luffysolution-svg/obsidian-vault-mcp/compare-papers

Claude Code and agent skill by luffysolution-svg/obsidian-vault-mcp

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Compare a user-selected set of papers across explicit methods, mechanisms, results, conditions, assumptions, or limitations. Use for bounded multi-paper comparisons, not open-ended corpus discovery or a general literature review.

Install

npx vskill@latest install luffysolution-svg/obsidian-vault-mcp/compare-papers

SKILL.md

Compare papers

<!-- ovm:skill-managed:start -->

Read comparison dimensions before building the matrix. When the user asks to save the comparison, also read the complete literature-review output contract before constructing the write call.

  1. Confirm the paper set and preserve any set supplied by the user.
  2. Extract the requested comparison dimensions; do not replace them with defaults.
  3. Use literature_retrieve across the set, then call literature_paper_read in targeted mode only for unresolved cells.
  4. Normalize terms, units, baselines, conditions, sample definitions, and assumptions.
  5. Mark every matrix cell as directly comparable, qualitatively comparable, not comparable, or missing.
  6. Synthesize agreements, differences, conflicts, and gaps across papers instead of stacking summaries.
  7. Answer in chat unless the user requests persistence.
  8. When saving, use literature_analysis_write with review mode comparative, skillName: compare-papers, and skillVersion: "1.0.0"; preview with dry-run, inspect it, then commit the same fields and managed content.

Never infer comparability from similar terminology alone. Do not invent missing values, conditions, citations, or causal explanations.

<!-- ovm:skill-managed:end -->

User Customizations

Add local comparison conventions below this line.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/luffysolution-svg/obsidian-vault-mcp/compare-papers/badge)](https://verified-skill.com/skills/luffysolution-svg/obsidian-vault-mcp/compare-papers)

Something wrong with this skill or its page? Tell us.