Плагины

Card-based task orchestration for DeepSeek Harness: splits work into cards, dispatches and monitors tasks, handles stalls, verifies results, and adopts work conversations.

Reason tree: breaks a conclusion into a bottom-up argument tree, marks each branch as holds, fails or open, and jumps to the source file in Hippocampus.

Collects the open questions of each AI turn into a right-side panel; you answer them, add notes, and send the decisions back to the conversation in one message.

Adds contextual guidance for explaining technical misconceptions in conversations.

Codex-inspired lifecycle command hooks for DSH, with explicit tool-input sharing, pre-tool deny policies, notifications, and local audit examples.

File-state cache skill for coding agents: one explore call replaces ls+grep+read, reads remember they already happened, and edits return a diff plus the exact changed line range instead of a full re-read. State is a JSON cache on disk, so it survives across tool calls and restarts. Requires Python 3.8+ (standard library only).

Adds SKILL.md bundles from nested subfolders of the standard DSH skill roots to the catalog, with settings for depth, watching, and extra roots.

Host plugin that adds the /dsh-book-deconstruct command and the dsh-book-deconstruct tool to any session for a full book walkthrough plus one deep insight.

Save conversations, manage notes with images, export files, and sync across devices through your own private GitHub repository.

Makes identifiers inside inline code in chat clickable; resolves a definition, then a wrapper, then the next occurrence, and opens the file at that line in the sidebar preview.

Fixes web_fetch failing with "non-public IP address" while Clash, Surge or v2rayN runs in TUN/fake-IP mode: finds your local HTTP proxy by itself, sends web_fetch through it while the proxy is on and directly when it is off, and adds an Auto/Proxy/Direct switch to the sidebar. Model calls are left alone by default.

Connects DeepSeek Harness to AIyting's image generation MCP endpoint and registers four tools: aiyting_image_catalog (models, routes and specs), aiyting_image_settings (read, quote and save parameters), aiyting_image_generate (return a quote first, and submit only with an explicit credit ceiling) and aiyting_image_task (task lookup, waiting, and a local per-account ledger for unfinished jobs). A sidebar page signs in with an AIyting access key, shows points, today's usage and daily quota, logs out, and keeps per-conversation defaults for model, route, aspect ratio, resolution and count.

Annotates bash results whose exit code 1 is an answer rather than an error (grep with no match, diff with differences, false test) so the agent does not re-investigate them.

TransProof translation proofreader for DeepSeek Harness: full web UI (AI translation needs your own model API key or a local Ollama endpoint) plus a local, non-networked run-local-check agent tool.

Connects DeepSeek Harness to Postel over MCP: search a library of X posts that went viral by topic, write posts and X threads in the user's saved voice, and save, schedule or publish them to X, LinkedIn, Bluesky and Mastodon; adds a postel-writing skill. Research works without an API key.

LibTV canvas and media tools for DeepSeek Harness, with three director skills bundled and one-time WeChat QR authorization.

Manage Zuad digital signage programs, media, playback schedules, and devices through DeepSeek Harness. Requires an existing Zuad signage backend and an account on it; you sign in from the plugin settings and the password stays local.

Connects the agent to JuzPost, a social media scheduler, over MCP: lists connected accounts, checks per-platform limits, uploads media, and drafts, schedules or publishes posts to YouTube, Instagram, Facebook, TikTok, X, LinkedIn, Pinterest, Bluesky, Threads, Tumblr and WordPress. Registers the JuzPost tools as mcp__juzpost__* plus a workflow skill that confirms with the user before anything is published. Needs a JuzPost API key in JUZPOST_API_KEY; JuzPost issues API keys on paid plans.

Daily check-in for Nanjing Forestry University's ACM AI Hub plus seat booking for its library — both site addresses are hardcoded — with a settings page and a progress badge; built for DeepSeek Harness Mobile (DSHM) on Android.

Connects the CallAI SEO MCP server: 10 SEO data tools plus a generic DataForSEO request tool for Google/Bing SERP (with AI Overview sources), keyword volume and difficulty, long-tail ideas, competitor keyword gaps, backlinks and page audits. Includes a callai-seo skill. Requires a CallAI API key; pay as you go.

Localizes the prompts DeepSeek Harness sends to the model — system prompt sections, runtime context, tool descriptions and parameter docs — into Simplified Chinese. Its Cordis API dictionary is derived from zjl1989-li/dsh-harness-zh-cn (MIT), which translates the same prompt layers at runtime; do not enable both at once.

Notes-backed context compression for DeepSeek Harness: replaces LLM-summarized compaction with a model-written persistent notebook plus recoverable raw history, so the rollover boundary itself costs zero model calls.

Hippocampus: renders workspace files, DSH memories and past sessions as a rotatable neuron graph in the sidebar, with Chinese-friendly labels and automatic re-indexing on every start.

Keep conclusions alive across context compaction: the model writes a task checkpoint and the plugin re-injects it into the system prompt's first node — the span compaction never touches, so it survives any number of compactions. Four-tier injection (0/95/175/≤12000 chars) scales with session relatedness; checkpoints live in the plugin's own folder, never in your workspace.