Plugins

Cleans AI traces from Russian text: finds chatbot copy-paste artefacts (ChatGPT, Gemini, Grok, Perplexity, DeepSeek), strips hidden text marks (zero-width characters, invisible layout; shadow scan catches markers split by invisibles), and rewrites the text into natural prose on request; 40 regex markers, 38 with full evidence-registry entries; 156 gates, 530 tests; offline, text-only bundle (binary metadata removal lives in scripts/).

baro as a DeepSeek Harness subagent provider: delegate a multi-story goal, get parallel execution, independent review and a verified outcome back — with a live run panel in the sidebar

Paste a link; the agent reads it. Xiaohongshu, Douyin, Bilibili, WeChat, articles, PDFs and audio become citable Markdown for a wiki or knowledge base. On 60 turns with vs without: finishes reading 22% -> 92% (+70 points), times out 68% -> 0%, answer quotes a real source fact 23% -> 82% (the A/B is exploratory: different time caps, no human correctness review). On 123 live links 80% came back usable (93% of the pages that answered); an unreachable link reports in 26 s. Codex, Claude Code, DSH.

BrewReel (精酿) for DeepSeek Harness: write a storyboard JSON, get a vertical promo video.

sift-light — Evidence-first search for AI agents.

A plugin collection for DeepSeek Harness (DSH). Install this one bundle to get every plugin listed below; each plugin can also be installed on its own.

Local-first MCP App for scientific figures. Import, review, and publish a global library on disk; reuse exact templates in Pi, DeepSeek Harness (dsh), Claude, Codex, Cursor, and Wisp.

Memory center for sedimem, a local cross-client memory layer: one sidebar entry opens the read-only observer as a full page — today's changes, a hand-rotatable 3D memory graph, and 30-day hygiene trends, with a scope picker. The host reuses an already-running observer when observerUrl points at one (pure proxy, no extra process) and spawns an embedded copy as fallback, both reading the same ~/.memo; read-only, loopback-only, with an extra cross-site fence on the routes. The write path (MCP memory_* tools) shared by DSH/Codex/Claude Code is untouched. Zero dependencies.

Native account-pool and provider plugin for DeepSeek Harness on macOS and Windows: official browser OAuth and provider-native transports for Codex, Antigravity, Grok, Claude, Cursor, WorkBuddy, Command Code, Hermes and OpenRouter Free, with per-account model catalogs, plan and quota windows, quota warnings, and manual, sticky-session, round-robin, failover or most-allowance-left account selection.

Registers a local OpenAI-compatible bridge as a native dsh model provider: reuses the models already signed in on the desktop app on this machine, manages the bridge and its local dashboard process, and adds five tools, a /workbuddy command and a nine-tab settings panel. Requires the desktop app to be installed and signed in on the same machine; the bridge binds 127.0.0.1 only.

Search 65,600+ API docs from 20 Chinese open platforms through five read-only tools and a runtime skill.

Compare multiple skills on the same task and pick the winner.

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.

You.com agent skill provider and MCP setup for DeepSeek Harness (dsh), registered via ctx.skills

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.

AI agent skills for Sealos — deploy any project, provision databases, object storage & more with one command. Works with Claude Code, Gemini CLI, Codex.

Local Obsidian vault as the agent knowledge store, with read-only DSH tools that route status, preference, correction, memory, project, search, and suggest to the matching page.

QA pipeline as 10 agent skills: requirement analysis, test strategy, case writing and review, E2E (Playwright) and API automation, exploratory, regression scope and bug analysis, backed by a shared knowledge base with format rules, risk model and schema validators.

A Claude-persona desktop pet pinned to the bottom-right corner of the DSH web GUI — shows balance, today's usage, peak/off-peak pricing and per-turn cost, with editable bubbles (text, balance, usage, pricing, images, random lines and weighted choices), per-line styles and fonts, a floating quick editor, sound effects, and custom character/audio. Ships animated roles that breathe and blink, plus a balance-alert variant that switches to a crying face when the balance falls below the alert line; 256/384 animation tiers and an optional 512 HD pack installed from the resource manager. 63 Claude-flavored lines. A derivative of MeteorNOX/DeepSeek-Balance-Whale-Widget (MIT).

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

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

Claude Science-style research workbench: ReAct research-loop engine (research_* tools), versioned artifacts with provenance (artifact_* tools), and 10 science skills for genomics/pathogens/bioinformatics.

Run Claude Code, Kimi CLI, Codex CLI, PI CLI, OMP CLI, OpenCode and CodeBuddy CLI (off by default, unverified) inside DeepSeek Harness sessions over ACP, with a CLI and model menu, a git changes panel and worktrees in the Web and Desktop UI. Needs each CLI installed and signed in (OMP, OpenCode and CodeBuddy must be installed first). The CLI runs outside the DSH sandbox and decides what to ask: only Claude Code in manual mode and OpenCode with ask permissions raise DSH approval cards, Codex, PI and OMP run commands without asking.

Skill marketplace and manager: manage skills from all local coding agents (10+ executors, incl. Claude Code and Codex) in one page and import them into the DSH skill library; built-in market of 6600+ skills, per-skill token-overhead stats, and model visibility control.