agentsclimarketplace
Sign in

Research briefing

Skill papersflow-ai/papersflow-skills/skills/research-briefing

Build a focused literature and citation briefing from PapersFlow. Use when the user wants paper search, citation verification, related-paper discovery, or citation graph exploration.From its SKILL.md

Install
npx -y skills add papersflow-ai/papersflow-skills --skill research-briefing

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.8 KB, 577 tokens by cl100k_base, as published. Nobody here has run it

Research Briefing

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."

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most research analysis skills give in 577 tokens

Counted across 1,213 of the 2,113 authors here whose files we hold, read 2026-09-06

  • Cite sources for every important claimin 47 of 1213, across 38 files
  • Separate facts from inferences and recommendationsin 21 of 1213, across 12 files
  • Write findings to a markdown filein 19 of 1213
  • Label every insight with a confidence levelin 18 of 1213, across 8 files
  • Read product marketing context before asking questionsin 18 of 1213, across 8 files
  • Rank themes by frequency and intensityin 16 of 1213, across 6 files
  • Establish research mode before proceedingin 16 of 1213, across 6 files
  • Segment survey responses by customer tier or tenurein 16 of 1213, across 6 files
  • Categorize support tickets before analyzingin 16 of 1213, across 6 files
  • Weight research sources from the last twelve monthsin 16 of 1213, across 6 files
  • Use at least five data points per segmentin 15 of 1213, across 5 files
  • Extract verbatim quotes for all research findingsin 15 of 1213, across 5 files

Said here and by no other author read

  • Resolve the user target topic or paper
  • Use search_literature for broad discovery
  • Verify citations using provided identifiers
  • Use find_related_papers for nearby work
  • Use get_citation_graph for network views
  • Use get_paper_neighbors for grouped lists

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.