DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

Scholia — DSH Plugin for DeepSeek Harness
← Plugins
S

dsh-scholia

Scholia

DSH plugin dsh-scholia

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add github:H2CO3w/scholia#5e206a656324a50ab48715833d6d8dfe81ac2bc7
READMECompatibilityVersions
3424460d00818798fc142cd9386a5c76

Description

DSH plugin dsh-scholia

Compatibility and provenance

Scholia is published as dsh-scholia and currently resolves to version 0.1.0. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
any
Release source
github
Registry updated
10/7/2026

Versions

0.1.0
stable
10/7/2026

Related plugins

Loading related plugins…

Latest
0.1.0
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
any
License
Not declared
Source
github
GitHub
★ 0
Weekly downloads
0
Last push
10/9/2026
View source ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in

Related plugins

More verified plugins in search-research.

Weknora@wxg-prc-cpg/dsh-weknoraWeKnora knowledge retrieval tools for DeepSeek Harness (dsh): semantic search, document reading and RAG/agent answers over your own knowledge bases.Free Searchdsh-free-searchFree web search for DeepSeek Harness: 24 engines (Bing/DuckDuckGo/AnySearch/SearXNG/Exa/Tavily/Keenable/Firecrawl/Parallel keyless; Zhihu global/site via MCP and Perplexity/SerpBase/DeepSeek/You.com/Baidu/Kimi/Aliyun/Doubao with key; OpenAI/Gemini/Claude Dejadsh-dejadeja-vu memory for DeepSeek Harness: the session history of forty other coding agents, searchable and recalled before each step — a local index, no LLM.Builtin Browserdsh-builtin-browserShared real browser plugin for DeepSeek Harness: install-and-use — a visible native browser the human can take over, driven by the agent over CDP. DOM-level interaction (React/Vue safe), per-task session isolation, cookie persistence (dsh_browser_auth), C

README

scholia

(package name dsh-scholia)

v0.1 — early and incomplete. Interfaces will change.

A DSH plugin that turns a formalized theorem (Lean 4 / Mathlib) into something a mathematician can actually read: a paper-style page with the statement rendered as math, a proof outline, and annotations anchored to the formal objects.

Everything here is generated from a real corpus of Mathlib declarations plus out-of-corpus Lean sources used as regression fixtures.

What it produces

3424460d00818798fc142cd9386a5c76
ArtifactWhat it is
Paper view out/render/*.htmlOne page per theorem: rendered statement, Lean source, per-step annotations. Zero <script>.
Main-line outline out/outline/<root>/index.htmlThe proof's dependency cone reduced to a single ordered line of steps, each with the author's own one-sentence summary.
Step pages out/outline/<root>/NN.htmlFor one step: the modules it brings with it, each with its own summary.
Dependency graph out/graph/*.svgThe module-level import DAG, statically rendered.

Start with out/outline/Euler.Solution/index.html and out/render/CHSH_inequality_of_comm.html.

How the outline is built

The module graph alone is unreadable at 1829 nodes. What works is a main line:

  • start from the module that declares the paper's theorem (taken from the source repo's formalization.yaml);
  • at each step follow the dependency with the largest subtree;
  • each step's load is the telescoping difference |subtree(p_i)| - |subtree(p_{i+1})|, which partitions the cone exactly — no overlaps, nothing missed.

Every module carries a /-! ... -/ docstring written by whoever wrote the file, so each step can be labelled with a sentence of mathematics instead of a file name.

Reading order is foundations-first (--order reading); the reverse is the raw dependency order.

Layout

src/core/     pure logic: skeleton extraction, anchors, graph, validation
src/io/       corpus streaming, SQLite lexicon index, artifacts, contract
src/render/   pure string generation: paper view, outline, graph, math
src/tools/    the DSH tools
scripts/      offline export scripts
vendor/katex/ vendored KaTeX (self-contained, server-side rendering)
docs/         SPEC / ARCHITECTURE / INTERFACES / USAGE (Chinese)
test/         incl. out-of-corpus Lean fixtures
out/          generated artifacts

Requirements

Node.js 24+ (uses the built-in node:sqlite), Lean 4 sources if you want to regenerate the graph/outline artifacts.

The corpus (data/lsv2.jsonl) and the lexicon index (cache/lexicon.db) are not in this repo — they are hundreds of MB. See docs/USAGE.md.

Status

  • 360 tests, 0 failures.
  • The paper view is the mature part; the outline and graph are newer (v1.4).
  • Known limits are recorded in docs/ARCHITECTURE.md §11, including the Unicode→LaTeX gaps, the surface-syntax dependence of the skeleton extractor, and what the v1.3 "signature unknown" handling covers.

License

MIT — see LICENSE.

Bundled third-party material keeps its own license:

  • vendor/katex/ — KaTeX, MIT (see vendor/katex/LICENSE and PROVENANCE.json)
  • test/fixtures/lean/ — fragments from openai/NavierStokesAndEuler, Apache-2.0, attributed in each fixture header