Plugins

Vergleicht mehrere Skills an derselben Aufgabe und kürt den Sieger.

Skills and optional MCP rows for ten Russian marketplaces: price comparison across Wildberries, Detsky Mir and Yandex Market, plus per-source search, product cards and reviews. The 13 skills load on install; both MCP rows stay disabled until RU_MARKETPLACE_MCP_DIR points at a local clone, which needs Python 3.12+ and uv.

DeepSeek Harness (DSH) plugin: dispatch work to DSH agents from Claude Code / Codex — native subagent progress, in-host worker sessions with per-tier presets, and a multimodal bridge that lends the text-only harness vision and image generation.

DSH plugin: Claude-style Chinese risk control & conversation autonomy for DeepSeek Harness web

Hacker News tools for feeds, discussion threads, search, and user profiles.

DeepSeek Harness (dsh) bundle wiring SkillRoute's skill router into your agents.

给 HR / 猎头的 AI 招聘工作流：岗位标准梳理、Boss直聘 + 猎聘双通道寻源初筛、市场人才盘点、简历评估、约面试、候选人台账与日报。可装成 Claude Code 插件或 DeepSeek Harness (dsh) 插件——后者自带可直接上手操作的「招聘浏览器」面板；也能配合任意读 AGENTS.md 的 AI 编程助手使用。

OpenCues for DeepSeek Harness — LLM word alternatives and `_`-gated blank fill-ins in the dsh composer.

Word alternatives and underscore-gated fill-ins in the composer. End a line with _ and it is filled; misspellings are flagged as you type. Routes through the model dsh is already configured with, so it needs no API key.

Agent-Native document handling for DSH — addressable blocks let an agent read and edit one section instead of the whole file. Ships the geml MCP server and the authoring and code-graph skills.

Block-addressed document editing: an MCP server exposing geml_get / geml_set / geml_check and friends, so an agent reads or rewrites one addressed block of a Markdown or GEML document instead of the whole file. Ships the GEML authoring skill and a code-graph skill that builds and navigates a project call graph as GEML codemaps.

🌊 Persistent dock & fully-customizable balance/usage panel for DeepSeek Harness — activity heatmap, dual-channel comparison, local-only & privacy-first

Deep-read books and articles in five modes (quick, deep, knowledge map, Feynman, full book) with claim-evidence-data reports, Mermaid/XMind mindmaps, batch comparison, budget preflight, transparent background-job progress, and MD/HTML exports from URLs, files, or pasted text.

Role-based Codex / Claude Code / ACP subagent providers for the DeepSeek Harness — continuable children, durable session recovery, per-role product permissions, and delegation with a permission ceiling.

Google Antigravity (agy) OAuth auth + model access plugin for DeepSeek Harness: multi-account pool, 429 rotation, device fingerprinting, CLI and web login.

Forschungs-Werkbank im Stil von Claude Science: ReAct-Research-Loop-Engine (research_*-Tools), versionierte Artefakte mit Herkunftsnachweis (artifact_*-Tools) sowie 10 Science-Skills für Genomik/Pathogene/Bioinformatik.

Terminal-UI im Stil von Claude Code für DeepSeek-Harness-Agenten, als out-of-tree dsh-Plugin-Bundle.

Macht jedes Projekt mit einem Befehl KI-Agent-fähig. Adaptive Tech-Stack-Erkennung (7 Sprachen × 14 Frameworks × 61 Komponenten), generiert automatisch AGENTS.md, ein Doku-Grundgerüst, CI/CD und Test-Infrastruktur.

Self-evolving team memory as plain Markdown in git: a native Cordis plugin that registers 38 bare-name memory tools plus a prompt-signals section re-evaluated at every assembly, with RPE reinforcement, decay and sleep consolidation; shares one data repo with its Claude Code (MCP) and OpenClaw hosts; verified against DSH 0.1.0-rc.6.

Chinese long-form screenwriting skill: two input blocks (background + character bible) feeding a causal-value engine, anti-AI-flavor review, and a continuity ledger; works on Codex / Claude Code / dsh / zcode.

Claude-style drag-and-drop/paperclip file upload with content sniffing, document-to-Markdown via Microsoft MarkItDown (built-in JS fallback), text inlining, and a read_document tool for agents.

Trägt dauerhaften Task-Status über DeepSeek Harness, WorkBuddy, Claude Code und Codex hinweg, mit maschinenlesbaren Checkpoints und optimistischem Locking.

Äquivalent zu Claude Codes /rewind für DeepSeek Harness: git-basierte Arbeitsbereichs-Dateischnappschüsse vor jeder verändernden Tool-Ausführung, Sitzungs-Forks an Rundengrenzen und ein Einmalbefehl /rewind, der Dateien wiederherstellt und die Sitzung zu einem Checkpoint zurück-forkt

Deklarative Berechtigungsregeln im Claude-Code-Stil für DeepSeek Harness: geordnete Allow/Deny/Ask-Regeln mit Abgleich von Tool-Name, Argument (Glob/Regex) und Arbeitsbereichspfad in der tools/pre-execute-Kaskade, vollständiges Sitzungsprotokoll-Audit und HMR-Regel-Reload.