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.

DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in
← Plugins
L

@snow-the/dsh-lib-analyzer

Lib Analyzer

Library absorption analysis for DeepSeek Harness: scan reference corpora (ref/), drive absorption-report task batches (tasks.jsonl → out/*.md), validate report discipline (evidence file:line, ✓◐✗ comparison, 提取方式), and maintain a searchable per-library knowledge base (.dsh-lib-analyzer/pages) — hind

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

npx -y @deepseek-ai/dsh plugin --profile web add github:snow-The/dsh-lib-analyzer#215c51102587e554c2357e21461532cd794e9478
READMECompatibilityVersions

Description

Library absorption analysis for DeepSeek Harness: scan reference corpora (ref/), drive absorption-report task batches (tasks.jsonl → out/*.md), validate report discipline (evidence file:line, ✓◐✗ comparison, 提取方式), and maintain a searchable per-library knowledge base (.dsh-lib-analyzer/pages) — hindsight-style knowledge pages driven by auditable reports instead of conversation recall.

Compatibility and provenance

Lib Analyzer is published as @snow-the/dsh-lib-analyzer 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
10/19/2026

Versions

0.1.0stable
10/19/2026

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
MIT
Source
github
GitHub
★ 0
Weekly downloads
0
Last push
11/1/2026
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

Related plugins

More verified plugins in search-research.

Browser Skill Dsh Plugin@wxg-prc-cpg/browser-skill-dsh-pluginDeepSeek Harness tool plugin that exposes BrowserSkill browser automation (bsk_* tools) to the modelFree Searchdsh-free-searchFree web search for DeepSeek Harness: 27 engines (Bing/DuckDuckGo/AnySearch/SearXNG/Exa/Tavily/Keenable/Firecrawl/Parallel/You.com keyless; Zhihu global/site via MCP and Perplexity/SerpBase/DeepSeek (official + native tools/search)/Baidu/Kimi/Aliyun/DoubaAb Wechat Scrapedsh-ab-wechat-scrape--- description: "The out-of-tree wechat_scrape tool: retrieves WeChat official-account articles, filters promotional blocks, and saves each as a Markdown file, for maintainers of this machine's dsh profiles." kind: "package-reference" ---Ab Market Researchdsh-ab-market-researchAn out-of-tree DeepSeek Harness plugin: the trade_search tool (multi-round aspect-broadening query planning, publisher-tier ranking, source diversity, JSON snapshot) and its browser card in one package.

README

dsh-lib-analyzer

Library absorption analysis for DeepSeek Harness — turn a reference corpus (ref/) into auditable, evidence-first absorption reports and a searchable per-library knowledge base.

Inspired by two things, and better than both for this job:

  • r32's ref → batch pipeline (tasks.jsonl → prompts → batch/out/*.md absorption reports with 大文件纪律 / 证据优先 / 提取方式 provenance): its discipline is now enforced by tools, not just prompt text.
  • hindsight-coding-agents: its knowledge-page + retrieval idea is kept, but pages here are derived from finished reports (with file:line evidence and rebuildable from disk) instead of being recalled from conversation — auditable, no background model calls, fully offline.

Tools

ToolPurpose
libscanScan ref/<library>: tree, language mix, >1MB big-file list (big-file discipline), doc inventory. Read-only.
libtasksDrive batch/tasks.jsonl (id/target/focus/deliverable/output per line): list with filesystem-derived status, or --next pending task in full.
libreportValidate a finished report (required sections 概览/关键机制/可吸收设计/落地章节建议/风险与教训/提取方式, ✓◐✗ markers, file:line evidence), then sink a knowledge page into .dsh-lib-analyzer/pages/ and update the index.
libsearchKeyword search across knowledge pages + produced reports (hindsight-style retrieval, local-only).

Skill

  • library-analysis — full workflow: take task → read project context (adc/src/book/SYNTHESIS) → scan → disciplined read-only research → report with provenance → libreport sink → next task.

Layout

<project>/
├── ref/                 # read-only reference corpus
├── batch/
│   ├── tasks.jsonl
│   └── out/*.md         # absorption reports
└── .dsh-lib-analyzer/
    ├── index.json
    └── pages/<lib>.md   # per-library knowledge pages

Design rules

  1. Node builtins only — no child processes, no network, no model calls.
  2. All writes stay inside .dsh-lib-analyzer/.
  3. Task status is derived from the filesystem (output file exists), never from memory.
  4. The knowledge base is fully rebuildable from reports.

License

MIT