플러그인

DeepSeek Harness Web을 위한 조합 가능한 작업·추론·품질·사람 검토 자기진화 컨트롤.

DeepSeek Harness Web을 위한 조합 가능한 작업·추론·품질 컨트롤.

Cordis 네이티브의 증거 기반 풀스택 엔지니어링 워크플로: 조사 우선 계획, 명시적 검증 증거, 민감한 작업에 대한 승인 인식 게이팅.

Matt Pocock의 선별된 엔지니어링·생산성 에이전트 스킬 25개(집요한 질문, TDD, 코드 리뷰, 도메인 모델링 등)를 이식한 DSH 번들.

엔지니어링 방법론 스킬 라이브러리를 하나의 Cordis 플러그인으로 묶음: DeepSeek Harness의 ctx.skills에 14개 Agent Skill(계획·테스트·디버깅·리뷰·인도)을 등록합니다.

SOLIDWORKS for DeepSeek Harness: dsh reads, edits, rebuilds, renders and exports the models in a SOLIDWORKS 2016 or later, on the same Windows PC or in a Windows VM on your Mac. Read-only by default; the Windows side decides what may be written.

提示词优化按钮（完全免费）：一键把输入改写成更清晰的提示词。内置免费模型通道，零配置零费用，不可用时自动回退到对话模型。

WeChat Mini Program engineering tools: scan a project for pages missing from app.json, scaffold pages with automatic registration, fix orphan pages, manage subpackages, tabBar and components, and drive the WeChat DevTools CLI for preview QR codes and uploads.

Provides a specification-driven engineering workbench with versioned requirements and documents, isolated Git workspaces, independent review, verification, and explicit human acceptance. Requires Node.js 24+ and Git.

Engineering checklists distilled from Gillespie's Fundamentals of Vehicle Dynamics: 164 cards over the book's ten chapters, one skill entry with two-level routing. Each card gives the inputs a computation needs, the procedure, the boundary conditions where the method stops being valid, and a page reference — the explanation itself stays in the book. No passage of the book's prose is reproduced; about 77 defects in the source (misprints, OCR damage, internal contradictions) are documented in the cards. A study aid, not a substitute for the book.

Composes tools, skills and MCP servers into switchable per-session sets, shrinking the resident tool surface and the system prompt on demand.

Toggles the rea-mcp server on and off from the DSH Web UI session header or through the rea_mcp_toggle agent tool, so the 170 mcp__rea__* tool schemas stop being sent with every request while REA is off (the tools payload drops from about 722 KB to about 95 KB) and the REA child process exits; the choice is kept in a profile-scoped state file and restored at startup by a row-level disabled expression.

One switch that takes an MCP server's tool schemas and its instructions block out of the model context for every agent, live and without a restart, built for the 207 tool schemas REA registers whether or not a task is reverse engineering. A pill in the composer dock, /rea on|off|status|toggle, and GET/POST /rea-toggle/state; the position is remembered across restarts and subagents are covered before their first step.

Stops compaction summaries and session titles from burning their output budget on reasoning, by lowering the thinking level and raising the token floor for auxiliary calls only.

Sparkle button immediately left of the model selector that rewrites the composer draft into an executable prompt in place, modelled on WorkBuddy: the host calls the conversation LLM with a prompt-engineering system prompt, multi-level undo keeps up to 8 previous drafts, and a token-level diff card shows added and removed spans, the number of changed spots and the net character delta. Runs on the session model, is disabled while the draft is empty, and keeps the browser-session cookie fence in front of the LLM call.

Adds an ✦ button to the DSH composer that rewrites the current draft into a clearer, more specific prompt in the same language, with one click to restore the original, plus an enhance_prompt tool the agent can call; the rewrite replaces the draft and is never sent automatically.

Adds a ✨ button and an /enhance command to the composer that rewrite the draft into a structured prompt, flag open questions below the input, follow the current session model, and offer an undo.

Adds a reforge control to the DSH composer that rewrites the current draft into a sharper prompt in place, as one undoable edit, with one-click revert and cancellation.

Adds a sparkle button to the DSH composer that rewrites the current draft into a clearer, more specific prompt with a single tool-free LLM call, then writes the result back into the input.

Adds an enhancement chip to the composer input action row, left of the model selector: it rewrites the draft in place using the model already selected in the session, in five styles, with one-click undo and an /enhance slash command.

Reverse-engineering workbench: bridges a local IDA Pro into DeepSeek Harness through @deepseek-ai/dsh-mcp-client, exposing the ida-pro-mcp toolset (decompile, xref, rename, comment) as mcp__ida__* tools. Auto-selects idalib headless mode (analyses a binary in-process, no IDA GUI) or GUI mode (connects to the IDA plugin RPC on port 13337). Adds re_check, re_open and re_status; the bundled MCP server is a zero-dependency stdio proxy usable from any MCP client.

SillyTavern-style prompt rules for DSH: layered system-prompt anchors, constant/keyword entries, reproducible probability gates and regex rewriting.

Rewrites your composer draft in the voice of a chosen character card before it is sent, using the model the current session is already on, with an optional review panel and a local check that reports any identifier or path the rewrite dropped.

DSH 试金石：给「自改造」补上评测这一环——用一套金标准用例，把改动前 vs 改动后跑一遍、打分、对比，好就留、不好就撤。