paper-agent: Skill for Claude Code

.claude/skills/research-idea-generator/SKILL.md

research-idea-generator is a skill for Claude Code from Guo-Chenxu/paper-agent. It costs 43 tokens per session (1,626 once invoked), scanned A, original, Apache-2.0.

A workflow for turning summaries of research papers into evaluated research ideas and detailed proposals.

In plain words
What is it for?
Use it after collecting and screening papers to generate, rank, review, and expand new research directions.
Why use it?
It helps identify gaps in existing work and compare possible ideas by novelty, feasibility, and potential impact.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is Guo-Chenxu/paper-agent's own configuration. It tells Claude Code how to work on paper-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything paper-agent configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is # Summaries should be in ./paper_summaries/ directory.

Reuse

Borrowing it

Nothing to install: this file belongs to Guo-Chenxu/paper-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Guo-Chenxu/paper-agent/main/.claude/skills/research-idea-generator/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Guo-Chenxu/paper-agent

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for research-idea-generator

README.md
[![agentmods](https://agentmods.dev/badge/skills/guo-chenxu/paper-agent/research-idea-generator/github.svg)](https://agentmods.dev/skills/guo-chenxu/paper-agent/research-idea-generator)
Your own site
<a href="https://agentmods.dev/skills/guo-chenxu/paper-agent/research-idea-generator"><img src="https://agentmods.dev/badge/skills/guo-chenxu/paper-agent/research-idea-generator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for research-idea-generator

Your own site · 80×15
<a href="https://agentmods.dev/skills/guo-chenxu/paper-agent/research-idea-generator"><img src="https://agentmods.dev/badge/skills/guo-chenxu/paper-agent/research-idea-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,626 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.01626
Opus 5 $0.00022 $0.00813
Sonnet 5 $0.00009 $0.00325
Haiku 4.5 $0.00004 $0.00163

Measured 10d ago against content hash 451bb63bc43d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

research-idea-generator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/build_research_ideas_report.py, scripts/export_idea_prompts.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/research-idea-generator/SKILL.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Idea Generator

Skill Goal

Systematic research idea generation and evaluation workflow:

  1. Analyze paper summaries to build research knowledge graph
  2. Identify research gaps and opportunities
  3. Multi-agent parallel idea generation (3+ agents, 5+ ideas each)
  4. Idea evaluation and ranking by innovation, feasibility, and impact
  5. Adversarial review and refinement of top ideas
  6. Detailed research proposal generation

When To Use

  • Have completed paper collection and screening
  • Need to generate novel research ideas from literature review
  • Want systematic gap analysis and idea evaluation
  • Require detailed research proposals with background, hypothesis, and methodology

Environment

Run from the repository root with active Python interpreter.

Required packages:

python -m pip install requests tqdm

Scripts

  • Export idea generation prompt pack: ./scripts/export_idea_prompts.py
  • Build final research ideas report: ./scripts/build_research_ideas_report.py

The export_idea_prompts.py script is domain-agnostic and accepts:

  • --research-domain: Your research field (e.g., "machine learning", "computer vision", "natural language processing")
  • --summaries-dir: Directory with paper summaries
  • --num-agents: Number of idea generation agents (default: 3)
  • --ideas-per-agent: Ideas per agent (default: 5)
  • --experiment-constraints: Optional constraints (e.g., "Single server only")

References

  • Idea generation workflow and prompts: ./references/idea-generation.md

Workflow

Step 1: Load Paper Summaries

Load structured paper summaries from previous screening workflow:

# Summaries should be in ./paper_summaries/ directory
ls ./paper_summaries/*.md

Step 2: Build Research Knowledge Graph

Analyze all paper summaries to construct knowledge graph covering:

  • Solved problems: What has been thoroughly addressed
  • Open problems: What remains unsolved or partially solved
  • Common limitations: Shared weaknesses across existing methods
  • Cross-domain opportunities: Potential for technique transfer
  • Emerging trends: Recent breakthroughs applicable to the domain

Read the full file on GitHub · 235 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 235 lines · 43 tokens per session scan A 451bb63bc43d

Subscribe to this mod's changes

research-idea-generator is a skill published in the GitHub repository Guo-Chenxu/paper-agent (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,626 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens