Plugins

Cut token cost in 4 layers without cutting model intelligence: handoff, rtk, headroom, caveman token-saving skills — each also available as a standalone installable plugin.

Watches agent execution traces and fires an LLM review at every successful turn end when signals trip, crystallizing reusable workflows into registered skills that improve progressively with later runs.

Skill marketplace with aggregated search across SkillHub and ClawHub, in-app README preview, one-click install and uninstall, and a chat-input skill picker.

AI-driven presentation workflow packaged as a dsh skill: generates editable PPTX decks and SVG snapshots from PDF, DOCX, URLs or Markdown, fills native PPTX templates, and enhances finished presentations.

Free lip-sync video generation plugin for DSH with 3000+ voices and 500+ languages.

Configurable image recognition for text-only DSH models: image messages are first transcribed by an OpenAI-compatible vision model (Base URL, model ID and API key set in a Settings section) and then passed to the main model as text, while image-input support is advertised. The API key auth scheme is selectable — OpenAI, Anthropic, Gemini or Azure style request headers — and a missing key is reported before any request is sent.

Vision bridge for text-only DeepSeek: send images (alone or mixed with text) and a fast tiny vision model describes them behind the scenes — the chat keeps the picture, DeepSeek sees only text. Pure plugin: uninstall restores everything.

Routes the DSH web_search tool through Ollama's web search API, reusing OLLAMA_API_KEY. No DeepSeek official key needed.

Provisions the kimi-webbridge bridge daemon (auto-install with SHA-256 verification, auto-start) and registers a 25-action skill that drives the user's real browser through the local bridge.

Drag-and-drop file upload into the conversation composer, token usage pill with quota tracking, and session archive management — a three-in-one daily-driver addon.

Local knowledge base manager for DSH agents: multi-format import, CJK-aware chunking, sqlite-vec vector + BM25 hybrid search with bge-reranker-base rerank, snapshots, kbpack export/import and cross-KB search — 22 agent tools plus a Web panel.

Answers hard questions by staging a formal debate: two adversarial subagents argue opposite sides with research, then the main agent rules on the transcript through the debate_open, debate_round, and debate_verdict tools.

Automated daily content pipeline for Insta360 GO 3S: BLE/WiFi remote capture of aquarium footage, wireless import, ffmpeg quality evaluation with decision log, Auto editing (segment selection, TTS narration, music, subtitles), and Bilibili upload via biliup (dry-run by default).

Insurance product comparison & proposal expert — clause analysis, cost-effectiveness, coverage planning, generates verifiable client-facing PDF proposals.

Insurance company operations analyst — runs real solvency, profitability, embedded value (EV), investment risk and regulatory compliance calculations, not just text explanations.

Insurance company financial & operating analyst — solvency, financials, investment, distribution channels and peer comparison with real calculations.

Insurance actuary — runs real actuarial calculations (life & P&C reserve valuation under C-ROSS II BEL+RM, profit testing NBV/VNB/IRR, embedded value EV, pricing & loss-triangle reserving), not just explanations.

Renders HTML, React (JSX/TSX), Vue, SVG, Mermaid and Markdown written by the agent in an isolated iframe sandbox with SSE hot-reload, and adds a DOM click inspector, side-by-side visual diff, a responsive device matrix and one-click Vite ZIP export.

AST-based context compression, test log filtering, and token budget guard for DeepSeek Harness: strips redundant syntax, prunes noisy log lines, and enforces a token ceiling so the context window never overflows.

Nine consolidated tools that give agents full access to the stool ops CLI: server management, database query/redis, log search/tail, CI/CD deploy and history, MFA codes, git operations, notes, todos, and misc utilities (accounting, weekly reports, audit, project listing, nginx presets).

Windows desktop automation for DeepSeek Harness: accessibility-first observe/act loop with 30 standard tools (element/coordinate targets, auto/a11y/event strategy routing), superseded-observations and no-replay safety semantics, persistent kill switch, RuntimeId/rect-drift stale protection, chat cards and a floating panel (live ops, frame wall, env auto-detect settings), tiled vision describe for low-res models, JSONL audit trail and a pid allowlist. Requires Windows 10+ and Python 3.9+ with uiautomation and pillow (installable from the settings page).

Parse Chinese e-invoice PDFs (XML attachment first, text-layer regex fallback) into structured JSON with amount cross-check, and generate expense reports (Markdown / xlsx).

Supervisor-style workflow orchestration over top-level sessions: confirmation-gated batch dispatch, team workstreams, steering running tasks, idle-wait collection and live model-route discovery across 11 task_* tools plus a /tasks slash command.

Settings panel for global and per-workspace AGENTS.md, with identity and persona injection, runtime-context toggle, and result notifications.