sakanaai/ai-scientist-v3/retrieve-references

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Retrieve grounded BibTeX references from Semantic Scholar Graph API, OpenAlex, or Google Scholar (`scholarly`) and write references.bib plus provenance JSON for paper generation.

Install

npx vskill@latest install sakanaai/ai-scientist-v3/retrieve-references

SKILL.md

What the skill is about

Fetch references from Semantic Scholar Graph API, OpenAlex, or Google Scholar (via scholarly) and keep only real BibTeX entries.

When to use the skill

  • Final report/paper generation.
  • Related-work section needs grounded citations.

What to do

  1. Build focused search queries from task goal, method names, and top experiment ideas.
  2. Preferred path (Semantic Scholar Graph API):
bash
python scripts/s2_fetch.py \
--query "query one" \
--query "query two" \
--min-refs 8 \
--max-refs 15 \
--out-bib references.bib \
--out-json references_provenance.json
  1. Fallback path (OpenAlex):
bash
python scripts/openalex_fetch.py \
--query "query one" \
--query "query two" \
--min-refs 8 \
--max-refs 15 \
--search-limit 10 \
--out-bib references.bib \
--out-json references_provenance.json

Optional:

  • --mailto you@example.com to enter the OpenAlex polite pool
  • Env fallback: OPENALEX_EMAIL
  1. Alternate path (Google Scholar API wrapper with scholarly):
bash
python -m pip install scholarly
python scripts/scholarly_fetch.py \
--query "query one" \
--query "query two" \
--min-refs 8 \
--max-refs 15 \
--search-limit 25 \
--sort-by relevance \
--proxy-mode auto \
--delay-seconds 0.5 \
--out-bib references.bib \
--out-json references_provenance.json

Proxy options:

  • --proxy-mode auto|none|free|single
  • --proxy-http <url> / --proxy-https <url> for single
  • Env fallbacks: SCHOLARLY_PROXY_MODE, SCHOLARLY_PROXY_HTTP, SCHOLARLY_PROXY_HTTPS
  • Global HTTP_PROXY / HTTPS_PROXY are intentionally ignored to avoid accidental ambient proxying
  1. Require S2_API_KEY when available for s2_fetch.py (script reads env automatically).
  2. Keep only references with valid BibTeX and citation key.
  3. Dedupe by citation key and paper id.
  4. Fail hard if references found < min-refs.
  5. Use s2_fetch.py first for stability, openalex_fetch.py as the next fallback, and scholarly_fetch.py last if the other sources fail.

Outputs

  • references.bib
  • references_provenance.json

Notes

  • Use templates/provenance.schema.json for expected shape.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/sakanaai/ai-scientist-v3/retrieve-references/badge)](https://verified-skill.com/skills/sakanaai/ai-scientist-v3/retrieve-references)

Something wrong with this skill or its page? Tell us.