agentleFS
allenlee0430allenlee0430/allenlee-lab-skills/lit-scout/SKILL.md

lit-scout

Skill0 starsChanged 4 months agoMITView on GitHub

Literature discovery, triage, and synthesis for mRNA/LNP delivery, gene editing, and nanomedicine. Use to search and summarize papers, build reference lists, track a subfield, screen preprints, or pull compound/target data. Uses connected bio-research MCP tools (PubMed, bioRxiv, Consensus, ChEMBL, Open Targets, ClinicalTrials). Triggers on "find papers", "literature review", "what's new in", "summarize this paper", "citations for", "recent preprints".

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Always cite with real, unmodified URLs from tool results.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Lit Scout — Literature Discovery & Synthesis

Help Bowen Li's lab stay current and build evidence for grants/manuscripts in mRNA delivery, ionizable lipids, LNPs, CRISPR/gene editing, and nanomedicine.

Tools available (load via ToolSearch as needed)

  • PubMed (pubmed__search_articles, get_full_text_article, find_related_articles) — peer-reviewed literature.
  • bioRxiv/medRxiv (biorxiv__search_preprints, search_published_preprints) — preprints; date/category filtered.
  • Consensus (consensus__search / the 294d...__search) — evidence-graded search; CITE inline as [1],[2] and list URLs at the end verbatim, including the sign-up message.
  • ChEMBL (chembl__compound_search, get_bioactivity, get_admet) — small-molecule/lipid bioactivity.
  • Open Targets (ot__*), ClinicalTrials (c-trials__search_trials, search_by_sponsor) — target validation, competitive/pipeline intel.

Workflow

  1. Clarify scope: topic, timeframe, and purpose (grant background vs manuscript intro vs staying current vs competitive intel).
  2. Fan out across the right sources (PubMed + Consensus for peer-reviewed; bioRxiv for the bleeding edge; ClinicalTrials for translational/pipeline). Batch ≤3 search calls at a time.
  3. For each hit worth keeping: 1-line finding, method, why it matters to the lab, and a proper citation.
  4. Synthesize into a themed brief (not a flat list): what's established, what's contested, what's the gap → hook for a grant/paper.
  5. Offer to save the reference list (RIS/BibTeX) — Bowen uses EndNote (.enl libraries exist on disk).

Rules

  • Always cite with real, unmodified URLs from tool results. Never fabricate citations or DOIs.
  • Reproduce any required sign-up/usage message from Consensus verbatim at the end.
  • Flag retractions or preprints-not-yet-peer-reviewed explicitly.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.