DSH Plugins Marketplace

DSH Plugins

Plugins

/

Development & Infrastructure

/

dsh-research-lab

s

dsh-research-lab

Manifest valid

Research lab toolkit for DeepSeek Harness: AutoSci wiki, ASI-Bench eval ledger, self-building FTS5 retrieval, arXiv digest/review, writing rewrite

hasBundlePatch

dsh-research-lab

Research-lab toolkit for DeepSeek Harness: a wiki-centric, eval-rigor-driven research workflow distilled from AutoSci (wiki as the center of a research project), ASI-Bench (evaluation rigor), daily-arXiv-ai-enhanced (digest), ChatPaper (paper review), nature-skills / research-writing-skill (academic writing), Supervisor-Skills (senior-review instinct), and hard lessons from real distillation experiments (hypothesis → verdict loops, eval 口径 discipline).

Tools

toolpurposeinspired by
rlab_wikiwrite wiki pages (experiment/literature/decision/todo) under <project>/.rlab/wiki/ + rebuild indexAutoSci
rlab_experimenthypothesis → prediction → evidence → verdict → conclusion pagesAutoSci + falsifiability discipline
rlab_benchper-project eval ledger (bench.jsonl); flags 口径 (protocol) mismatches, e.g. mixing test/dev splitsASI-Bench
rlab_paper_reviewarXiv id → adversarial 8-point review checklist (also applies to your own papers)ChatPaper + ASI-Bench
rlab_arxiv_digestkeyword digest of recent arXiv papers → <project>/.rlab/digests/<date>.mddaily-arXiv-ai-enhanced
rlab_writingline-anchored academic-expression check (passive/weak verbs/vague quantifiers/filler/term consistency)nature-skills, research-writing-skill
rlab_relatedself-building keyword retrieval: NLP tokenization + SQLite FTS5, no preset lexicon — terms are TF-IDF-mined from your docs (EN words + ZH n-grams) and expanded iteratively (search → mine → merge → repeat)hamuleite-style corpus, Rocchio relevance feedback
rlab_statusone-screen project state: wiki counts, bench report, open TODOs—

On-disk layout

<project>/.rlab/
  wiki/
    index.md            # auto-rebuilt
    experiment/<id>.md  # hypothesis → verdict
    literature/<id>.md  # paper notes (link from digests)
    decision/<id>.md    # ADRs: why you chose X
    todo/<id>.md        # open items
  related.db           # FTS5 corpus + auto-built lexicon (rlab_related)
  bench.jsonl           # one eval row per line (JSON)
  digests/<date>.md     # arXiv digests

Eval 口径 discipline (rlab_bench)

Every row must state metric, split, and for MTEB tasks the hf_subset. The report warns whenever a task's history mixes splits — comparing test-vs-dev scores is the classic way papers fool themselves (and reviewers).

Install

# from ~/.dsh/profiles/web
pnpm add @snow-the/dsh-research-lab@file:../.dsh-starter/plugins/dsh-research-lab
# add "dsh-research-lab" to dsh.profile.bundles, then restart dsh web

Build

pnpm install && pnpm build   # tsc declarations + esbuild bundle → dist/

Comments

Loading…

Similar plugins

dsh-raven-research

by wxxb789

Source-grounded deep research, writing, and learning plugin for DeepSeek Harness (dsh): steerable checkpoints, mid-run steering, and citations verified against retrieved sources.

Manifest valid

★ 0

MIT

TypeScript

Oct 6, 2026

dsh plugin --profile web add dsh-raven-research

by x2802490130-prog

Writing engine for DeepSeek Harness: long-form web-novel orchestration with a separate DeepSeek key, lore management, semantic retrieval, and a corpus library.

Tools & CapabilitiesManifest valid

★ 12

↓ 380/wk

MIT

JavaScript

Aug 25, 2026

dsh plugin --profile agent add dsh-tool-writing

by 863683348

Academic writing toolkit for DeepSeek Harness agents: paper outlines, title/abstract skeletons, GB/T 7714 / APA / MLA citations, phrasing QA, and a pre-submission checklist

Tools & CapabilitiesDevelopment & InfrastructureManifest valid

★ 8

↓ 405/wk

MIT

JavaScript

Sep 11, 2026

dsh plugin --profile web add dsh-plugin-academic-writing

by kiiiiile

AI-reviewed auto-approval for DeepSeek Harness: safe tool asks granted automatically, risky ones escalated with the review attached

Manifest valid

★ 0

MIT

TypeScript

Sep 14, 2026

dsh plugin --profile web add dsh-approval-ai-review

DeepSeek Harness plugin: a research desk for literature discovery, anchored reading, multi-perspective review, hypothesis tracking, sandboxed verification runs and export.

Tools & CapabilitiesManifest valid

★ 0

MIT

JavaScript

dsh plugin --profile web add dsh-research-desk

by NIRVANA-APOC

Local-first AI literature desk for DeepSeek Harness: parsing, bilingual reading, in-page AI answers, knowledge graphs, and agent library tools.

Tools & CapabilitiesManifest valid

★ 0

TypeScript

Nov 9, 2026

dsh plugin --profile web add dsh-litnotes