idea-generation

The idea-generation skill generates and refines research ideas through iterative evaluation and novelty assessment against literature.

New
Installs
4
Use cases
8/10
Quality

Is idea-generation safe to install?

Review the source first

Review the source first: our audit of idea-generation's source files found 1 shell command, 0 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes local Python scripts and reads local reference files.

How we audit skills: our security review methodology.

Who is this skill for?

Researchers and developers brainstorming research directions or validating the novelty of specific concepts.

What can you do with it?

  • Generating diverse research ideas from a research area or codebase context
  • Refining research ideas through iterative evaluation of quality and feasibility
  • Assessing the novelty of research ideas using literature search tools
  • Ranking research ideas based on interestingness, feasibility, and novelty scores

How good is this skill?

Quality score: 8/10. The skill documentation is clear and provides specific instructions for the workflow and script execution. It lacks explicit API endpoint definitions for the novelty check, relying on local script execution.

What does the skill file contain?

SKILL.md
# Idea Generation

Generate and refine novel research ideas with literature-backed novelty assessment.

## Input

- `$0` — Research area, task description, or existing codebase context
- `$1` — Optional: additional context (e.g., "for NeurIPS", constraints)

## Scripts

### Novelty check against Semantic Scholar
```bash
python ~/.claude/skills/idea-generation/scripts/novelty_check.py \
  --idea "Adaptive attention head pruning via gradient-guided importance" \
  --max-rounds 5
```

Performs iterative literature search to assess if an idea is novel.

## References

- Ideation prompts (generatio...

Frequently asked questions

How does the skill assess novelty?

The skill uses a Python script to perform iterative literature searches and provides prompts for manual review of Semantic Scholar or arXiv results.

What metrics does the skill use to score ideas?

The skill scores ideas on a scale of 1-10 across three dimensions: Interestingness, Feasibility, and Novelty.

How many refinement rounds does the skill perform?

The skill performs up to 5 rounds of iterative refinement per idea.

Data sourced from lingzhi227/agent-research-skills on GitHub. Install counts from skills.sh. The summary and security audit are derived from the skill's source files: every command and URL listed appears verbatim in the source.

Related skills