Plugins

AlphaRSI — three-role self-improvement loop that evolves the training recipe of alpha sequence models. Operator runs walk-forward, Evaluator grades with OOS RankIC, Refiner proposes hyperparameters via TPE Bayesian search; only strictly-better recipes are kept. Offline one-command run, data bundle shipped with sha1 reconciliation, GPU auto-detect. Ships one skill.

9router-backed web search and fetch for DeepSeek Harness. Enabling the bundle automatically routes native web_search/web_fetch tools to 9router; disabling it restores the remaining provider configuration.

Approval-free writes into whitelisted directories — wraps the filesystem fence for write/edit tools and auto-answers bash sandbox escalations that touch whitelisted paths, with a settings GUI.

A continuation of simon300000/dsh-auto: the Auto Approve permission preset for the DSH Web UI reviews each approval with one single-shot model call instead of a reviewer subagent, auto-approves only the actions that pass and hands the rest to human approval, and remembers confirmed decisions as project- and global-scope allow/deny lists, with an approval timeline in the right sidebar.

Self-diagnosing, self-repairing watchdog for DSH plugins: 15s health patrol, version-switch repair with observe window and auto rollback, unknown symptoms escalated to human.

Runs git init in each newly registered DSH workspace, with an empty initial commit by default, so git-aware plugins have a repository to attach to; directories already inside a work tree are skipped.

Automatically orchestrates complex DeepSeek Harness requests. It detects when delegation is useful, builds a dependency-aware plan, assigns bounded researcher, architect, backend, frontend, tester, and documentation workers, collects structured evidence, and sends the results to a final reviewer. The bundle atomically enables the workflow engine and model-facing subagent tools; disabling the plugin disables its complete tool group as well.

Skill routing for DeepSeek Harness: embeds skills and each user task with a local model, keeps the clearly-relevant skills with a gap-based selection rule, and auto-injects their full bodies into the prompt.

Controlled browser automation for DeepSeek Harness: the agent_browser tool and BrowserAutomationService drive a real Chromium or Chrome page (or an explicit CDP endpoint) through the agent-browser CLI, with allowedDomains containment and per-call output limits.

Computer Use for macOS desktop applications: reads any app's accessibility tree as text with element indices, then clicks, types, pastes, scrolls, drags, selects text and sets values through it, plus screenshots read back as images. Driven by a persistent JavaScript REPL — the agent gets two tools (`js`, `js_reset`) and calls an `sky` API inside them, so state survives between calls and the tool schema stays fixed as capabilities grow. Accessibility trees come back as diffs after the first read; actions address elements by index and indices from a stale read are refused rather than misapplied; typing waits for keyboard focus and reads the field back; paste restores the clipboard. Requires macOS 14.4+, Accessibility permission (Screen Recording only for screenshots) and Node 20+; ships a prebuilt native module, so nothing compiles at install time.

Adds DSH restart and stop controls with token-aware reconnect and policy-based recovery for interrupted web sessions.

Customize the DeepSeek Harness desktop shortcut icon: pick a preset or upload an image, auto-remove the white backdrop, build a multi-size ICO, and write the shortcut in one click.

Large-image recognition for vision-exp models: lossless 800×800 tile recognition (smart/pipeline/full), local OCR with preprocessing & handwriting routing, optional multi-vendor GPU (DirectML/CUDA/OpenVINO) with auto CPU fallback.

A browser that lives in the DSH host: every session gets its own tab, the AI drives it, and you watch or take over that same tab inside the DSH Web UI — logins, 2FA, QR codes and CAPTCHAs included.

Turn approved tracker tickets into review-ready pull requests with DeepSeek Harness.

DeepSeek Harness plugin for verified competitive-programming problem-setting workflows.

Local plugin installer in the DSH web Settings: a file picker for .tgz plugin packages (multi-select) or a full machine path, installing them into the auto-detected profile via the official `dsh plugin add` with live CLI output — no terminal needed.

Adds an "approve for me" access mode whose approval requests are answered by an independent reviewer model instead of a person: the reviewer can read the workspace read-only, a reviewer that cannot run hands the request back to the human, and every decision is recorded with its rationale in an Approvals tab.

Automatic tier-based model routing for DeepSeek Harness: a virtual `smart` model classifies each request by difficulty (hard / normal / easy) and by vision need, then delegates it to the models you already configured. 三级难度 + 视觉自动路由，虚拟 smart 模型零配置接入。

Community DeepSeek Harness plugin: deterministic engineering orchestration with Commander, Executor and Smart Watchdog (CxService + cx_controller tool).

One-click restart for DeepSeek Harness: a web button (plus a dsh_restart agent tool) hands the relaunch to a detached helper that waits for the port to free, relaunches the exact same command, streams the new host's output, auto-reconnects the page — and

Drives the GME Test Agent from inside Harness: three tools list interface catalogs, start and repair autonomous test generation in a local Python backend, poll the task until review, and keep PR, skip and cleanup actions behind explicit user consent.

Deterministic engineering orchestration for DeepSeek Harness with Commander, Executor, Smart Watchdog, bounded recovery and durable execution state.

DSH bundle that vendors the full mattpocock/skills tree, preserves upstream invocation policies, and applies an exact-match DSH semantic overlay checked during automatic upstream synchronization.