Apache-2.0 純 Markdown 自主科研系統：900+ 技能、四層層級與 7 個 MCP 整合；README 僅支援 Claude Code 與 Codex，無 DeepSeek Harness 路徑（生態級）。
DSH 整合
生態系相關
作者聲明
安全稽核
未稽核
最後核實
2026-08-21
授權條款
Apache-2.0
01它能幫你完成什麼？
Turn a research direction into an executable, machine-readable Research Spec
A Research Spec with checkbox progress tracking, quantified completion criteria, backtrack conditions and session recovery, generated after North Star crystallization
Researchers and AI engineers who want an autonomous AI research agent rather than a search assistant
Run systematic literature acquisition and research-gap discovery
Multi-pass academic paper discovery via Semantic Scholar with citation chaining and snowball sampling, plus 15+ gap detection methods
Academic and industry researchers who need systematic literature coverage instead of keyword search
Continue long research campaigns across sessions without losing state
Checkpoint-based context files (context/INDEX.md + ≥500-line checkpoints) that let a new agent session resume from the spec's checkbox state
Teams running multi-session deep-research campaigns that span days or weeks
02如何將外掛接入 DeepSeek Harness？
先決條件
- Node.js 22 or newer
- Claude Code or Codex as the executing agent runtime — the two runtimes documented in the README
- API keys for the MCP servers you enable (Brave, Apify; Tavily optional; Semantic Scholar key optional — public API works keyless at lower rate limits)
安裝步驟
- 01
Clone the repo and install dependencies: `git clone https://github.com/yogsoth-ai/de-anthropocentric-research-engine.git`, `cd de-anthropocentric-research-engine`, `npm install` (pulls the bundled MCP servers)
$ git clone https://github.com/yogsoth-ai/de-anthropocentric-research-engine.git
- 02
Codex: run `./install/codex.sh` (or `./install/codex.sh --target /path/to/your/project`; Windows: `.\install\codex.ps1`) — it adds a marked DARE section to the target's AGENTS.md and copies the knowledge base into `.dare/skills`; use `--dry-run` to preview
- 03
Claude Code: `cp mcp.example.json .mcp.json` and fill in your API keys
- 04
Claude Code: copy (or symlink) every skill into your project's `.claude/skills/` or the user-level `~/.claude/skills/` (e.g. `mkdir -p .claude/skills && cp -R skills/* .claude/skills/`)
- 05
Claude Code: invoke the entry point `/de-anthropocentric-research-engine`; later execute a generated spec with `/executing-specs`
- 06
Optional: for experiment-execution install the `superpowers` and `ponytail` Claude Code plugins via the plugin marketplace; for ara-from-context run `npx @ara-commons/ara-skills`
$ npx @ara-commons/ara-skills
驗證整合成功
作者未說明
03DSH 整合程度與能力邊界
Pure-markdown research-skill ecosystem; the README documents Claude Code (skills copied into `.claude/skills/`) and Codex (`install/codex.sh`) as the only runtimes and makes no DeepSeek Harness/dsh claim
Autonomous research orchestration (arsenal, not pipeline)
A research direction — cold-start from zero, warm-start from vague interest, or hot-start from a specific question→A crystallized North Star, then an executable Research Spec the agent executes stage-by-stage across 10 freely-composable packages, with explicit backtrack conditions
Writes Research Spec files (e.g. docs/de-anthropocentric/specs/) and context files during executionSystematic literature acquisition & gap discovery
A research topic or crystallized scope→Multi-pass paper discovery via Semantic Scholar (citation chaining, snowball sampling, cross-database verification) plus 15+ gap detection methods and 31+ ideation techniques
Network calls to Semantic Scholar and web-search MCP servers7 MCP integrations for external data access
Configured MCP servers: semantic-scholar, wiki-vault, brave-search, tavily-search, keenable, apify, alphaxiv→Paper lookup and citations, LLM-optimized web search, full-page scraping, and a persistent research knowledge graph (BM25 search, typed edges)
Requires API keys for some servers (BRAVE_API_KEY, APIFY_TOKEN; optional TAVILY_API_KEY, SS_API_KEY, VAULT_ROOT)keenable and alphaxiv connect to hosted remote endpoints (keyless public servers)Two Apify X-research Actors are paid and not loaded by the example configCheckpoint-based context management
A running research campaign spanning multiple sessions→Named context files with ≥500-line checkpoints, a context/INDEX.md registry, and automatic session recovery from the spec's checkbox state
Writes context files under context/ (gitignored at runtime)
04適合誰？何時不該用？
適合
- Researchers and AI engineers who want an autonomous AI research agent rather than a search assistant
- Academic and industry researchers who need systematic literature coverage instead of keyword search
- Teams running multi-session deep-research campaigns that span days or weeks
不適合
- DARE has no application code, runtime or framework — execution depends entirely on the host coding agent's ability to follow complex multi-step instructions; the README names Claude Code as the runtime, with Codex supported via the install script.
- The README documents no DeepSeek Harness (dsh) integration path — the Quick Start covers only Claude Code and Codex, so DSH users should treat DARE as an ecosystem research toolkit until a dsh path is published.
05相容性、維護與安全提醒
- DARE has no application code, runtime or framework — execution depends entirely on the host coding agent's ability to follow complex multi-step instructions; the README names Claude Code as the runtime, with Codex supported via the install script.
- The README documents no DeepSeek Harness (dsh) integration path — the Quick Start covers only Claude Code and Codex, so DSH users should treat DARE as an ecosystem research toolkit until a dsh path is published.
- Research campaigns reach external services via the 7 MCP servers — Brave and Apify require keys (Tavily and Semantic Scholar keys optional), while Keenable and AlphaXiv connect to hosted public endpoints; wiki-vault writes to a local vault directory you configure.
Apache-2.0 · actively maintained (latest release v3.2.2, 2026-06-21; last push 2026-08-15)
06常見問題
能在 DeepSeek Harness（dsh）裡執行 DARE 嗎？
依 README 現況不行。Quick Start 只涵蓋兩種執行環境——Claude Code（把技能複製或符號連結到 `.claude/skills/`）和 Codex（`install/codex.sh` 在目標專案的 AGENTS.md 中寫入 DARE 區塊）。README 沒有 dsh 安裝路徑，目前應把 DARE 當作生態級科研工具包。
DARE 是 MCP 伺服器還是原生工具？
都不是——DARE 是純技能架構：900+ 個 Markdown 指令檔由編碼代理直接讀取並執行，沒有應用程式程式碼和執行階段。它*使用* 7 個 MCP 伺服器（Semantic Scholar、Brave Search、Tavily、Keenable、AlphaXiv、Apify、Wiki Vault）取得外部資料。
需要什麼先決條件？
Node.js 22 或更新版本、git，以及 Claude Code 或 Codex 執行環境。`npm install` 會取得內建的 MCP 伺服器套件。部分 MCP 伺服器需要 API 金鑰（Brave、Apify；Tavily 選用；Semantic Scholar 無金鑰也能用，只是速率限制較低）；Keenable 和 AlphaXiv 是免金鑰的託管公開端點。
我的研究資料會流向哪裡？
MCP 呼叫會發往外部服務——Semantic Scholar、Brave/Tavily 網頁搜尋、Apify 抓取，以及託管的 Keenable 和 AlphaXiv 端點。Wiki Vault 把知識圖譜寫到你用 VAULT_ROOT 指定的本機 Obsidian 相容庫目錄。兩個 Apify X 資料抓取 Actor 是付費的，範例設定預設不載入。
主要限制有哪些？
執行完全依賴宿主代理遵循複雜多步指令的能力。experiment-execution 包還需要額外安裝 `superpowers` 和 `ponytail` 兩個 Claude Code 外掛，ara-from-context 需要外部的 `npx @ara-commons/ara-skills` 編譯器。
07相關的 DSH 工作流程
distilly
作者 titanwings
Distilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill（原同事 Skill）.
dsh-market
作者 dsh-market
The plugin market inside DeepSeek Harness — browse, search, one-click install · DSH 視覺化外掛市場
ai_animation
作者 unclecheng-li
本專案整理了用於生成[炫酷 HTML 動畫網頁]的 AI Prompts，涵蓋動畫效果、3D 視覺化、PPT 風格演示、UI 美化等多個類別。
aegis
作者 ganyuanran
讓 AI 編碼智慧體具備架構意識：基線優先、證據驗證、漂移檢查，保障長任務安全。
08資料與來源
The entire system is 900+ markdown files — each one a self-contained instruction set that Claude Code reads and executes…
Skills are auto-discovered from a `.claude/skills/` directory — there is no `settings.json` path option.
此頁面根據專案公開文件、儲存庫中繼資料與 DSH Plugins 的結構化解析所產生；最後核實於 2026-08-21。發現錯誤？提交更正。
最佳 DeepSeek Harness 外掛
從全目錄挑出的 12 個值得優先安裝的外掛，涵蓋各個分類。