qui arrêtent les boucles d'agents emballées, format de passation à six champs, routage des revues par niveau de risque et séquence fixe verify→commit→push→review→close. Une seule skill au lieu des mêmes règles copiées dans les instructions de chaque agent.

1il y a 3 moisFlux et automatisationMIT
C

dsh-inspector

cocosgt/dsh-inspector

Inspectez et gérez la chaîne d'instructions en direct et les skills de projet de la session dsh en cours, avec création et édition sur place — ce que vous voyez est ce que reçoit le modèle.

1il y a 3 moisDéveloppement et outils de plugins
3

dsh-session-tidy

349840432m-dev/dsh-session-tidy

One-click tidy for the DSH session list: archive blank sessions and sessions inactive for N days, keep the newest N per workspace, clean truncated or instruction-prefixed titles, and disambiguate duplicate titles — with a preview sheet, selectable presets, and batch undo. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

0avant-hierSessions et messagesMIT
I

dsh-github-push

imcaibaicai/dsh-github-push

Pushes a local folder to GitHub on one instruction: proxy autodetection, the token read from the OS credential store and scrubbed from every log line, a pre-push secret gate, and SHA read-back verification of the remote branch.

0avant-hierGit et revue de codeMIT
H

dsh-wechat-assistant

huangzihengcmd/dsh-wechat-assistant

Drive DeepSeek Harness from WeChat: scan a QR code to sign in, send instructions in WeChat, and the agent reply lands back in the same chat window. Several agents can share one WeChat account, each with its own model, preset and context, switched from the chat with /use. Only the configured owner WeChat account can drive the agent; other senders are rejected by default and require explicit approval.

0il y a 4 joursIntégrations et accès distantMIT
S

dsh-quickjot

spankingsnail/dsh-quickjot

随手记 lets AI turn a sentence into a note, a to-do or a dated event. No need to choose a type, fill out a form or pick a date first: give your instructions in a conversation or open 随口记, and AI organizes the item from what you say, asking for clarification when information is unclear. When plans change, keep talking: “move it to tomorrow at ten”, “mark it complete” or “add the work tag”, without finding the item again and editing each field. Items stay on your machine and are shared across conversations, with in-app reminders and WeChat notifications through DSH-IM.

0il y a 3 joursIntégrations et accès distantMIT
P

dsh-tts-voice

pandaman0759/dsh-tts-voice

End-of-turn voice summary: the model calls voice_say once before finishing a reply so the conclusion is spoken through Breeze TTS, with Chinese bracket audio tags (laughter, sighs, pauses) and optional performance instructions. Audio is synthesized host-side and played from browser memory without ever touching disk; the character limit is a writing target for the model, not a cut-off, so long lines still play in full. The API key stays in the credential store, and an optional daily Breeze check-in is included. Needs a Breeze API key and sends the spoken text to the Breeze service; its HTTP routes (including the settings route that stores the key) have no DSH access check.

0avant-hierVision, voix et multimodalMIT
S

dsh-agents-md-presets

salvare013/dsh-agents-md-presets

Named AGENTS.md presets for DSH: save instruction sets under $DSH_HOME/agents-md-presets, apply one to the current conversation workspace, edit bodies in your own editor, and keep one rolling backup of the file being overwritten.

0il y a 3 joursAméliorations UIMIT
Y

dsh-chinese-reasoning

yingshuozhang/dsh-chinese-reasoning

Makes a DeepSeek Harness agent reason in Simplified Chinese: each turn it appends one runtime-context instruction at the end of the conversation, and it can keep a stable declaration in the system prompt as well. Settings pick Simplified Chinese or off, and whether that declaration is included.

0il y a 5 joursMémoireMIT
L

dsh-gpt-adapter

lxjmaster/dsh-gpt-adapter

DeepSeek Harness plugin for GPT models and Codex instructions, skills, plugin resources, and MCP configuration.

0il y a 4 joursMCP et connecteursMIT
A

dsh-sync

anime-fan-5903/dsh-sync

Synchronizes native DSH instructions, user Skills, and reviewed portable settings across devices through Microsoft OneDrive, with optional cloud encryption and explicit conflict resolution; conversations and credentials are excluded.

0il y a 5 joursDéveloppement et outils de pluginsGPL-3.0
F

dsh-plugins (dsh-360)

feahter/dsh-plugins

Health check for a DSH profile: scores skills and agent instruction files, subagent definitions and presets on one shared 18-bucket S–E grade scale, with a sidebar panel, four dsh360_* tools, and a backup with undo for every write.

0il y a 19 heuresCompétencesMIT
D

dsh-plugin-antigravity-agents

domush/dsh-plugin-antigravity-agents

Native Google Antigravity agents loader and subagent orchestration engine with model selection and Web UI settings integration. Loads agent definitions from ~/.agents/agents and the workspace's .agents/agents; the selected main agent's instructions go into the system prompt, and a matching agent's instructions are prepended to DSH's own subagent and spawn_teammate calls. Settings are written to .agents/agents/settings.json in the workspace.

0il y a 3 joursMémoireMIT
Y

dsh-broadcast

yyhy110421/dsh-broadcast

Sends one instruction to a chosen group of existing DSH sessions at once, with attachments, optional answer collection and up to eight temporary subagents.

0il y a 9 joursSessions et messagesMIT
A

dsh-prompt-boost-model

amyaxy/dsh-prompt-boost-model

Prompt enhancement for the DSH composer, with a model picker that lists the models the host actually offers: a Boost button beside the composer sends the current draft to a model on the Host, shows the rewrite in a before/after overlay, and replaces the draft only when you confirm. While boosting, the button glyph becomes a spinning arc; once a rewrite is applied the same button becomes an in-place Undo that restores the original draft and then returns to its idle state. Settings hold the enable switch, a provider/model choice rendered as a grouped dropdown built from the live provider list (including configurable providers that are not set up yet) rather than free-text fields, temperature, output limit, timeout and optional custom instructions. Empty or reasoning-only model answers are reported with their real cause instead of a generic failure, and the Host endpoint only answers loopback requests from the same origin.

0il y a 4 joursAméliorations UIMIT
L

guster

lumos-789/guster

Audits and evolves agent context at four scopes: a single repository, a group of related repos, a knowledge hub, or the whole machine. Discovers projects, instruction files, skills, tools, knowledge, state, evidence and credential references; reports drift, duplicate facts, broken pointers, budget overruns, unindexed knowledge, stale state and unregistered credentials; scores each scope on its own dimensions; and turns findings into reviewable migration plans that back up every file before moving it. The format contract is a versioned spec (CTX rules, markdownlint-style IDs) following open conventions — the AGENTS.md open format, llms.txt-shaped indexes, YAML front-matter note headers — now backed by published JSON Schema contracts (draft 2020-12) for the hub manifest and the plan JSON, plus an editor modeline that validates hub.yaml with zero configuration. The hub is declarative (schema 2, zones with light profiles, sections may live outside the hub root), a one-pass check command runs scan, doctor and score, and state writes are atomic and lock-protected; scoring stays honest about missing evidence — a waiver greens the gate, never the score. Ships a stdlib-only Python CLI plus two skills; credentials are referenced by path and never printed. Requires Python 3.9+ (stdlib only) and DSH 0.2.1-rc.2 or newer, below 0.3.0.

0avant-hierDéveloppement et outils de pluginsMIT
W

dsh-draft-studio

wufeng0105/dsh-draft-studio

You type half a thought — "make me a scraper for Douban" — and the AI has to guess the rest. Click one button beside the input box and that line becomes a full instruction it can actually follow: what to build, what to output, what the limits are, how you'll know it's done. It never picks for you: where you haven't decided something (which library, which format), it lists the options instead of choosing one. The result is still a draft — never sent, and one click or Ctrl+Z puts your original back. Four presets (general / code / writing / translation), each one editable text you can rewrite to taste, and you choose which buttons appear. Optional: read the last few turns of the conversation so "that thing I mentioned" resolves correctly; use the current session's model or pin a specific one. Pure JS, no build, no bundled dependencies.

0avant-hierUtilisation et facturationMIT
T

dsh-session-manager

tsechiyuan/dsh-session-manager

Session manager and session settings for the DSH sidebar: sessions grouped by workspace with archive filters, title search, batch archive and a read-only transcript preview; global and per-workspace name, occupation and instructions injected into the system prompt; optional recent-only and hide-workspace filters for the sidebar.

0il y a 4 joursSessions et messagesMIT
W

dsh-workspace-rules

winson-young/dsh-workspace-rules

A settings page that edits the current project's CLAUDE.local.md, the private per-project instruction file DSH's built-in loader reads at the start of a session; the file stays out of git.

0il y a 7 joursDéveloppement et outils de pluginsMIT