Literature Review
K-Dense-AI/scientific-agent-skills
Runs systematic, scoping or narrative literature reviews across PubMed, arXiv, bioRxiv and Semantic Scholar, with citation checks and Markdown or PDF output.
Routes literature searches through the PaperSeek launcher, picks suitable scholarly sources, parses JSON output and keeps API keys out of the chat.
Install PaperSeek Literature Search
$ npx skills add MingfengHong/paperseek --skill paperseek -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install MingfengHong/paperseek paperseek --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/MingfengHong/paperseek.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/paperseek .claude/skills/paperseek && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "paperseek" agent skill from https://github.com/MingfengHong/paperseek/tree/main/skills/paperseek into .claude/skills/paperseek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paperseek", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/MingfengHong/paperseek/tree/main/skills/paperseekType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add MingfengHong/paperseek --skill paperseek -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install MingfengHong/paperseek paperseek --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MingfengHong/paperseek.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/paperseek .agents/skills/paperseek && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "paperseek" agent skill from https://github.com/MingfengHong/paperseek/tree/main/skills/paperseek into .agents/skills/paperseek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paperseek", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add MingfengHong/paperseek --skill paperseek -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install MingfengHong/paperseek paperseek --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MingfengHong/paperseek.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/paperseek .cursor/skills/paperseek && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "paperseek" agent skill from https://github.com/MingfengHong/paperseek/tree/main/skills/paperseek into .cursor/skills/paperseek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paperseek", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/MingfengHong/paperseek.git --path skills/paperseek--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add MingfengHong/paperseek --skill paperseek -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install MingfengHong/paperseek paperseek --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MingfengHong/paperseek.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/paperseek .gemini/skills/paperseek && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "paperseek" agent skill from https://github.com/MingfengHong/paperseek/tree/main/skills/paperseek into .gemini/skills/paperseek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paperseek", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install MingfengHong/paperseek paperseekInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add MingfengHong/paperseek --skill paperseek -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/MingfengHong/paperseek.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/paperseek .github/skills/paperseek && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "paperseek" agent skill from https://github.com/MingfengHong/paperseek/tree/main/skills/paperseek into .github/skills/paperseek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paperseek", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add MingfengHong/paperseek --skill paperseek -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install MingfengHong/paperseek paperseek --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MingfengHong/paperseek.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/paperseek .opencode/skills/paperseek && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "paperseek" agent skill from https://github.com/MingfengHong/paperseek/tree/main/skills/paperseek into .opencode/skills/paperseek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paperseek", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
paperseek- GitHub stars
- 0
- Token cost
- ~1.6k tokens
- SKILL.md length
- 674 words
- Files
- 6 (incl. scripts, references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Routes literature searches through the PaperSeek launcher, picks suitable scholarly sources, parses JSON output and keeps API keys out of the chat.
- Works in 6 steps: Use OpenAlex as the default source… → For uncertain environments, run… → Run search with JSON output for machine… → …
- Searching for papers from a natural-language research question
- SKILL.md covers Reference Rules, Quick Self-Check, Core Workflows and Default Search Procedure, plus 3 more sections
- Runs Python scripts from its folder; calls python; needs LLM_API_KEY and OPENALEX_API_KEY
What it does
The skill bundles a self-contained Python runtime in scripts/, so core searches work even when the full PaperSeek package is missing; if the package is installed, the launcher hands off to it for the complete CLI and Web UI. The standalone runtime handles search, smoke, sources, doctor, config listing and history path using only the standard library. Sources include OpenAlex, arXiv, Semantic Scholar, PubMed, Crossref, WoS Starter and computer science top conferences, with Google Scholar available through Serper.
Three reference files cover management (install, doctor, smoke, config and secrets), source routing (which source fits and whether citation expansion applies) and the exact CLI contract. When a reference disagrees with the live CLI output, the agent trusts the CLI and reports that the reference may need an update. It starts uncertain environments with the doctor and sources commands, never asks you to paste API keys into chat, and avoids downloading paywalled PDFs.
When your agent uses it
- Searching for papers from a natural-language research question
- Checking whether PaperSeek and its sources are configured correctly
- Choosing between OpenAlex, arXiv, PubMed and other sources for a topic
- Exporting a ranked paper list or exploring a citation map
Example prompts
- “Find recent papers on retrieval-augmented generation using OpenAlex and give me the JSON results.”
- “Run the PaperSeek doctor check and tell me which sources are ready.”
- “Which source should I use for clinical trial papers on diabetes?”
Requirements
- Python to run the bundled launcher
- API keys for some sources, configured locally through environment variables
- Compatibility (from SKILL.md): Bundles a self-contained Python standard-library runtime for core OpenAlex/arXiv/Semantic Scholar/PubMed/computer science top-conference/Crossref/WoS literature search. The full PaperSeek package is optional and used automatically when installed.
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Use OpenAlex as the default source unless the user asks for another source or the task clearly needs preprints, biomedical literature, top…
- For uncertain environments, run paperseek doctor --json before searching.
- Run search with JSON output for machine parsing
- Parse ranked results. Prefer stable fields such as relevance_score, citation_count, venue, doi, url, abstract, and relevance_reason.
- Report search query, source, iteration count, result count, and the top ranked papers. Do not treat LLM relevance score as proof of quality.
- If the result set is poor, broaden or narrow the natural-language question and rerun. Do not fabricate missing DOI, authors, abstracts, or…
What it can do on your machine
Read from SKILL.md and the folder at commit ced3100. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 2 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
LLM_API_KEYOPENALEX_API_KEYWOS_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Compatibility
Bundles a self-contained Python standard-library runtime for core OpenAlex/arXiv/Semantic Scholar/PubMed/computer science top-conference/Crossref/WoS literature search. The full PaperSeek package is optional and used automatically when installed.
From compatibility in the SKILL.md frontmatter.
Context cost
PaperSeek Literature Search loads about 1.6k tokens when it runs, and up to ~5.3k if it reads all its reference files. Until then it costs about 109 tokens; SKILL.md has 674 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from MingfengHong/paperseek at commit ced3100, republished under its Apache-2.0 licence (© MingfengHong). 674 words, ~1,576 tokens.
Download SKILL.mdSave it as
.claude/skills/paperseek/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- paperseek
- description
- LLM literature-search workflow router for PaperSeek CLI and local Web UI. Use when users ask to search papers, find literature, run natural-language academic search, diagnose PaperSeek configuration, inspect PaperSeek source results, export ranked paper lists, or explore citation maps. Guides agents to call paperseek commands, parse JSON output, choose data sources, and avoid storing secrets or downloading paywalled PDFs.
- compatibility
- Bundles a self-contained Python standard-library runtime for core OpenAlex/arXiv/Semantic Scholar/PubMed/computer science top-conference/Crossref/WoS literature search. The full PaperSeek package is optional and used automatically when installed.
- license
- Apache-2.0
PaperSeek
You are using PaperSeek as an LLM-based literature search agent. This Skill includes a self-contained runtime under scripts/ and can run core literature search even when the PaperSeek Python package is not installed. When the package is installed, the launcher automatically delegates to the full CLI/Web/source implementation.
Reference Rules
- For install, Skill script launching,
doctor,smoke,config, health checks, and secrets handling, readreferences/management-layer.md. - For choosing OpenAlex, arXiv, Semantic Scholar, PubMed, Google Scholar through Serper, computer science top-conference, Crossref, or WoS Starter and deciding whether citation expansion applies, read
references/source-routing.md. - For exact CLI commands, output fields, JSON expectations, and stable command contracts, read
references/cli-contract.md. - If a reference conflicts with
paperseek --help,paperseek sources --json, orpaperseek doctor --json, trust the live CLI and report that the Skill reference may need an update.
Quick Self-Check
When the environment is uncertain, start with:
python skills/paperseek/scripts/paperseek.py doctor
python skills/paperseek/scripts/paperseek.py sourcesFor a minimal live source test:
python skills/paperseek/scripts/paperseek.py smoke --source openalex --query "machine learning" --jsonFor install guidance or full Web UI/citation-map features:
python skills/paperseek/scripts/paperseek.py --install-helpThe launcher skills/paperseek/scripts/paperseek.py first tries the full PaperSeek package. If that package is unavailable, it falls back to scripts/paperseek_skill_runtime.py, which implements standalone search, smoke, sources, doctor, config list/path/keys, and history path using only the Python standard library.
Do not ask the user to paste API keys into chat. Ask them to configure keys locally with environment variables, paperseek config set ..., or the Web UI session fields.
Core Workflows
| User intent | Workflow | First command |
|---|---|---|
| Find papers from a research question | Natural-language literature search | python skills/paperseek/scripts/paperseek.py search "QUESTION" --source openalex --json |
| Inspect whether PaperSeek is usable | Diagnostics | python skills/paperseek/scripts/paperseek.py doctor --json |
| Test a source with a small real query | Smoke check | python skills/paperseek/scripts/paperseek.py smoke --source openalex --query "machine learning" --json |
| Choose source and parameters | Source capability lookup | python skills/paperseek/scripts/paperseek.py sources --json |
| Start interactive UI | Local Web UI | paperseek-web after installing the full package |
Default Search Procedure
- Use OpenAlex as the default source unless the user asks for another source or the task clearly needs preprints, biomedical literature, top CS conference coverage, DOI registry metadata, or institution-backed WoS metadata.
- For uncertain environments, run
paperseek doctor --jsonbefore searching. - Run search with JSON output for machine parsing:
python skills/paperseek/scripts/paperseek.py search "open innovation and digital platforms" --source openalex --json- Parse
rankedresults. Prefer stable fields such asrelevance_score,citation_count,venue,doi,url,abstract, andrelevance_reason. - Report search query, source, iteration count, result count, and the top ranked papers. Do not treat LLM relevance score as proof of quality.
- If the result set is poor, broaden or narrow the natural-language question and rerun. Do not fabricate missing DOI, authors, abstracts, or citations.
Show full SKILL.md (257 more words)Show less
Output Boundaries
- PaperSeek returns metadata and ranked candidate lists. It does not download PDFs.
- It may return links to records, DOI pages, OpenAlex records, or available PDF URLs from metadata, but those are not guaranteed access rights.
- WoS Starter should be treated as key-backed and currently marked temporarily unavailable in the UI.
- Crossref is good for DOI and bibliographic metadata; it is not the best sole source for semantic recall.
- The standalone Skill runtime does not perform citation expansion. Install the full PaperSeek package for citation maps and the Web UI.
Failure Handling
| Situation | Action |
|---|---|
| CLI missing | Use python skills/paperseek/scripts/paperseek.py ...; install the full package only for Web UI/citation maps/full workflow parity. |
| Missing LLM key | Standalone search still works with deterministic query/ranking heuristics; tell user to set LLM_API_KEY for LLM query refinement and ranking. |
| OpenAlex warning about key | Explain that OpenAlex can be tested without a key but stable usage should configure OPENALEX_API_KEY. |
| Crossref warning about email | Suggest CROSSREF_EMAIL for polite-pool requests. |
| WoS 401 or missing key | Check WOS_API_KEY and Starter API entitlement. |
| WoS 512 | Treat as Clarivate upstream or query compatibility issue; retry with simpler query or switch to OpenAlex while investigating. |
| Zero or weak results | Try shorter English keywords, remove narrow field hints, or switch data source. |
Do Not Do
- Do not store API keys in Skill files, README files, tests, or chat.
- Do not use PaperSeek for paywall bypass, Sci-Hub fallback, or bulk PDF downloading.
- Do not invent paper metadata from model memory.
- Do not claim a systematic review is complete from PaperSeek output alone.
© MingfengHong, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 5 other files (scripts, references) in skills/paperseek of MingfengHong/paperseek.
- SKILL.md
- references/cli-contract.md
- references/management-layer.md
- references/source-routing.md
- scripts/paperseek.py
- scripts/paperseek_skill_runtime.py
Open the folder on GitHubat commit ced3100
Compare with similar skills
PaperSeek Literature Search next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| PaperSeek Literature Search this skillMingfengHong/paperseek | 0 | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Literature ReviewK-Dense-AI/scientific-agent-skills | 48k | 1 repos | ~3.2k | Automated safety check: Notes | MIT | |
| Literature Reviewneflibata-feng/MyArxiv-Agent | 126 | 20 repos | ~5.9k | Automated safety check: Notes | MIT | |
| Paper Research on arXivXiaomiMiMo/MiMo-Code | 14k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Daily arXiv Paper Briefjuliye2025/evil-read-arxiv | 1.7k | — | ~4.3k | Automated safety check: Pass | None | |
| Literature ReviewNorman-bury/research-writing-skill | 3.4k | — | ~2.2k | Automated safety check: Notes | MIT |
Similar skills
Literature Review
neflibata-feng/MyArxiv-Agent
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.).
Paper Research on arXiv
XiaomiMiMo/MiMo-Code
Searches arXiv, fetches metadata, generates BibTeX, downloads PDFs and finds citations and related papers using a bundled Python script.
Daily arXiv Paper Brief
juliye2025/evil-read-arxiv
Searches arXiv for recent papers matching your research interests, scores them and writes a daily recommendation note into an Obsidian vault.
Literature Review
Norman-bury/research-writing-skill
A skill your agent uses when writing literature review sections - guides searching, organizing, and synthesizing academic sources
Literature Search Methodology
aiming-lab/AutoResearchClaw
Lays out a systematic literature review method: PICO-based search strategy, inclusion criteria, PRISMA screening, quality assessment tools and synthesis approaches.
Related
Works with
Categories
Questions about PaperSeek Literature Search
What does PaperSeek Literature Search do?
Routes literature searches through the PaperSeek launcher, picks suitable scholarly sources, parses JSON output and keeps API keys out of the chat. The skill bundles a self-contained Python runtime in scripts/, so core searches work even when the full PaperSeek package is missing; if the package is installed, the launcher hands off to it for the complete CLI and Web UI. The standalone runtime handles search, smoke, sources, doctor, config listing and history path using only the standard library.
When should I use PaperSeek Literature Search?
PaperSeek Literature Search fits situations like: searching for papers from a natural-language research question; checking whether PaperSeek and its sources are configured correctly; choosing between OpenAlex, arXiv, PubMed and other sources for a topic; exporting a ranked paper list or exploring a citation map.
How do I install PaperSeek Literature Search in Claude Code?
Run `npx skills add MingfengHong/paperseek --skill paperseek -a claude-code`. Or copy the skill folder (skills/paperseek in MingfengHong/paperseek) into .claude/skills/paperseek in your project. Claude Code loads it when a task matches its description.
How do I install PaperSeek Literature Search in Codex?
Run `npx skills add MingfengHong/paperseek --skill paperseek -a codex`. Or copy the skill folder (skills/paperseek in MingfengHong/paperseek) into .agents/skills/paperseek in your project. Codex loads it when a task matches its description.
Can I use PaperSeek Literature Search in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add MingfengHong/paperseek --skill paperseek -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/paperseek, .gemini/skills/paperseek, .github/skills/paperseek and .opencode/skills/paperseek in your project.
What does PaperSeek Literature Search need to run?
Going by SKILL.md and its folder, PaperSeek Literature Search needs Python for the scripts in its folder, the command-line tools its instructions call (python) and credentials named LLM_API_KEY, OPENALEX_API_KEY and WOS_API_KEY. Our summary lists: Python to run the bundled launcher; API keys for some sources, configured locally through environment variables. Compatibility (from SKILL.md): Bundles a self-contained Python standard-library runtime for core OpenAlex/arXiv/Semantic Scholar/PubMed/computer science top-conference/Crossref/WoS literature search. The full PaperSeek package is optional and used automatically when installed..
Does PaperSeek Literature Search access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is PaperSeek Literature Search safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does PaperSeek Literature Search use?
PaperSeek Literature Search is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does PaperSeek Literature Search use?
About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.7k tokens, read only when the agent opens those files.
What are the alternatives to PaperSeek Literature Search?
Skills that share tags, products or a category with PaperSeek Literature Search: Literature Review (K-Dense-AI/scientific-agent-skills, 48k stars), Literature Review (neflibata-feng/MyArxiv-Agent, 126 stars), Paper Research on arXiv (XiaomiMiMo/MiMo-Code, 14k stars) and Daily arXiv Paper Brief (juliye2025/evil-read-arxiv, 1.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains PaperSeek Literature Search?
MingfengHong (a GitHub user) maintains it in MingfengHong/paperseek, which has 0 GitHub stars. The repository was last updated on October 9, 2026.
Source: MingfengHong/paperseek on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.