search-lit

90 / 100 · Low risk

Fine to try. Some of what it can do is expected: a research skill usually looks things up on the internet.

By Aperivue/medsci-skills (GitHub) · research · 379 stars · scanned at commit e0ea3b0

Use when finding papers or building a reference list. Searches PubMed, Semantic Scholar and bioRxiv/medRxiv, includes only references verified through an API, and generates BibTeX. Auditing an existing reference list is /verify-refs.

Works with any agent that supports SKILL.md skills.

What this skill can do

Runs commands on your computer

The author does not mention this.

Found in 4 places.

skills/search-lit/SKILL.md, line 37EUTILS="${CLAUDE_SKILL_DIR}/references/pubmed_eutils.sh"
skills/search-lit/SKILL.md, line 130python3 "${CLAUDE_SKILL_DIR}/scripts/check_doi_record_match.py" --table 2_Screening/round3.tsv \
skills/search-lit/SKILL.md, line 147python3 "${CLAUDE_SKILL_DIR}/references/snowball.py" \

Show 1 more

skills/search-lit/SKILL.md, line 254ENGINE="${CLAUDE_SKILL_DIR}/../fulltext-retrieval/fetch_oa.py"

Connects to the internet

The author does not mention this. Expected for a research skill.

Found in 9 places.

skills/search-lit/references/pubmed_eutils.sh, line 52body=$(curl -sS -w '\n%{http_code}' -A "Mozilla/5.0 (${TOOL})" "$@")
skills/search-lit/references/snowball.py, line 32- Exit 0 only when every seed/direction answered in full. A failed fetch (network error, an
skills/search-lit/references/snowball.py, line 60import urllib.request

Show 6 more

skills/search-lit/references/snowball.py, line 98req = urllib.request.Request(url, headers={"User-Agent": "medsci-skills/snowball"})
skills/search-lit/references/snowball.py, line 99with urllib.request.urlopen(req, timeout=30) as resp: # noqa: S310 (trusted host)
skills/search-lit/references/snowball.py, line 333f" INCOMPLETE: {len(problems)} seed/direction fetch(es) failed or were truncated; "
skills/search-lit/scripts/check_doi_record_match.py, line 66import urllib.request
skills/search-lit/scripts/check_doi_record_match.py, line 136req = urllib.request.Request(url, headers={"User-Agent": ua, "Accept": "application/json"})
skills/search-lit/scripts/check_doi_record_match.py, line 138with urllib.request.urlopen(req, timeout=30) as r: # noqa: S310 - fixed https host

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'search-lit' ] || [ -L ~/.agents/skills/'search-lit' ]; then echo 'A skill folder named search-lit already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/Aperivue/medsci-skills' "$d" && git -C "$d" checkout --quiet 'e0ea3b0be3bf529aa0b94ee5fd8450e78848932c' -- 'skills/search-lit' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/search-lit' ~/.agents/skills/'search-lit' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'search-lit' ~/.claude/skills/'search-lit' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for Aperivue/medsci-skills shows the score of its lowest-scoring skill.

SkillTrust badge for Aperivue/medsci-skills

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/Aperivue/medsci-skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/Aperivue/medsci-skills/)

Score history

Date	Version	Score
2026-11-13	`e0ea3b0`	90
2026-11-07	`cc462bc`	100