Research Briefing

Build a focused literature and citation briefing from PapersFlow. Use when the user wants paper search, citation verification, related-paper discovery, or ci...

Security Scan

The skill's instructions and requirements are internally consistent with its stated purpose (paper search, citation verification, and graph exploration) and it is instruction-only with no extra privileges, but there is limited provenance and an unclear dependency on a hosted 'papersflow-mcp' server that may or may not need credentials.

Purpose & Capability

The name/description (research briefing from PapersFlow) matches the SKILL.md workflow: search_literature, verify_citation, find_related_papers, citation graph operations and fetch. Nothing requested (no env vars, no binaries) contradicts the described functionality.

Instruction Scope

Runtime instructions stay on-topic: they tell the agent which PapersFlow tools to call for each user intent, how to structure outputs, and explicitly avoid guessing node ids. They do not instruct reading arbitrary files, environment variables, or transmitting data to unrelated endpoints.

Install Mechanism

No install specification and no code files — this is instruction-only, which minimizes disk/code install risk.

Credentials

The SKILL.md references a hosted 'papersflow-mcp' server but the skill declares no required environment variables or credentials. This can be fine if the server is public, but it could also indicate an omission (API key or endpoint not declared). Confirm whether PapersFlow access requires authentication or special endpoints.

Persistence & Privilege

always:false and no install-time persistence. The skill is user-invocable and allows autonomous invocation (platform default) but requests no elevated or persistent system privileges.

Assessment

This skill appears to do what it says: guide literature search and citation-graph queries using PapersFlow tools, and it does not request extra system access. Before installing, verify whether the referenced 'papersflow-mcp' server is public or requires an API key/credentials (the skill declares none). Also consider the provenance risk: the skill has no homepage and an opaque owner ID — if you plan to send private or unpublished text to the service, confirm the service's privacy policy and whether you need an explicit API key or trusted endpoint.

Use this skill when a user wants a high-signal research briefing grounded in the hosted papersflow-mcp server.

Workflow

1. Resolve the user's target topic, title, DOI, or seed paper.
2. Start with search_literature for broad discovery.
3. Use verify_citation when the user gives a citation string, DOI, URL, PubMed ID, arXiv ID, or uncertain bibliographic reference.
4. Use find_related_papers when the user wants nearby work around a seed paper.
5. Use get_citation_graph when the user wants a graph view with references, incoming citations, and optionally similar papers.
6. Use get_paper_neighbors when the user wants a one-hop grouped view instead of a graph-first view.
7. Use expand_citation_graph only after you already have seed node ids from a previous graph result.
8. Use fetch when the user wants a richer single-paper record after search or graph exploration.

Output Style

• Prefer short grouped sections over long prose.
• Include paper titles, years, identifiers, and why they matter.
• If the user asked for a graph-oriented answer, explicitly distinguish:
  • references
  • later citations
  • similar papers
• If the graph result looks noisy, say so instead of pretending the neighborhood is authoritative.

Tool Guidance

Use search_literature

Use for:

• topic exploration
• early-stage paper discovery
• short lists of candidate seed papers

Use verify_citation

Use for:

• checking a citation string
• normalizing a DOI or paper URL
• producing a reliable paper identifier before deeper exploration

Use get_citation_graph

Use for:

• seed-centered graph exploration
• showing how a paper connects to prior and later work

Prefer this when the user explicitly asks for a graph, network, map, or influence chain.

Use get_paper_neighbors

Use for:

• concise grouped neighbors
• "show me the references / citations / similar papers" requests

Prefer this over the graph tool when the user cares more about grouped lists than graph structure.

Use expand_citation_graph

Use only when:

• you already have valid node ids from a previous graph result
• the user wants to grow the graph one hop farther

Do not guess node ids.

Examples

• User asks: "Find five strong papers on retrieval-augmented generation evaluation and tell me which one to start with."
• User asks: "Verify this citation and give me a normalized version."
• User asks: "Show me the citation graph around Attention Is All You Need."
• User asks: "Expand the graph from these two node ids and tell me where the important branches are."