Research·v2.5.0

Paper Search Pro Agent Skill

Name: Paper Search Pro
Author: O0000-code

Find academic papers across up to 7 sources (OpenAlex, Semantic Scholar, CrossRef, PubMed, arXiv, plus native-Chinese NSSD and yiigle)…

Install this skill Read the source first Free Written by O0000-code

Context cost: 167.8k tokensestimated from the bundle, loaded when it triggers
Bundle: 112 of 198 fileshanded out here; the rest is at its source
Licence: Apache-2.0the author’s own terms
Last change: —v2.5.0
Servers it uses: Noneruns standalone

What it does

Find academic papers across up to 8 sources (OpenAlex / Semantic Scholar / CrossRef / PubMed / arXiv for English, OpenReview for AI venues, plus native-Chinese retrieval via NSSD 国家哲社文献中心 + yiigle 中华医学期刊) with adjustable depth — Quick scan (5 min) to Audit prep (3 hr). Use when the user wants to find papers, run a literature search, gather references, scope a research topic, search Chinese-language / 中文原生 literature (中文文献/中文核心/CSSCI/C刊/国内研究/国内文献/中华××期刊/心理学报/经济研究), or filter results by journal tier (中科院分区/一区/几区, Q1, JCR/SJR quartile, 影响因子/impact factor, 期刊分区, 顶刊/top journal, '按分区筛'), or…

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

literature-searchopenalexprismapubmed

Filed under

Research

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md67.1 kB · preview

--- name: paper-search-pro license: Apache-2.0 allowed-tools: Bash, Read, Write, Edit, Glob, Grep, Task metadata: author: Bo version: 2.5.0 vendored-from: futurehouse/paper-qa (Apache 2.0) ---

12# paper-search-pro

14Multi-source literature search with adjustable depth. Four tiers, five data sources orchestrated by you (the main agent). Python helpers handle deterministic work; LLM classification is delegated to parallel Inline SubAgents — no external API key required.

16## When to use this skill

18- User wants to find academic papers / 找文献 / 论文搜索

19- User is preparing a literature review, systematic review (SR), scoping review, or meta-analysis

20- User wants to scope research on a topic for a thesis / proposal / coursework / news story

21- User asks "what research exists on X" / "find me papers about Y"

22- User uploads a query that suggests literature gathering (PICO, SPIDER, MeSH, RCT, etc.)

24## When NOT to use

26- User wants to **read** a specific paper (use PDF reader / download tool)

27- User wants to **summarize** a single known paper (use a summarizer)

28- User wants to **download** PDFs given DOIs (use paper-downloader-portable)

29- User already has a literature set and wants to write a review (use literature-set-review / factor-outcome-review)

30- User wants concept explanation, not papers ("what is prospect theory" → just answer)

This is a preview of SKILL.md. Download or install the skill to get the whole thing.

In the file

SKILL.md9,226 words

Files112

LicenceApache-2.0

Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈430

always loaded

The name and description, so the model knows the skill exists and when to reach for it.

167,395

on trigger

The instruction body and 111 supporting files, read only when the skill fires.

83.9%

of a 200k window

Ten skills this size would not fit in the window together.

050k100k150k200k context window

167.8k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

It asks the agent to write files, using whatever file access your client already has. Whether it reaches the network is not declared.

What it asks for

Writes filesyes

Network accessnot declared

Read from the allowed-tools line of this skill’s own SKILL.md. It also asks for Bash, which could do either, so what is not named there is not ruled out. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

If this is not it

323 other skills in Research

What is in the bundle

The download carries 112 of the 198 files in its source folder; the list here names 112 files, 1838.9 kB on disk. Mostly text — the instructions the model reads — with 61 scripts in it that your client would run only if the instructions tell it to. The other 86 are not in the download, nor are at least 14 files of types a skill download does not carry — listed after these, with why.

SKILL.md67.1 kB
CLAUDE.md4.0 kB
LICENSE.txt11.4 kB
NOTICE.md2.3 kB
README.md13.6 kB
README.zh.md13.3 kB
THIRD_PARTY.md5.7 kB
assets/default_config.yaml7.3 kB
assets/md_template.md.jinja5.9 kB
evals/evals.json1.6 kB
references/agent_mode.md49.1 kB
references/arxiv_helper_cheatsheet.md7.3 kB
references/citation_chasing.md5.2 kB
references/classifier_subagent_prompt.md5.1 kB
references/crossref_helper_cheatsheet.md6.7 kB
references/error_handling.md9.4 kB
references/journal_metrics.md14.0 kB
references/openalex_helper_cheatsheet.md9.1 kB
references/output_files.md8.4 kB
references/prisma_s_checklist.md8.4 kB
references/pubmed_helper_cheatsheet.md7.1 kB
references/query_planner.md14.3 kB
references/rcs_rubric.md6.9 kB
references/runtime_bootstrap.md4.9 kB
references/setup.md11.6 kB
references/source_routing.md29.0 kB
references/ss_helper_cheatsheet.md8.4 kB
references/stop_decision.md6.9 kB
references/summary_writer.md5.7 kB
references/tier_decision.md5.3 kB
scripts/__init__.py0.1 kB
scripts/agent_search.py121.6 kB
scripts/arxiv_helper.py16.6 kB
scripts/config.py3.1 kB
scripts/crossref_helper.py22.5 kB
scripts/data_materialization.py36.9 kB
scripts/detect_language.py2.6 kB
scripts/discovery_curve.py21.2 kB
scripts/federated_kg_resolver.py30.0 kB
scripts/generate_exports.py13.9 kB
scripts/html_renderer_webartifacts.py18.3 kB
scripts/journal_rank.py37.9 kB
scripts/md_report.py14.3 kB
scripts/nssd_helper.py26.6 kB
scripts/openalex_helper.py60.9 kB
scripts/prisma_s_logger.py26.2 kB
scripts/pubmed_helper.py15.2 kB
scripts/quota_guard.py11.4 kB
scripts/rank_filter.py19.6 kB
scripts/rank_intent.py27.0 kB
scripts/rcs_parser.py13.7 kB
scripts/requirements.txt1.0 kB
scripts/semantic_cache.py5.5 kB
scripts/sjr_helper.py23.7 kB
scripts/ss_helper.py46.7 kB
scripts/types.py18.9 kB
scripts/yiigle_helper.py15.6 kB
tests/__init__.py0.1 kB
tests/test_agent_rank.py18.0 kB
tests/test_agent_search.py56.2 kB
tests/test_arxiv_helper.py10.3 kB
tests/test_crossref_helper.py17.7 kB
tests/test_data_materialization_rank.py9.9 kB
tests/test_detect_language.py2.4 kB
tests/test_federated_kg_resolver.py27.3 kB
tests/test_journal_rank.py22.0 kB
tests/test_modules_smoke.py2.4 kB
tests/test_nssd_helper.py29.0 kB
tests/test_openalex_helper.py27.7 kB
tests/test_prisma_s_logger.py2.3 kB
tests/test_pubmed_helper.py11.7 kB
tests/test_quota_guard.py10.6 kB
tests/test_rank_filter.py17.3 kB
tests/test_rank_intent.py27.2 kB
tests/test_rcs_parser.py6.7 kB
tests/test_sjr_helper.py29.4 kB
tests/test_ss_helper.py33.8 kB
tests/test_yiigle_helper.py15.2 kB
assets/benchmark_queries/custom_zh_queries.json5.9 kB
assets/benchmark_queries/litsearch_subset.json4.8 kB
assets/benchmark_queries/sparbench_subset.json3.1 kB
scripts/vendored/__init__.py0.1 kB
scripts/vendored/LICENSE-paperqa.txt11.4 kB
scripts/vendored/README-vendored.md8.7 kB
scripts/vendored/tenacity_retry.py9.2 kB
assets/webartifacts_app/paper-report/components.json0.4 kB
assets/webartifacts_app/paper-report/eslint.config.js0.6 kB
assets/webartifacts_app/paper-report/index.html0.3 kB
assets/webartifacts_app/paper-report/package.json2.6 kB
assets/webartifacts_app/paper-report/pnpm-lock.yaml232.4 kB
assets/webartifacts_app/paper-report/postcss.config.js0.1 kB
assets/webartifacts_app/paper-report/README.md2.4 kB
assets/webartifacts_app/paper-report/tailwind.config.js2.2 kB
assets/webartifacts_app/paper-report/tsconfig.app.json1.1 kB
assets/webartifacts_app/paper-report/tsconfig.json0.2 kB
assets/webartifacts_app/paper-report/tsconfig.node.json0.6 kB
assets/webartifacts_app/paper-report/vite.config.ts0.2 kB
assets/webartifacts_app/paper-report/public/favicon.svg9.5 kB
assets/webartifacts_app/paper-report/public/icons.svg5.0 kB
assets/webartifacts_app/paper-report/src/App.css0.1 kB
assets/webartifacts_app/paper-report/src/App.tsx12.8 kB
assets/webartifacts_app/paper-report/src/main.tsx1.2 kB
assets/webartifacts_app/paper-report/src/assets/react.svg4.1 kB
assets/webartifacts_app/paper-report/src/assets/vite.svg8.7 kB
assets/webartifacts_app/paper-report/src/lib/format.ts2.1 kB
assets/webartifacts_app/paper-report/src/lib/i18n.ts38.8 kB
assets/webartifacts_app/paper-report/src/lib/mock-data.ts66.2 kB
assets/webartifacts_app/paper-report/src/lib/normalize.ts7.7 kB
assets/webartifacts_app/paper-report/src/lib/prisma-titles.ts3.2 kB
assets/webartifacts_app/paper-report/src/lib/safari-detect.ts1.6 kB
assets/webartifacts_app/paper-report/src/lib/types.ts8.2 kB
assets/webartifacts_app/paper-report/src/lib/utils.ts0.2 kB

Not in the download

The first 100 are named here, those the skill reads first. Too big is over our 2 MB file limit, too deep is past six folders and not carried is a type a skill download does not hold. Marked read: its SKILL.md or scripts name the file, so without it the skill works only in part. Take them from its source.

assets/webartifacts_app/paper-report/src/components/hero/FilterBar.tsxread · too deep
docs/index.htmlread · 7.2 MB, too big
assets/webartifacts_app/paper-report/bundle.htmlread · 7.2 MB, too big
assets/webartifacts_app/paper-report/src/index.cssread · 6.2 MB, too big
.github/og-image.pngnot carried
.gitignorenot carried
.skillignorenot carried
assets/webartifacts_app/paper-report/.gitignorenot carried
assets/webartifacts_app/paper-report/.parcelrcnot carried
assets/webartifacts_app/paper-report/src/assets/hero.pngnot carried
assets/webartifacts_app/paper-report/src/components/adapters/KickerAccordion.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/adapters/KickerAlert.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/adapters/SearchInput.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/adapters/SegmentedToggle.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/adapters/SimpleTooltip.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/audit/audit-utils.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/audit/AuditTab.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/audit/ComplianceSummary.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/audit/PhaseGroup.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/audit/PrismaRow.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/audit/StatusDot.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/chrome/LayoutSwitcher.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/chrome/thumbs/Thumbs.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/hero/SliderWithZones.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/hero/TierStrip.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/hero/tops/DocumentTop.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/hero/tops/EditorialTop.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/hero/tops/SwissTop.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/methods/CitationScatter.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/methods/DiscoveryCurve.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/methods/MethodologyAccordion.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/methods/MethodsTab.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/methods/RcsHistogram.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/methods/SectionHeader.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/methods/Stat.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/methods/TierAllocation.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/methods/TopicsTreemap.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/methods/useInsights.tstoo deep
assets/webartifacts_app/paper-report/src/components/methods/YearBarChart.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/papers/JournalRank.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/papers/PaperCardItem.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/papers/PaperList.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/papers/PaperRowCatalog.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/papers/PaperRowIndex.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/papers/PaperRowIndexHeader.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/papers/PaperSheet.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/papers/QuickJump.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/papers/TierDot.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/papers/TierHeader.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/papers/ZoneFilter.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/accordion.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/alert.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/aspect-ratio.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/avatar.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/badge.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/breadcrumb.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/button.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/calendar.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/card.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/carousel.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/chart.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/checkbox.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/collapsible.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/command.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/context-menu.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/dialog.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/drawer.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/dropdown-menu.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/form.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/hover-card.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/input.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/label.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/menubar.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/navigation-menu.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/popover.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/progress.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/radio-group.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/resizable.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/scroll-area.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/select.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/separator.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/sheet.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/skeleton.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/slider.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/sonner.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/switch.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/table.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/tabs.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/textarea.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/toggle.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/toggle-group.tsxtoo deep
assets/webartifacts_app/paper-report/src/components/ui/tooltip.tsxtoo deep
assets/webartifacts_app/paper-report/src/fonts/geist-mono.woff2not carried
assets/webartifacts_app/paper-report/src/fonts/geist-sans.woff2not carried
docs/screenshots/audit.pngnot carried
docs/screenshots/audit-zh.pngnot carried
docs/screenshots/discovery-report.pngnot carried
docs/screenshots/discovery-report-zh.pngnot carried
docs/screenshots/findings.pngnot carried
docs/screenshots/findings-zh.pngnot carried

What is not in it

A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 61 scripts beside the text, so the download is 112 files — not the whole of its source: at least 100 files are left out, and the skill reads 4 of them. The first 100 are listed under the files, with why. The Apache-2.0 licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Paper Search Pro · 167.8k tokens when loaded · macOS, Linux
mkdir -p .claude/skills && t=$(mktemp -d) &&
  curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/paper-search-pro/bundle.tar.gz &&
  tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/paper-search-pro" ] &&
  { [ ! -e .claude/skills/paper-search-pro ] || { mv .claude/skills/paper-search-pro "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } &&
  mv "$t/paper-search-pro" .claude/skills/ && echo "Installed .claude/skills/paper-search-pro"

On Windows, or any OS with Node 20+

npx mcprush@latest skill add o0000-code/paper-search-pro

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/paper-search-pro/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/paper-search-pro/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/paper-search-pro" ] && { [ ! -e ~/.claude/skills/paper-search-pro ] || { mv ~/.claude/skills/paper-search-pro "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/paper-search-pro" ~/.claude/skills/ && echo "Installed ~/.claude/skills/paper-search-pro" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/paper-search-pro/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. Not in this download: at least 100 files of its source, 4 of them read by its SKILL.md or scripts (the list, and why). Take them from its source.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/

Claude DesktopCustomize › Skills

ChatGPTSkills › Create › Upload

Cursor.cursor/skills/

VS Code.github/skills/

Codex CLI.agents/skills/

Gemini CLI.gemini/skills/

Grok Build.grok/skills/

Microsoft CopilotSkills › Upload a skill

PerplexityComputer › Skills › Upload a skill

DeepSeek Harness.dsh/skills/

Zed.agents/skills/

Devin Desktop.devin/skills/

Windsurf (legacy).windsurf/skills/

OpenAI Agents SDKInstructions or sandbox Skills

HTTP / APIa request parameter

This release

Version2.5.0

Publishedno release date on file

PriceFree

Referenceo0000-code/paper-search-pro

Versions

v2.5.0 is what is on the shelf; no release here carries a date. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v2.5.0

No earlier releases have been published to the marketplace.

Pinning

The install command always fetches the release that is current the day you run it — v2.5.0 today — and cannot ask for an earlier one. The copy on your disk does not change until you run it again.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

O0000-code

Publishes on mcprush.

0 servers listed1 skill listednot claimed

Profile

Publisher

Servers0

Claim this skill