paper-workbench
A DeepSeek Harness bundle for a paper-reading, learning, and reproduction workbench.
Install
$ dsh plugin --profile web add github:LessXi/paper-workbench # 在 DSH 源码目录跑 pnpm dsh …，可加 #<commit> 锁定Plugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Registers a `paper` tool with status and PDF parsing functions.
- Initializes workspace-based paper-lab skills through `/paper-init`.
- Provides workflows for paper search, reading, learning, citation mapping, surveys, update watching, reproduction, and workbench review.
- Supports lite text extraction and an optional fuller parsing setup for formulas, tables, and figures.
- Can configure MCP-based paper search where available, with documented fallback to web search and curl retrieval.
Useful For
- Create a structured workspace for literature review and research notes.
- Study papers with guided questioning, recall checks, and code review rather than AI-only summaries.
- Build surveys with method lineages, comparison matrices, and timelines.
- Track arXiv topics and produce update digests.
- Attempt CPU-oriented paper reproductions with numerical comparisons.
Who It Fits
- DeepSeek Harness users researching academic literature.
- Agents and terminal users using ZCode, Claude Code, or compatible workspace skills.
- Researchers and students who want a local paper-study workflow.
Documented Limitations
- DSH installation is documented for the web profile and must be run from the DSH source directory via pnpm.
- The workflow requires `uv`; Python 3.12 is managed through it.
- Full parsing has a longer initial setup and depends on MinerU, while lite mode provides text extraction.
- MCP search integrations are optional and fall back to web search and curl when unavailable.
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 4 development, 2 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- LessXi/paper-workbench
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin Bundle
- Source checked
- 487c5f6 · 2026-08-20
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 0GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-08-19
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed safety and session audit.
View plugin →Native SQLite-backed local project taskboard plugin and UI for DeepSeek Harness with Agent claim and review flows.
View plugin →Persistent multi-model Agent teams and bounded DAG workflows with GUI controls for DeepSeek Harness.
View plugin →A standalone, local persistent-memory system for AI agents, with DeepSeek Harness support provided through the separate dsh-mnemon plugin.
View plugin →