paper-navigator
Find, read, download, and locally cache academic papers. Disambiguate ambiguous queries, discover via keyword search / citation traversal / recommendations / arXiv monitoring / trending / GitHub search, evaluate (TLDR, citations, code, SOTA), read using a 3-level strategy, and save PDFs to a local library for offline reuse. Use when finding a specific paper, listing papers on a topic, tracking recent advances, finding a baseline with code, reading or downloading a paper by URL, searching the local PDF library, or collecting a corpus for survey/ideation. Trigger phrases include: find/search pap
npx skills add BioTender-max/awesome-bio-agent-skills --skill paper-navigator --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Paper Navigator Find and read academic papers. The skill routes by **intent** into three branches; cost should match intent. ## Core Principles (apply to every branch) These four rules override branch-specific instructions when they conflict — they exist because every paper-search failure mode reduces to one of them. 1. **Track history** — before each new search, recall queries already run and what they returned. Identical or near-identical queries waste budget; if a query returned nothing, change angle, not synonyms. 2. **Search what's missing, not what you know** — every query must map to an explicit information gap (see `references/search-principles.md` § "Gap Diagnosis"). Stacking broad terms ("deep learning survey trends future") dilutes the relevance signal and returns noise. 3. **Atomize multi-concept queries** — one query = one gap. Comparisons ("A vs B"), multi-property requests (mechanism + application), or year-spanning asks must be split into independent queries. The search engine cannot weigh two intents at once. 4. **Never hallucinate** — every factual claim (title, author, year, citation count) must come from a tool result. Do not fill in from training data, even f
- Core Principles (apply to every branch)
- Intent Router
- Branch 0 — LOCAL-FIRST (run before any external search)
- Branch 1 — POINT
- Branch 2 — LIST
- Branch 3 — ITERATIVE
- Tool Cheat Sheet
- No-S2-key Operating Mode ($S2APIKEY unset)
- Output Formats
- Reference Files
What does the paper-navigator skill do?
Find, read, download, and locally cache academic papers. Disambiguate ambiguous queries, discover via keyword search / citation traversal / recommendations / arXiv monitoring / trending / GitHub search, evaluate (TLDR, citations, code, SOTA), read using a 3-level strategy, and save PDFs to a local library for offline reuse. Use when finding a specific paper, listing papers on a topic, tracking recent advances, finding a baseline with code, reading or downloading a paper by URL, searching the local PDF library, or collecting a corpus for survey/ideation. Trigger phrases include: find/search pap
How do I install it?
Run `npx skills add BioTender-max/awesome-bio-agent-skills --skill paper-navigator --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From BioTender-max/awesome-bio-agent-skills, a repository with 144 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.