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.

End-of-chat visual storyboard: a storyboard tool renders a self-contained HTML card (inline SVG diagram, numbered flow, facts grid, timeline) from a JSON spec, writes it under ~/.dsh/storyboard/<session>/ and opens it in the sidebar; a system-prompt section and a /storyboard command trigger generation. Server-only, zero runtime dependencies.

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.

Keeps a redundant sandbox-escalation argument from failing a tool call. Escalating tools (pwsh, bash, write, edit) advertise the full sandbox_permissions enum, but DSH only accepts a level strictly wider than the one already in effect — a check its own source calls 'deliberately not a schema constraint'. A model that reflexively passes the argument therefore picks the level it is already at and the call dies before running with 'sandbox escalation to "workspace-write" is not strictly wider than this call's current "workspace-write" mode', costing some models a whole turn of retries. This plugin registers one tools/execute waterfall listener and, only on that documented rejection and only when the arguments really carried an escalation field, re-issues the identical call once without it. Safe by DSH's own documentation: the rejection precedes any execution ('nothing has run'), and the corrected call cannot match again, so the retry is loop-free. Reproduced and verified end to end — before: isError true, the command never ran; after: the command's real output, isError false, one tool/call and one tool/result. Zero dependencies.

33 github_* tools covering REST reads, issue writes, Git data writes, private repo creation, and clone; in-process permission gate and cost-discipline companion skill; no gh CLI required.

Training attestation — reproducible, attributable, auditable off-site standardized training for asset pricing. Hard-gates four failure modes (half-refresh, hash mismatch, unknown-read-as-pass, master pollution). Ships one skill.

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.

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.

On-demand memory for DeepSeek Harness: session logs are distilled into layered markdown (a summary, an index and per-topic files), and a mem_query tool returns only the matched entries rather than the whole index. Nothing is injected per turn, there are no dependencies, and every entry keeps a source pointer back to the conversation it came from.

Layered cross-session memory for DSH that pushes only what changed. The first round injects every active entry, later rounds push only added / updated / removed ones, and nothing at all is injected when nothing changed. Facts and decisions carry semantic keys (one active truth per key), the model may only write to an inbox that a human promotes, an entry can carry a review date that raises a one-time reminder when it comes due, search is relevance-ranked with Chinese matched by bigram, and a sidebar tab tells the lifecycle story instead of just listing files — entries are grouped into awaiting confirmation / in use / archived, viewable by type, tag or date, and the tab can promote a candidate, withdraw or archive a standing entry, restore an archived one and delete a candidate, alongside the global and workspace instruction files and the current injection size. A zero-dependency CLI ships with it, so the store is usable without DSH.

Multi-provider quota panel for DeepSeek Harness: DeepSeek official balance, jojo code, SCNet and Ark Coding Plan usage windows in the sidebar footer, with 90 days of local history and trend charts.

System-audio visualizer for the turn navigator rail: the rail reacts in real time to whatever the default playback device is rendering, with four motion modes (spectrum, pulse, sway, travelling wave), a 16-band logarithmic spectrum from a 2048-point FFT on the host, and live sensitivity, strength, bass-punch and wave-speed controls. Audio is captured host-side through WASAPI loopback, so there is no permission prompt, no microphone and no screen capture. The browser half adds one attribute, one stylesheet, some CSS variables and a sidebar control row, and never patches the official component; switching it off removes the attribute, the stylesheet and the variables, returning the rail to its default styling. Windows only.

Live change review for DeepSeek Harness: tracks write/edit tool calls per session, lists changed files above the composer and opens each file's line-level diff in a plugin-registered right-sidebar tab, with session-log / initial-version / Git comparison modes, per-change and per-file revert, subagent aggregation and SSE updates. A fork of cirelir/dsh-change-review rebuilt around the right sidebar.

Make a Git for Windows installation resolvable as `bash` inside the dsh host process, so the official bash shell stack (dsh-bash-sandbox + dsh-tool-bash) can run on Windows

Unofficial DeepSeek Harness plugin: add, remove, enable and disable external MCP servers from the Web settings page or from chat, so the harness calls their tools as native tools

Preview, debug (logs and screenshots), and publish WeChat Mini Games inside the dsh Web GUI, through the official mini game helper service

In-process DeepSeek Harness subagent provider that seeds a child with only the last N completed parent turns (fork-lite), leaving official fork untouched.

Engineering work-tools for DeepSeek Harness: registers two model-facing Host Tools — a scoped `git` runner, and a package-manager runner (`dev`) that detects npm/pnpm/yarn/bun from the workspace lockfile and picks the right verb per manager. Both run through dsh's sandboxed shell and return structured stdout/stderr/exitCode, so the agent gets focused, reviewable results instead of raw bash, and adding another tool is a copy-paste of one register block.

Knowledge Planet (知识星球 zsxq) integration for DeepSeek Harness: cookie/QR-login auth against the unofficial web API (api.zsxq.com/v2), exposes agent tools (groups, topics, topic detail, search, publish, comment, like), a login flow, and a web settings pane

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.

Report stage — academic paper writing for asset pricing and machine learning research. Ships one skill.

Data stage — data discovery and quality assessment for asset pricing and machine learning research. Ships one skill.

Literature review stage — search, synthesis, and citation-chain tracking for asset pricing and machine learning research. Ships one skill.