survey-generation

The survey-generation skill creates academic survey papers through a multi-step pipeline involving parallel outline generation, RAG-based writing, citation validation, and coherence enhancement.

858
Installs
5
Use cases
9/10
Quality

Is survey-generation safe to install?

Review the source first

Review the source first: our audit of survey-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 shell commands to perform literature searches and reads/writes local files to generate the survey structure and content.

How we audit skills: our security review methodology.

Who is this skill for?

Researchers and academics who need to generate comprehensive literature surveys based on existing research papers.

What can you do with it?

  • Generating structured academic survey outlines
  • Writing survey subsections using RAG from collected papers
  • Validating citation accuracy and claim faithfulness
  • Converting inline citations to BibTeX format
  • Refining document flow and local coherence

How good is this skill?

Quality score: 9/10. The skill documentation provides a clear, step-by-step workflow and defines specific input/output structures. The reliance on external scripts for research is clearly documented.

What does the skill file contain?

SKILL.md
# Survey Generation

Generate complete academic survey papers with structured outline, RAG-based writing, and citation validation.

## Input

- `$0` — Survey topic or research area

## Scripts

### Literature search
```bash
python ~/.claude/skills/deep-research/scripts/search_semantic_scholar.py \
  --query "relevant search query" --max-results 50
```

## References

- Survey prompts (outline, writing, citation, coherence): `~/.claude/skills/survey-generation/references/survey-prompts.md`

## Workflow (from AutoSurvey)

### Step 1: Collect Papers
1. Search Semantic Scholar / arXiv for papers o...

Frequently asked questions

What sources does the skill use for research?

The skill searches Semantic Scholar and arXiv for relevant papers.

How does the skill ensure citation accuracy?

The skill validates that cited paper titles are correct, verifies that citations support the claims, and uses Natural Language Inference to check claim-source faithfulness.

What output files does the skill produce?

The skill produces a main.tex file, a references.bib file, an outline.json file, and individual section files in a survey directory.

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