Agent skill

Paper Scout

by AlphaLab-USTC in AlphaLab-USTC/ResearchClaw

Discover and recommend latest arXiv papers matching user research interests.

MITAuto-check passedProduct & Project Management

Install Paper Scout

skills CLI

$ npx skills add AlphaLab-USTC/ResearchClaw --skill paper-scout -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install AlphaLab-USTC/ResearchClaw paper-scout --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/AlphaLab-USTC/ResearchClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/paper-scout .claude/skills/paper-scout && rm -rf skills-src

Use ~/.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/

Paste into Claude Code

Install the "paper-scout" agent skill from https://github.com/AlphaLab-USTC/ResearchClaw/tree/main/skills/paper-scout into .claude/skills/paper-scout/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-scout", 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

$skill-installer install https://github.com/AlphaLab-USTC/ResearchClaw/tree/main/skills/paper-scout

Type 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.

skills CLI

$ npx skills add AlphaLab-USTC/ResearchClaw --skill paper-scout -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install AlphaLab-USTC/ResearchClaw paper-scout --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AlphaLab-USTC/ResearchClaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/paper-scout .agents/skills/paper-scout && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "paper-scout" agent skill from https://github.com/AlphaLab-USTC/ResearchClaw/tree/main/skills/paper-scout into .agents/skills/paper-scout/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-scout", 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.

skills CLI

$ npx skills add AlphaLab-USTC/ResearchClaw --skill paper-scout -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install AlphaLab-USTC/ResearchClaw paper-scout --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AlphaLab-USTC/ResearchClaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/paper-scout .cursor/skills/paper-scout && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "paper-scout" agent skill from https://github.com/AlphaLab-USTC/ResearchClaw/tree/main/skills/paper-scout into .cursor/skills/paper-scout/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-scout", 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

$ gemini skills install https://github.com/AlphaLab-USTC/ResearchClaw.git --path skills/paper-scout

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add AlphaLab-USTC/ResearchClaw --skill paper-scout -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install AlphaLab-USTC/ResearchClaw paper-scout --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AlphaLab-USTC/ResearchClaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/paper-scout .gemini/skills/paper-scout && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "paper-scout" agent skill from https://github.com/AlphaLab-USTC/ResearchClaw/tree/main/skills/paper-scout into .gemini/skills/paper-scout/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-scout", 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.

GitHub CLI

$ gh skill install AlphaLab-USTC/ResearchClaw paper-scout

Installs 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).

skills CLI

$ npx skills add AlphaLab-USTC/ResearchClaw --skill paper-scout -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/AlphaLab-USTC/ResearchClaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/paper-scout .github/skills/paper-scout && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "paper-scout" agent skill from https://github.com/AlphaLab-USTC/ResearchClaw/tree/main/skills/paper-scout into .github/skills/paper-scout/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-scout", 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.

skills CLI

$ npx skills add AlphaLab-USTC/ResearchClaw --skill paper-scout -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install AlphaLab-USTC/ResearchClaw paper-scout --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AlphaLab-USTC/ResearchClaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/paper-scout .opencode/skills/paper-scout && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "paper-scout" agent skill from https://github.com/AlphaLab-USTC/ResearchClaw/tree/main/skills/paper-scout into .opencode/skills/paper-scout/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "paper-scout", 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: paper-scout
GitHub stars: 134
Token cost: ~1.4k tokens
SKILL.md length: 494 words
Files: 1
Skills in repo: 7
Repo updated: Apr 7, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Discover and recommend latest arXiv papers matching user research interests.

Works in 5 steps: Build search queries → Fetch and parse → Score and rank → …
User says: 推荐今日论文
SKILL.md covers ⚙️ Step 0 — Read the Research… and ⚠️ Error Handling
Reaches export.arxiv.org and ar5iv.labs.arxiv.org

What it does

Paper Scout is an agent skill from AlphaLab-USTC/ResearchClaw. Discover and recommend latest arXiv papers matching user research interests. Use when user says: 推荐今日论文, paper scout, 每日论文, daily papers, paper recommendation.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Product & Project Management, covering User research. It works with arXiv. The repository describes itself as: 上朝式科研：AI-powered research workflow showcase. The licence is MIT.

When your agent uses it

User says: 推荐今日论文
Paper recommendation

Example prompts

“/paper-scout”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

Build search queries
Fetch and parse
Score and rank
Format and output
Auto-learn from feedback

What it can do on your machine

Read from SKILL.md and the folder at commit 9d64c4b. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml and xml).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- export.arxiv.org
- ar5iv.labs.arxiv.org
- arxiv.org
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Paper Scout loads about 1.4k tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 494 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~43
When it runs · the whole SKILL.md, loaded when a task matches: ~1.4k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from AlphaLab-USTC/ResearchClaw at commit 9d64c4b, republished under its MIT licence (© AlphaLab-USTC). 494 words, ~1,380 tokens.

Download SKILL.mdSave it as .claude/skills/paper-scout/SKILL.md (or your agent's skills folder).

name: paper-scout
description: Discover and recommend latest arXiv papers matching user research interests. Use when user says: 推荐今日论文, paper scout, 每日论文, daily papers, paper recommendation.

Paper Scout — Daily Paper Discovery

⚙️ Step 0 — Read the Research Profile (Always First)

Before running any capability, load the user's research profile.

Location: ~/.openclaw/workspace/research-claw-config.md

If this file does not exist, use these defaults silently and mention at the end:

💡 想定制推荐兴趣？试试说「更新我的研究画像」

yaml

# Default profile (used when no config found)
research_direction: "Large language models, reinforcement learning, agentic AI"
seed_papers: []
keywords:
  - large language models
  - reinforcement learning
  - agentic AI / AI agents
  - retrieval-augmented generation
  - multimodal models
whitelist_authors: []
learned_preferences:
  accept: []
  reject: []

Config fields reference:

research_direction — free-text description of the user's research focus
seed_papers — list of arXiv IDs the user considers gold-standard references
keywords — interest topics used for Paper Scout search queries
whitelist_authors — researcher names to prioritize in recommendations
learned_preferences.accept — keywords/topics user has explicitly liked
learned_preferences.reject — keywords/topics user has skipped or disliked

Goal: Find today's top arXiv papers matching user interests. Output Top 5–10 with relevance scoring.

Triggers: 推荐今日论文 · 每日论文 · paper scout · daily cron job

Step 1 — Build search queries

From the loaded profile, extract keywords and construct arXiv query URLs:

http://export.arxiv.org/api/query?search_query=all:{KEYWORD}&sortBy=submittedDate&sortOrder=descending&max_results=25&start=0

Replace spaces in keywords with + (e.g., large+language+models)
Run 2–4 queries covering different interest areas
If the user has seed_papers, also fetch their metadata via:
```
https://export.arxiv.org/abs/{ARXIV_ID}
```
Use these to calibrate what "relevant" means (topics, methods, problem framing).

Step 2 — Fetch and parse

Use web_fetch for each query URL. Parse the XML Atom response:

xml

<entry>
  <title>...</title>           <!-- paper title -->
  <author><name>...</name></author>   <!-- first/all authors -->
  <summary>...</summary>       <!-- abstract -->
  <id>http://arxiv.org/abs/XXXX.XXXXX</id>   <!-- canonical URL -->
  <published>2026-03-26T...</published>       <!-- submission date -->
  <arxiv:primary_category term="cs.LG"/>     <!-- category -->
</entry>

Filter: Only keep papers published within the last 3 days (compare <published> to today's date in Asia/Shanghai timezone). If fewer than 5 papers remain, extend to 7 days and note it.

Step 3 — Score and rank

Score each paper 1–5 on relevance:

Signal	Score Boost
Title contains exact keyword from user profile	+2
Abstract contains ≥3 keyword matches	+1.5
Author in `whitelist_authors`	+2
Paper cites or builds on seed paper	+1.5
Novel contribution words: "propose", "novel", "outperform", "state-of-the-art", "benchmark"	+0.5
Survey/review signal: "survey", "overview", "analysis of existing"	−1
Topic in `learned_preferences.accept`	+1
Topic in `learned_preferences.reject`	−2

Sort descending by score. Keep Top 5 (or Top 10 if user asks for more).

Step 4 — Format and output

📡 今日论文推荐 | Daily Paper Scout
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🗓️ {DATE} | 匹配兴趣: {COMMA_SEPARATED_KEYWORDS}

1️⃣ **{Title}**
   👤 {First Author} et al. ({Year})
   🏷️ {category, e.g. cs.LG · cs.AI}
   💡 {One-sentence summary — Chinese or English, whichever matches user preference}
   🎯 相关原因: {1 sentence — why this matches user's profile}
   🔗 {arXiv URL}

2️⃣ **{Title}**
   ... (repeat)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📝 想深读某篇？发链接说 "帮我读一下" | 加入待读说 "加入待读 [链接]"

Show full SKILL.md (198 more words)Show less

Step 5 — Auto-learn from feedback

If the user reacts to a recommended paper with:

"不错" / "这个好" / "有意思" / "精读" → extract keywords from that paper's title/abstract, add to learned_preferences.accept in config
"skip" / "没意思" / "不相关" → extract keywords, add to learned_preferences.reject

Update ~/.openclaw/workspace/research-claw-config.md immediately.

Cron setup

If user wants daily delivery:

Time: 9:00 AM (Asia/Shanghai)
Prompt: 推荐今日论文
Channel: user's preferred channel (Discord, Telegram, etc.)

⚠️ Error Handling

Error	Handling
arXiv API returns empty results	Retry once with broader query; if still empty, note "arXiv API temporarily unavailable"
PDF tool times out	Fall back to abstract-only mode; note `[Abstract only — PDF timeout]` in the note
PDF tool returns error for a paper	Try fetching `https://ar5iv.labs.arxiv.org/html/{ARXIV_ID}` as HTML fallback
Config file missing	Use defaults silently; add a note at end: "💡 想定制？说「更新我的研究画像」"
Reading list JSON missing or malformed	Start fresh with an empty list; inform user: "未找到现有列表，已新建空列表"
Template file not found	Report the expected path and ask user to check installation
No papers in last 3 days	Extend to 7 days, note it: "（近3天论文较少，已扩展至7天）"
Fewer than 3 read papers for Idea Generator	Proceed anyway, but note the limitation
User provides PDF/DOI instead of arXiv	Try to extract arXiv ID from DOI or search arXiv by title

Files

Just SKILL.md in skills/paper-scout of AlphaLab-USTC/ResearchClaw.

Open the folder on GitHubat commit 9d64c4b

Compare with similar skills

Paper Scout 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.

Paper Scout compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Paper Scout this skillAlphaLab-USTC/ResearchClaw	134	—	~1.4k	Automated safety check: Pass	MIT	6 mo ago
User Research Cookiycookiy-ai/user-research-skill	1.6k	—	~954	Automated safety check: Pass	MIT	1 mo ago
Fable DomainSahir619/fable-method	2.3k	—	~2.6k	Automated safety check: Pass	MIT	8 days ago
Produck Feedback To Buildtryproduck/produck-skills	511	—	~1k	Automated safety check: Pass	Apache-2.0	1 mo ago
Customer InterviewsRefoundAI/lenny-skills	1.4k	—	~1.7k	Automated safety check: Pass	MIT	2 mo ago
Product Discovery Brief Builderopen-mercato/skills	231	—	~3k	Automated safety check: Pass	MIT	5 days ago

Similar skills

User Research Cookiy
cookiy-ai/user-research-skill
End-to-end user research assistant — qualitative and quantitative.
1.6k GitHub stars~954 tokensUpdated 1 mo ago
Product & Project ManagementAuto-check passed
Fable Domain
Sahir619/fable-method
Discuss a domain with the user, research it from real sources, then generate a trusted skill bundle for it - a step-by-step workflow with a flowchart, a domain adapter, a trap fixture, and a smoke…
2.3k GitHub stars~2.6k tokensUpdated 8 days ago
Product & Project ManagementAuto-check passed
Produck Feedback To Build
tryproduck/produck-skills
Pulls full in-context user feedback tickets through the Produck MCP server and turns them into an aligned product change instead of a guess.
511 GitHub stars~1k tokensUpdated 1 mo ago
Product & Project ManagementAuto-check passed
Customer Interviews
RefoundAI/lenny-skills
Help users conduct high-impact customer interviews that move beyond surface-level feature requests to identify root emotional frustrations and specific causal triggers.
1.4k GitHub stars~1.7k tokensUpdated 2 mo ago
Product & Project ManagementAuto-check passed
Product Discovery Brief Builder
open-mercato/skills
Guides a product discovery conversation and writes product-brief.md with the problem, evidence, scope, decisions and the next open question, for existing, client or own ideas.
231 GitHub stars~3k tokensUpdated 5 days ago
Product & Project ManagementAuto-check passed
Discovery Synthesis
andreaskelm/pm-brain
Plan customer discovery, turn interview snapshots into synthesis and evidence-based opportunities, build or update an Opportunity Solution Tree, map jobs and segments, and design RAT tests for the…
234 GitHub stars~2.3k tokensUpdated yesterday
Product & Project ManagementAuto-check passed

Questions about Paper Scout

What does Paper Scout do?

Discover and recommend latest arXiv papers matching user research interests. Paper Scout is an agent skill from AlphaLab-USTC/ResearchClaw. Discover and recommend latest arXiv papers matching user research interests.

When should I use Paper Scout?

Paper Scout fits situations like: user says: 推荐今日论文; paper recommendation.

How do I install Paper Scout in Claude Code?

Run `npx skills add AlphaLab-USTC/ResearchClaw --skill paper-scout -a claude-code`. Or copy the skill folder (skills/paper-scout in AlphaLab-USTC/ResearchClaw) into .claude/skills/paper-scout in your project. Claude Code loads it when a task matches its description.

How do I install Paper Scout in Codex?

Run `npx skills add AlphaLab-USTC/ResearchClaw --skill paper-scout -a codex`. Or copy the skill folder (skills/paper-scout in AlphaLab-USTC/ResearchClaw) into .agents/skills/paper-scout in your project. Codex loads it when a task matches its description.

Can I use Paper Scout 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 AlphaLab-USTC/ResearchClaw --skill paper-scout -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/paper-scout, .gemini/skills/paper-scout, .github/skills/paper-scout and .opencode/skills/paper-scout in your project.

What does Paper Scout need to run?

SKILL.md names no scripts, command-line tools or credentials: Paper Scout is instructions for the agent only.

Does Paper Scout access the network?

SKILL.md names 3 domains. In commands or code: export.arxiv.org, ar5iv.labs.arxiv.org and arxiv.org; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Paper Scout 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. Review the folder before installing.

What licence does Paper Scout use?

Paper Scout is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Paper Scout use?

About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Paper Scout?

Skills that share tags, products or a category with Paper Scout: User Research Cookiy (cookiy-ai/user-research-skill, 1.6k stars), Fable Domain (Sahir619/fable-method, 2.3k stars), Produck Feedback To Build (tryproduck/produck-skills, 511 stars) and Customer Interviews (RefoundAI/lenny-skills, 1.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Paper Scout?

AlphaLab-USTC (a GitHub user) maintains it in AlphaLab-USTC/ResearchClaw, which has 134 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on April 7, 2026.

Source: AlphaLab-USTC/ResearchClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Paper Scout

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Paper Scout — Daily Paper Discovery

⚙️ Step 0 — Read the Research Profile (Always First)

Step 1 — Build search queries

Step 2 — Fetch and parse

Step 3 — Score and rank

Step 4 — Format and output

Step 5 — Auto-learn from feedback

Cron setup

⚠️ Error Handling

Files

Compare with similar skills

Similar skills

More from AlphaLab-USTC/ResearchClaw

Related

Questions about Paper Scout