By fingerskier
Subagents for literature research — search PubMed, format citations, and synthesize a verified corpus into prose. Zero-install: uses public APIs, no bundled servers.
Converts a list of citation hits into formatted references — Markdown footnotes, a numbered bibliography, or BibTeX. Use after gathering sources, when you need them rendered in a consistent citation style.
Synthesizes a set of verified sources into coherent, cited prose — a literature-review section, background, or chapter draft. Use when you have a corpus of papers/notes and need an integrated narrative, not a summary of each one in isolation.
Searches PubMed for biomedical literature and returns structured citation hits. Use when you need papers on a topic, by an author, or matching specific terms — and want clean metadata (PMID, title, authors, journal, year, DOI), not a web page.
Subagents for literature research in Claude Code — search the literature, format the citations, and synthesize a verified corpus into prose.
Zero-install. No bundled servers and no API keys: the search agent talks to the public NCBI E-utilities API directly. Drop the plugin in and it works.
| Agent | Model | Tools | What it does |
|---|---|---|---|
pubmed-searcher | haiku | web | Searches PubMed via NCBI E-utilities; returns structured hits (PMID, title, authors, journal, year, DOI). |
citation-formatter | haiku | read-only | Turns hits into Markdown footnotes, a numbered bibliography, or BibTeX. |
literature-synthesizer | opus | read-only | Weaves a corpus of sources into integrated, cited prose — a review section or chapter draft. |
A typical flow: pubmed-searcher finds the papers → citation-formatter renders the references → literature-synthesizer writes the section.
Verifying that a cited source actually supports a claim? Use the
fact-checkeragent fromclaude-agents-core— it's the general-purpose tool for that, so this pack doesn't duplicate it.
claude plugin marketplace add fingerskier/claude-plugins
claude plugin install research-agents@fingerskier-plugins
Agents are routed to automatically when a request matches their description, or you can call one explicitly:
"Use pubmed-searcher to find recent randomized trials on vitamin D and bone density, then have citation-formatter give me BibTeX."
"Hand these 12 abstracts to literature-synthesizer and draft a background section on the mechanism."
Each agent lives in agents/<name>.md — YAML frontmatter declares the agent (name, routing description, model, tool allowlist) and the markdown body is its system prompt. See the subagents docs.
NCBI asks that automated E-utilities use stay under ~3 requests/second; these agents make only a handful of calls per task, well within that.
Issues and PRs welcome. New agents should stay general within the research domain (no project- or institution-specific coupling), declare the minimum tools they need, and pick a model that fits (search/format → haiku, synthesis → opus).
Apache-2.0 © 2026 Fingerskier
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub fingerskier/claude-plugins --plugin research-agentsExegetical theology research — rigorous, multi-perspective Biblical exegesis with historian, linguist, author, theologian, disciple, shepherd, numerology, and full research skills.
CAD modeling with build123d — create, inspect, and export parametric 3D models using Python.
Design electronic schematics and PCB layouts using SKiDL — create circuits with Python code, validate designs, and export to KiCad.
MIDI plugin for Claude Code — load, analyze, edit, and play MIDI files with musical intelligence
Runs jobs in Claude on a schedule
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Use this agent when creating user interfaces, designing components, building design systems, or improving visual aesthetics. This agent specializes in creating beautiful, functional interfaces that can be implemented quickly within 6-day sprints. Examples:\n\n<example>\nContext: Starting a new app or feature design
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research