alaliqing/claude-paper
claude-paper is a tool for DeepSeek Harness. ð Cross-agent research paper toolkit for Claude Code, Codex, OpenCode, and DeepSeek Harnessâquick summaries, deep study materials, code demos, and a local web viewer.
REVIEW SCORECARD
â No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
A well-documented multi-agent paper study toolkit with active updates, though security and engineering rigor can't be fu
README documents a structured npm package with versioned install/upgrade flows, Node version constraints, and a Nuxt.js viewer, but no tests or CI are mentioned so rigor is only partially evidenced.
The install runs `npx --yes @zlzliqing/claude-paper@latest install`, which downloads and executes a remote package and writes to `~/.agents/skills/` and `~/claude-papers/`, but no secrets, permissions, or audit details are disclosed, so a neutral score is given.
It addresses a real pain point by turning PDFs into summaries, study materials, code demos, and a searchable local viewer across four agent hosts, which is a concrete and commonly needed workflow.
The repository is not archived and shows a last update of 2026-08-14 with 327 stars, indicating ongoing activity, though no commit history or release cadence is visible.
The README provides clear install commands per agent, system requirements including poppler-utils, usage examples with slash commands and URLs, and a marketplace alternative, making setup understandable.
Generated by AI after reading the project README â a decision aid, not an endorsement. Neutral scores are given when information is limited.
Loading GitHub README...
The GitHub README is temporarily unavailable. Please try again later.
Open repositoryINSTALL REFERENCE
npx --yes @zlzliqing/claude-paper@latest installThis command was extracted from an explicit README install reference and is display-only; the DSH host will not execute it automatically.
PROJECT TOPICS
VALIDATION LADDER
FAQ
ð Cross-agent research paper toolkit for Claude Code, Codex, OpenCode, and DeepSeek Harnessâquick summaries, deep study materials, code demos, and a local web viewer.
claude-paper has 327 stars and 25 forks on GitHub, last updated 2026-08-14.
claude-paper is distributed under the MIT license.
claude-paper is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
The system checks GitHub Topics against the site taxonomy and keyword rules. Current matches:agent-skillsãacademic-toolsãclaude-codeãcode-generationãlearning-managementãpdf-parserãresearch-papersã
Tiger3807861189
DeepSeek V4 Ã J-Space capability realization report â benchmark evidence that J-Space reduces capability-realization loss on DeepSeek V4.
1692775560
Mimir â one-stop research workbench plugin: compile LaTeX papers while writing, manage arXiv literature, track experiments, create metric charts, and orchestrate GPU server SSH tasks, covering the entire research cycle. An open-source research workbench plugin for the whole research cycle.
PerryLink
Verifiable research-report engine for DeepSeek Harness: content-addressed evidence ledger (claim-snapshot binding, tamper-evident) plus versioned sealed reports with per-claim verification verdicts and a manifest-sealed directory.
PerryLink
Industry and company research domain pack for DeepSeek Harness: methodology skills, industry chain mapping, public-source policy/news tracking, company research cards, and auditable research reports. Research only - not investment advice.
pingfanfan
From scratch, understand DeepSeek Harness's 'everything can be a plugin' â zero-basis plugin development tutorial (with 22 Chinese Skill examples) | Zero-to-plugin tutorial for DeepSeek Harness
xmutfyh
DeepSeek Harness (DSH) academic writing guard for papers â remove AI flavor from papers / AI-writing style detection, evidence preservation, journal-fit calibration, manuscript proofreading, writing_audit & automatic checks. Local, zero network, zero LLM.