# Send Research Paper Kb to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "research-paper-kb", "name": "Research Paper Kb", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/IlkhamFY/research-paper-kb", "canonicalUrl": "https://clawhub.ai/IlkhamFY/research-paper-kb", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/research-paper-kb", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=research-paper-kb", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-07T17:22:31.273Z", "expiresAt": "2026-05-14T17:22:31.273Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentDisposition": "attachment; filename=\"afrexai-annual-report-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/research-paper-kb" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/research-paper-kb", "downloadUrl": "https://openagent3.xyz/downloads/research-paper-kb", "agentUrl": "https://openagent3.xyz/skills/research-paper-kb/agent", "manifestUrl": "https://openagent3.xyz/skills/research-paper-kb/agent.json", "briefUrl": "https://openagent3.xyz/skills/research-paper-kb/agent.md" } } ``` ## Documentation ### research-paper-kb Persistent research paper knowledge base for AI agents. Ingest any paper (arXiv URL, DOI, or title) and extract structured intelligence into a permanent PAPERS.md knowledge base that survives across sessions. Never lose context on a paper again. ### Trigger Conditions Use this skill when the user: Pastes an arXiv URL (e.g. https://arxiv.org/abs/2310.12345) Pastes a DOI (e.g. 10.1038/s41586-024-07156-8) Says "add this paper to my KB" / "track this paper" / "save this paper" Says "what do we know about [paper title]" Says "update my paper KB" / "scan my PAPERS.md" Says "show me the papers I'm tracking" / "what papers have I saved" ### What This Skill Does Fetches the paper abstract, metadata, and key sections Extracts structured intelligence (method, gap, threat level, overlap) Generates a clean BibTeX entry Appends a structured entry to PAPERS.md in the workspace Updates MEMORY.md with a pointer so future sessions know the KB exists Works across sessions — the knowledge base is a file, not context ### Step 1: Identify the Paper Accept any of: arXiv URL: https://arxiv.org/abs/XXXX.XXXXX arXiv ID: 2310.12345 or 2310.12345v2 DOI: 10.XXXX/... Title string: look up via Semantic Scholar API Normalize to arXiv ID or DOI before proceeding. ### Step 2: Fetch Paper Metadata For arXiv papers — fetch the abstract page: https://arxiv.org/abs/ Extract: title, authors, date, abstract, subject categories. Also fetch the Semantic Scholar API for structured metadata: https://api.semanticscholar.org/graph/v1/paper/arXiv:?fields=title,authors,year,abstract,tldr,citationCount,influentialCitationCount,fieldsOfStudy For DOI papers — use Semantic Scholar: https://api.semanticscholar.org/graph/v1/paper/?fields=title,authors,year,abstract,tldr,citationCount,influentialCitationCount,externalIds For title lookup: https://api.semanticscholar.org/graph/v1/paper/search?query=&fields=title,authors,year,abstract,externalIds&limit=1 ### Step 3: Extract Structured Intelligence From the abstract and any available full text, extract: FieldWhat to ExtractMethodCore technical approach or contribution (1-2 sentences)Gap they claimWhat problem/limitation they say they're solvingKey resultsMain quantitative or qualitative outcomeOverlap with user's workAsk the user if context is unclear; or infer from prior PAPERS.md entries and MEMORY.mdThreat level1-5 scale: how much does this threaten the user's research? (1=unrelated, 5=directly competing)Citation countFrom Semantic ScholarRelated papersUp to 3 highly-cited related papers from the same fetch Threat level guide: 1 — Unrelated field, no overlap 2 — Adjacent method, different application 3 — Similar approach, different dataset/domain 4 — Direct competition, overlapping claims 5 — Near-identical work, same target problem ### Step 4: Generate BibTeX Generate a clean BibTeX entry. Format: For arXiv: @article{, title = {}, author = { and and ...}, journal = {arXiv preprint arXiv:}, year = {}, url = {https://arxiv.org/abs/}, note = {arXiv:} } For published paper: @article{, title = {}, author = { and and ...}, journal = {}, year = {}, doi = {}, url = {https://doi.org/} } BibTeX key convention: FirstAuthorLastNameYearFirstContentWord (e.g., Smith2024diffusion) ### Step 5: Write to PAPERS.md Check if PAPERS.md exists in the workspace root. If not, create it with the header: # PAPERS.md — Research Paper Knowledge Base > Auto-maintained by the \`research-paper-kb\` skill. Add papers with: "add this paper to my KB" > Last updated: --- Append (never overwrite) the following entry template: ## []() **Added:** **Authors:** , , ... **Venue:** **Citations:** (Semantic Scholar) **Threat Level:** <1-5> — ### Method <1-2 sentence description of the core technical contribution> ### Gap They Claim ### Key Results
### Overlap With My Work ### Notes ### BibTeX \`\`\`bibtex ### Step 6: Update MEMORY.md After writing to PAPERS.md, append or update the PAPERS.md pointer in \`MEMORY.md\`: Find or create a section \`## Research Paper KB\`: \`\`\`markdown ## Research Paper KB - PAPERS.md exists in workspace root — papers tracked as of - Latest addition: (/5) - Run \`research-paper-kb\` to add more papers If the section already exists, update the count and latest addition line. ### Step 7: Confirm to User Reply with a summary: ✅ Added to PAPERS.md **[Paper Title]** () - Authors: ... - Threat level: X/5 — - BibTeX key: \`AuthorYearWord\` PAPERS.md now has N papers. Run \`show me my papers\` to review. ### Query Mode: "Show Me My Papers" When the user asks to review their paper KB: Read PAPERS.md Summarize: total count, highest threat-level papers, recently added Optionally filter by threat level, topic, or year Offer to export BibTeX for all papers: collect all @article{...} blocks and present as a code block ### Query Mode: "What Do We Know About X?" When the user asks about a specific paper or topic: Search PAPERS.md for matching title/author/keywords Return the structured entry If not found, offer to add it: "This paper isn't in your KB yet. Want me to add it?" ### Edge Cases SituationHandlingarXiv paper not foundTry Semantic Scholar title search; if still not found, ask user to confirm titleDOI behind paywallFetch abstract from DOI.org metadata (https://doi.org/ with Accept: application/json); note "full text unavailable"Paper already in PAPERS.mdDetect by title/arXiv ID match; offer to update notes or threat level insteadUser doesn't know their research areaAsk: "What's your research focus? I'll use this to assess overlap." Store in MEMORY.mdSemantic Scholar rate limitFall back to arXiv API: http://export.arxiv.org/api/query?id_list= ### Integration With Other Skills This skill works best alongside: citation-management — for full BibTeX workflow and PubMed/Google Scholar search biorxiv-database — for biology/life-science preprints (use to find papers to add) cs-research-methodology — for identifying gaps and research proposals from your KB proactive-research (ClaWHub) — can feed new papers into this KB automatically ### Files Modified FileActionPAPERS.mdAppend new entry (create if missing)MEMORY.mdUpdate ## Research Paper KB section Never modifies: SOUL.md, USER.md, AGENTS.md, TOOLS.md, or any project files. ### Example Interaction User: "Add this to my KB: https://arxiv.org/abs/2310.06825" Agent: Fetches arXiv 2310.06825 → "Mistral 7B" by Jiang et al. Fetches Semantic Scholar metadata (12k citations) Extracts: method = grouped-query attention + sliding window; gap = efficient 7B model Assesses threat level vs user's work (reads MEMORY.md for context) Generates BibTeX key Jiang2023mistral Appends structured entry to PAPERS.md Updates MEMORY.md Replies: "✅ Added Mistral 7B (threat: 2/5 — efficient inference, different from your focus on X)" ### Metadata name: research-paper-kb version: 1.0.0 author: category: Academic & Research tags: [research, papers, arxiv, bibtex, knowledge-base, literature, academic, persistent-memory] summary: Persistent cross-session knowledge base for research papers. Ingest arXiv/DOI → extract method/gap/threat level → append to PAPERS.md. Never lose paper context again. requires: [] ## Trust - Source: tencent - Verification: Indexed source record - Publisher: IlkhamFY - Version: 1.0.0 ## Source health - Status: healthy - Source download looks usable. - Yavira can redirect you to the upstream package for this source. - Health scope: source - Reason: direct_download_ok - Checked at: 2026-05-07T17:22:31.273Z - Expires at: 2026-05-14T17:22:31.273Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/research-paper-kb) - [Send to Agent page](https://openagent3.xyz/skills/research-paper-kb/agent) - [JSON manifest](https://openagent3.xyz/skills/research-paper-kb/agent.json) - [Markdown brief](https://openagent3.xyz/skills/research-paper-kb/agent.md) - [Download page](https://openagent3.xyz/downloads/research-paper-kb)