AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Academic Search

skill-yellowbee686-everything-analysis-agent-academic-search · by yellowbee686

Search academic literature with Semantic Scholar and synthesize paper, author, citation, and related-work findings. Use when Codex needs to find papers, compare research directions, inspect paper metadata, gather citation context, or produce source-backed academic summaries without depending on project-specific agent runtimes.

↗ Repository
— No reviews yet
0 installs
13 views
0.0% view→install

Install

$ agentstack add skill-yellowbee686-everything-analysis-agent-academic-search

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Academic Search? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Academic Search

Overview

Use Semantic Scholar as the default live academic search source. Prefer the bundled scripts/semantic_scholar.py CLI for deterministic JSON retrieval, then synthesize results in the user's requested language.

Workflow

  1. Clarify the research target only when the query is underspecified. Otherwise search directly.
  2. Run scripts/semantic_scholar.py search-papers "" --limit with focused fields.
  3. Inspect titles, abstracts, venue, year, citation count, influential citation count, authors, and open-access URLs.
  4. Fetch paper details for high-value candidates with get-paper when abstracts, references, citations, or external IDs are needed.
  5. Fetch author details with get-author only when the user asks about a person, publication record, or author disambiguation.
  6. Summarize with explicit uncertainty. Do not invent claims beyond returned metadata.

Commands

On Windows, follow the current agent environment. Use WSL2 if the agent is already in WSL2; otherwise native Windows Python is fine for this skill.

Search papers:

python3 skills/academic-search/scripts/semantic_scholar.py search-papers "retrieval augmented generation" --limit 10

Get paper details:

python3 skills/academic-search/scripts/semantic_scholar.py get-paper CorpusID:208324896

Get author information:

python3 skills/academic-search/scripts/semantic_scholar.py get-author 1741102

References

  • Read references/query-workflows.md for field presets, filtering, deduplication, and synthesis guidance.
  • Use SEMANTIC_SCHOLAR_API_KEY when available. The script also works without it, subject to public rate limits.

Output Rules

  • Cite paper titles, years, venues, and paper IDs or URLs when available.
  • Separate search results from interpretation.
  • Mention API or rate-limit failures plainly and include the failed command when useful.
  • Prefer compact tables for paper comparisons and concise bullets for literature summaries.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Search