survey-generator

Generates structured literature surveys with real bibliographies from a research bundle into wiki markdown pages.

1|Updated May 6, 2026
One-click install
npx skills add https://github.com/surfingalien/FinSurfing --skill survey-generator-surfingalien
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: survey-generator
Source: https://github.com/surfingalien/FinSurfing/tree/main/.claude/skills/survey-generator
Command: npx skills add https://github.com/surfingalien/FinSurfing --skill survey-generator-surfingalien

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve? Compiling a literature survey on an AI/ML topic requires curating real papers, organizing a taxonomy, and writing cited prose — a slow manual process that often produces one-off artifacts that are never reused. ## Core Features & Use Cases - Provider-agnostic generation: Works with Anthropic, OpenAI, OpenRouter, Fireworks, or any custom OpenAI-compatible endpoint, with provider auto-detection from environment variables. - Wiki-native output: Writes versioned markdown surveys to <wiki>/derived/surveys/<slug>-vN.md, appends deduplicated bibliography rows to sources.md, and indexes pages into an FTS5 store for later retrieval. - Schema-validated research bundles: Enforces that every cited paper key exists in the bibliography and that no bibliography entries are invented. - Use Case: Ask for a survey on "Reasoning Models" anchored to an arXiv survey or awesome-list; the agent builds a research bundle, then the script generates a 6-10 section cited survey saved permanently in your wiki. ## Quick Start Ask the agent to generate a literature survey on your chosen topic using a public anchor URL, targeting your wiki slug.

Frequently Asked Questions about survey-generator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate a literature survey on an AI topic with an LLM?

Provide a topic and a public anchor URL such as an arXiv survey or GitHub awesome-list. The agent builds a research_bundle.json with taxonomy, sections, and real bibliography entries, then runs build-survey.js to produce a cited markdown survey in your wiki.

Which LLM providers does the survey generator support?

It supports Anthropic, OpenAI, OpenRouter, Fireworks, and any custom OpenAI-compatible endpoint. The provider is auto-detected from environment variables like ANTHROPIC_API_KEY or OPENAI_API_KEY, or set explicitly with the --provider flag.

Can I compare survey output across different models?

Yes. Run build-survey.js multiple times with different --provider and --model flags against the same bundle. Each run writes a separate versioned file like topic-v1.md and topic-v2.md, so you can diff the outputs.

Does the survey generator prevent hallucinated citations?

Yes. The script validates that every paper key referenced in sections exists in the bibliography, rejects duplicate keys, and the prompt instructs the model to cite only the provided bibliography entries using exact citation IDs.

What are the limitations of the generated survey output?

Output quality depends entirely on the research bundle you curate; the script does not fetch or verify papers itself. If prose is thin, you must tighten section guidance in the bundle and rerun rather than editing the generated markdown.