DSH Plugins Marketplace

DSH Plugins

Plugins

/

Tools & Capabilities

/

dsh-academic-research-skills

d

dsh-academic-research-skills

Manifest valid

Community-maintained ARS port for DeepSeek Harness with research and writing skills, native Team review and pipeline workflows, and workspace-scoped status and integrity tools.

hasBundlePatch

dsh-academic-research-skills

English · 中文

DeepSeek Harness(DSH)插件:把 Claude Code 的 Academic Research Skills (ARS) (v3.24.2,CC-BY-NC-4.0)移植为 DSH 技能,并随包携带完整 ARS 核心工具层 (scripts/、shared/、根 agents/ 与 MODE_REGISTRY.md)。

安装后自动获得:

  • 5 个模型可调用技能:deep-research(13-agent 调研团队,8 种模式)、 academic-paper(12-agent 论文写作,11 种模式)、academic-paper-reviewer (5 席位同行评审面板)、academic-pipeline(10 阶段全流水线编排)、 sr-screener(协议驱动的系统综述记录筛选,8 种模式)
  • 2 个原生 DSH 团队技能(0.4.4 原生层):ars-team 用真实 subagent 跑五席位评审; ars-pipeline-team 把 10 阶段流水线映射成 Team board 的 stage task graph
  • 5 个原生工具(0.4.4):ars_search(OpenAlex 检索)、ars_lookup (DOI 元数据,OpenAlex/Crossref)、ars_integrity(调用 vendored check_pipeline_integrity.py)、ars_pipeline_status(流水线阶段产物盘点)与 ars_manifest(pinned upstream/内容计数);仅在 tools 服务挂载时注册,否则自动跳过
  • 可选 ARS Team agent preset(0.4.4):在 agentPresets 服务可用时注册, 新会话可选择 ars-team 预设,组合 ars-team 技能与 Team board
  • 映射、验证与市场草稿:native/team-map.md、 docs/native-validation.md、 docs/market/listing.md
  • 完整 ARS 核心工具层:根 scripts/(Python 检查器、ledger、citation gate、 adapters)、shared/(schema/合同)、根 agents/ 与 MODE_REGISTRY.md, 与上游对应文件逐字节一致
  • 16 个用户可调用命令:/ars-full、/ars-plan、/ars-reviewer、 /ars-lit-review、/ars-abstract、/ars-revision、/ars-outline、 /ars-citation-check、/ars-disclosure、/ars-format-convert、 /ars-rebuttal-audit、/ars-revision-coach、/ars-cache-invalidate、 /ars-mark-read、/ars-unmark-read、/ars-3w

署名 / Attribution:本项目为 ARS 的 DSH 移植,技能内容与命令衍生自 Cheng-I Wu(Imbad0202)的 academic-research-skills, 全部内容(含移植层)遵循 CC-BY-NC-4.0(非商业用途),详见 NOTICE.md 与 LICENSE。

本仓库是由 TY-Cheng 维护的社区 DSH 移植,源自 nullptr-DZF 的移植版本, 不是 ARS 官方发行版;上游仍是 Imbad0202 的 ARS。

安装

当前版本为 v0.4.6;详见发布说明。

要求:DeepSeek Harness(dsh)0.2.x(本次 e2e 在 0.2.2-rc.5 上验证), pnpm 可用。完整确定性工具链另需 Python 3.9+;建议在插件目录建 .venv:

python3 -m venv .venv
.venv/bin/python -m pip install -r requirements-dev.txt
# 可选:PDF 内容分类器
.venv/bin/python -m pip install -r requirements-pdf-content-classifier.txt
# 方式一:GitHub 仓库(当前 v0.4.6)
dsh plugin --profile web add github:TY-Cheng/dsh-academic-research-skills#v0.4.6

# 提交上游审查的 e2e 使用 v0.3.0(不含 0.4.4 原生层)
dsh plugin --profile web add github:TY-Cheng/dsh-academic-research-skills#v0.3.0

# 方式二:本地路径(开发调试)
dsh plugin --profile web add <本仓库绝对路径>

# 把 web 换成实际 profile(本次 e2e 用 desktop);重启对应 profile 后生效

安装后 dsh.profile.bundles 会追加 dsh-academic-research-skills,启动时 lib/startup.js 把 23 个入口(5 个 vendored 技能 + 2 个原生技能 + 16 个命令) 注册进 ctx.skills;manifest.json 记录上游 pin,SYNC_POLICY.md 说明 vendored 边界。

使用

用法操作
模型自动路由直接说“做学术研究 / 文献综述 / 帮我审稿 / 写论文”等(技能描述带触发词)
技能注入输入 /deep-research、/academic-pipeline 等技能名
斜杠命令输入 /ars-full(全流程)、/ars-reviewer(审稿)、/ars-plan(规划)等

与上游的差异

  • hooks 不移植:上游 Claude Code 的按角色写入 guard 与 SessionStart 播报在此移植版中不可用。macOS 上,DSH 0.2.2-rc.5 的文件写入与 Bash 后端在实测的 workspace-write 策略下允许 workspace 内写入、 拒绝向测试用的相邻目录写入。这是宿主写入边界,不等同于 ARS 的按角色 guard。见实测与适用范围。
  • 完整核心已 vendor:skills/、scripts/、shared/、根 agents/、 MODE_REGISTRY.md 与上游对应文件逐字节一致;commands/ 是生成的 DSH 适配层。Python 依赖见上。
  • 路径解析:注册时会在每个技能正文前加入 ARS package root 提示, DSH_ARS_ROOT 指向插件包根目录;sr-screener 自己的 scripts/ 仍相对 技能目录解析。这样 python3 scripts/... 不会误落到用户论文项目目录。
  • 原生层(0.4.4):native/skills/ars-team 把五席位评审 映射为真实 subagent;native/skills/ars-pipeline-team 把 10 阶段流水线 映射为 Team board 的 stage task graph;lib/startup.js 在 tools 服务 可用时注册 ars_search/ars_lookup/ars_integrity/ars_pipeline_status/ ars_manifest,在 agentPresets 可用时注册可选 ars-team preset。 vendored 内容不变;原生层验证与提交上游审查的 v0.3.0 e2e 分开。
  • 子代理:5 个 vendored 技能内共 42 个 agent 提示文件(另有 4 个根 agents/ 文件)默认内联运行;ars-team 用 subagent 分工跑五席位。 角色分离是流程控制,不是独立误差过程的证明。
  • 命令包装为 DSH 适配版:由上游 commands/ars-*.md 再生成并去掉 Claude Code 专属的 Skill 工具调用与 ${CLAUDE_PLUGIN_ROOT} 路径,产物可直接在 DSH 中执行(见下节)。

重新生成命令包装

commands/ 由上游 commands/ars-*.md 转换而来(加入 disable-model-invocation: true + user-invocable: true):

node tooling/regenerate-commands.mjs <上游仓库路径>

再生成时会自动去掉 Claude Code 专属的 Skill 工具调用和 ${CLAUDE_PLUGIN_ROOT} 路径。

日常同步与校验:

node tooling/sync-upstream.mjs <上游仓库路径>   # 复制核心 + 生成命令 + 写 manifest
npm run verify                                  # 离线哈希校验 + 23 个注册断言

English

A DeepSeek Harness plugin port of Claude Code's Academic Research Skills (ARS) (v3.24.2, CC-BY-NC-4.0). The package also carries the full ARS core: scripts/, shared/, root agents/, and MODE_REGISTRY.md.

Provides, out of the box:

  • 5 model-invocable skills: deep-research, academic-paper, academic-paper-reviewer, academic-pipeline, sr-screener
  • 2 native team skills (0.4.4 native layer): ars-team, which runs the five-seat panel as real subagents, and ars-pipeline-team, which maps the 10 pipeline stages onto a Team-board stage task graph
  • 5 native tools (0.4.4): ars_search (OpenAlex search), ars_lookup (DOI metadata via OpenAlex/Crossref), ars_integrity (runs the vendored check_pipeline_integrity.py), ars_pipeline_status (stage-artifact inventory), and ars_manifest (pinned upstream/content counts); registered only when the tools service is mounted, skipped otherwise
  • Optional ARS Team agent preset (0.4.4): registered when agentPresets is mounted; a new session can select the ars-team preset, which composes the ars-team skill with the Team board
  • Full ARS core: root scripts/ (Python checkers, ledger, citation gate, adapters), shared/ (schemas/contracts), root agents/, and MODE_REGISTRY.md, byte-identical to upstream
  • 16 user-invocable commands: /ars-full, /ars-plan, /ars-reviewer, /ars-lit-review, /ars-abstract, /ars-revision, /ars-outline, /ars-citation-check, /ars-disclosure, /ars-format-convert, /ars-rebuttal-audit, /ars-revision-coach, /ars-cache-invalidate, /ars-mark-read, /ars-unmark-read, /ars-3w

Attribution: this is a DSH port of ARS; skill content and commands are derived from Cheng-I Wu's academic-research-skills. Everything in this repo (including the porting layer) is licensed CC-BY-NC-4.0 — non-commercial use only. See NOTICE.md and LICENSE.

This community DSH port is maintained by TY-Cheng and builds on nullptr-DZF's original port. It is not an official ARS release; upstream remains Imbad0202's ARS.

Install

The current version is v0.4.6. See the release notes.

Requires DeepSeek Harness 0.2.x (tested on 0.2.2-rc.5) and pnpm. The deterministic tooling also needs Python 3.9+; a plugin-local .venv is recommended:

python3 -m venv .venv
.venv/bin/python -m pip install -r requirements-dev.txt
# optional PDF content classifier
.venv/bin/python -m pip install -r requirements-pdf-content-classifier.txt
# current release (v0.4.6)
dsh plugin --profile web add github:TY-Cheng/dsh-academic-research-skills#v0.4.6
# v0.3.0 used for the e2e submitted for upstream review (no 0.4.4 native layer)
dsh plugin --profile web add github:TY-Cheng/dsh-academic-research-skills#v0.3.0
# or from a local checkout:
dsh plugin --profile web add /path/to/this/repo
# replace web with your profile (this e2e used desktop); restart it

The bundle patch mounts lib/startup.js, which registers 23 entries (5 vendored skills, 2 native skills, and 16 commands) into ctx.skills at boot.

Differences from upstream

  • Hooks are not ported: the upstream Claude Code per-role write-scope guard and SessionStart announcement are unavailable in this port. On macOS, DSH 0.2.2-rc.5's file-write and Bash backends under the tested workspace-write policy allowed writes inside the workspace and denied the tested writes to a sibling directory. This is host-level confinement, not the ARS per-role guard. See the test and its limits.
  • Full core is vendored: skills/, scripts/, shared/, root agents/, and MODE_REGISTRY.md are byte-identical to upstream; commands/ is the generated DSH adapter layer. Python dependencies are listed above.
  • Path resolution: every registered skill body is prefixed with an ARS package-root note; DSH_ARS_ROOT points at the plugin package root. sr-screener's own scripts/ still resolve relative to its skill directory, so python3 scripts/... does not fall through to the paper project.
  • Native layer (0.4.4): native/skills/ars-team maps the five-seat review to real subagents; native/skills/ars-pipeline-team maps the 10 stages onto a Team-board stage task graph; lib/startup.js registers ars_search/ars_lookup/ars_integrity/ars_pipeline_status/ars_manifest when the tools service is mounted, and an optional ars-team preset when agentPresets is mounted. Vendored content is unchanged; the native validation is separate from the v0.3.0 e2e submitted for upstream review.
  • Subagents: the 42 skill-agent prompt files (plus the 4 root agents/ files) run inline by default; ars-team uses subagents for the five seats. Role separation is a process control, not proof of independent error processes.
  • Command wrappers are DSH-adapted: the wrappers are regenerated from the upstream commands/ars-*.md and stripped of Claude Code's Skill tool calls and ${CLAUDE_PLUGIN_ROOT} paths, so they run as-is under DSH.

Regenerating command wrappers

commands/ is generated from upstream commands/ars-*.md:

node tooling/regenerate-commands.mjs <upstream-checkout-path>

Regeneration also strips Claude Code's Skill tool call and ${CLAUDE_PLUGIN_ROOT} paths.

For a routine sync and offline check:

node tooling/sync-upstream.mjs <upstream-checkout>   # copy core + regenerate commands + manifest
npm run verify                                      # hashes + 23 registration assertions

Comments

Loading…

Similar plugins

dsh-academic-research-skills

by nullptr-DZF

Ported from the ARS Claude Code plugin (44k+ stars on GitHub): academic research skills for DeepSeek Harness — a deep-research agent team, a paper-writing pipeline, a multi-perspective peer-review pan

Knowledge & docsManifest valid

★ 34

JavaScript

Aug 27, 2026

dsh plugin --profile web add dsh-academic-research-skills

by lobster-liu

Multi-agent A-share research pipeline skill for DeepSeek Harness (6 roles, dual-blind risk review, source-cited reports, PII gate)

Manifest valid

★ 0

MIT

Python

Nov 4, 2026

dsh plugin --profile web add dsh-invest-research

by coffee-man666

Repository and agent-runtime analysis skills as an installable DeepSeek Harness (dsh) plugin

Security & AuditManifest valid

★ 0

MIT

TypeScript

Aug 24, 2026

dsh plugin --profile web add @deepseek-ai/dsh-lens

by qkycir-123

Automatically turn successful DeepSeek Harness sessions into reusable, reviewable Agent Skills.

Tools & CapabilitiesManifest valid

★ 109

↓ 442/wk

MIT

TypeScript

Nov 15, 2026

dsh plugin --profile web add dsh-run2skill

by lau4tin1

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

Manifest valid

★ 0

NOASSERTION

TypeScript

Oct 1, 2026

dsh plugin --profile web add dsh-skill-router

Coding agent preset plus an embedded coding-discipline skill for DeepSeek Harness: verify-first edits, minimal diffs, real test runs and evidence-based reports.

Tools & CapabilitiesManifest valid

★ 0

dsh plugin --profile web add dsh-coding-discipline