Wiki › Project

Research Dossier

Project · agent skill · 2026

Research Dossier is a free, open-source agent skill that turns a set of papers into a documented, visual, citation-checked literature review. It is the third step of the Research Suite, after Paper Scout finds the papers and Claim Conflict Finder maps where they disagree.

How it works

The agent writes the synthesis: the answer to the question, key takeaways, themes, debates, open questions and an annotation for each paper. It saves this to synthesis.json and cites papers only by key, as [@key]. A Python script, scripts/dossier.py, then builds the review:

  • Checks every citation against papers.json, and refuses to build if any key is unknown or typed by hand.
  • Numbers citations in reading order and builds an APA-style annotated bibliography.
  • Draws charts as inline SVG:
    • papers per year, with preprints marked;
    • the top venues;
    • papers per theme.
  • Adds the debates and evidence table from Claim Conflict Finder when they are present.
  • Records the search strings, sources, screening counts and excluded papers, so the review can be reproduced.

Outputs

FileUse
dossier.htmlThe report: one offline file, light and dark themes, table of contents, prints cleanly to PDF
dossier.mdNumbered citations and a reference list, to paste into Word or Google Docs
dossier.pandoc.md[@key] citations for Pandoc, so the review can be rendered in any citation style
references.bibEvery cited and included paper

The script makes no network requests and writes only inside its output folder. The repository includes the real run on galaxy merger histories used across the suite: 114 papers from OpenAlex and arXiv.

See also

In the knowledge graph

Research Dossier and the 10 things it is linked to. Open any dot for its page, or explore it in the full graph.

When
2023202420252026
Oct 2026 · 6 commits

As data

Everything on this page is read from triples in the knowledge graph. These are the 23 it states about Research Dossier, and 3 more its ontology implies; the console runs SPARQL over the whole graph, here in your browser.

Download
@prefix id: <https://ask.chaipat.cc/id/> .
@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
@prefix cj: <https://ask.chaipat.cc/ns#> .
@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .
@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .

id:ResearchDossier
    a cj:Project ;
    rdfs:label "Research Dossier" ;
    cj:description "Agent skill that turns a set of papers into a documented, visual, citation-checked literature review." ;
    cj:context id:OpenSource ;
    cj:repository "https://github.com/AppleBoiy/research-dossier"^^xsd:anyURI ;
    cj:firstCommit "2026-10-27"^^xsd:date ;
    cj:lastCommit "2026-10-27"^^xsd:date ;
    cj:commitCount 6 ;
    cj:kind "agent skill" ;
    cj:license "MIT" ;
    cj:theme id:ThemeAgentSkills , id:ThemeResearchTools ;
    cj:uses id:Python , id:AgentSkillsStd ;
    cj:tier 2 ;
    cj:integrates id:OpenAlex , id:arXiv ;
    cj:partOf id:ResearchSuite ;
    cj:mentions id:ClaimConflictFinder , id:PaperScout ;
    cj:article "https://ask.chaipat.cc/wiki/ResearchDossier"^^xsd:anyURI ;
    cj:activeIn id:Y2026 ;
    cj:activity _:b140 .