AgentStack
SKILL verified MIT Self-run

Eda Paper Fetch

skill-mr-fang-vlsi-edagent-eda-paper-fetch · by Mr-Fang-VLSI

Fetch primary-source paper metadata when evidence is missing or weak for EDA/model/flow claims. Use for requests like building reproducible paper candidate lists, generating user-download queues, and recording citation metadata for local validation.

No reviews yet
0 installs
15 views
0.0% view→install

Install

$ agentstack add skill-mr-fang-vlsi-edagent-eda-paper-fetch

✓ 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 Eda Paper Fetch? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

EDA Paper Fetch

Overview

Use this skill to produce evidence-backed paper sets, not ad-hoc links. Always output a local manifest and evidence note.

Workflow

  1. Define scope and constraints.
  • topic and claim to support/refute,
  • date window and venue preference,
  • target count (default: 5-15 papers).
  1. Search primary sources first.
  • Load references/source-priority.md.
  • Prefer official sources (publisher/arXiv/OpenReview/DOI landing pages).
  • Do not claim availability without opening source pages.
  1. Triage and score.
  • Keep only papers relevant to the exact claim.
  • Record reason for inclusion/exclusion using references/triage-template.md.
  1. Generate user-download queue instead of auto-download.
  • Write docs/papers/queues/.download_queue.tsv.
  • Include columns: paper_id, title, url, doi_or_arxiv, preferred_source, access_type(open/paywalled).
  • User manually downloads PDFs to docs/papers/pdf/ using filename:
  • __.pdf.
  1. Produce manifest and summary.
  • Write docs/papers/manifests/.paper_manifest.tsv.
  • Write docs/papers/manifests/.paper_manifest.md.
  • Include fields: paper_id, title, authors, venue, year, url, doi_or_arxiv, local_pdf_path, relevance_note, status(todo/downloaded/summarized).

Output Contract

Always return:

  1. local manifest path,
  2. local download queue path,
  3. unresolved paywalled items,
  4. one-paragraph evidence fitness assessment.

References

Read only when needed:

  1. references/source-priority.md
  2. references/triage-template.md

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.

Versions

  • v0.1.0 Imported from the upstream source.