mcpField
P
paper-spine-citation

paper-spine-citation

github.com/wubing2023Productivity6.1k211 installsUpdated 2w ago
Repository

About paper-spine-citation

paper-spine-citation is a PaperSpine skill that builds and verifies a pool of candidate citations to support claims in a manuscript. It audits references, marks uncertain entries, and curates a verified subset for final writing.

Key features

  1. 01Candidate citation support bank
  2. 02Source and DOI verification audit
  3. 03Citation quality and diversity analysis
  4. 04Uncertain reference marking
  5. 05Curation of verified citations

Use cases

  1. 01Collecting literature support for manuscript claims
  2. 02Checking candidate references before use
  3. 03Selecting a coherent set of verified citations

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/wubing2023/paperspine --skill paper-spine-citation

After installing, type/paper-spine-citationin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

references/
citation-support-bank.md
scripts/
_paper_spine_utils.py
citation_bank_check.py
citation_quality_audit.py
citation_verification_zh.py
humanize_check.py

Details

From the project README

PaperSpine Citation

Use this branch after research and before final writing. Its job is not to learn paper structure. Its job is to build a verified citation support bank that can support literature statements in the user's manuscript.

Inputs

Read paper_rewriting_output/paper_spine_config.json, especially:

  • target_name
  • scene
  • output_language
  • reference_mode
  • reference_paths
  • citation_target_count defaulting to 20
  • materials_dir
  • draft_path
  • research_dossier.md
  • sota_gap_map.md
  • reference_materials/source_index.md

Required Output

Create:

paper_rewriting_output/citation_support_bank.md

Use this table:

Candidate IDReference/BibTeXYearRecencySupports SectionSupport Claim SentenceWhy This Paper FitsSourceVerifiedVerification Note

Rules:

  • Generate at least citation_target_count * 3 candidates. Default: 60.
  • About 80% of candidates should be recent. In 2026, use 2023 or later as the simple recent threshold.
  • Each candidate must pair one paper with one or two support sentences that can be used in Introduction, Related Work, Discussion, limitations, or application paragraphs.
  • Prefer same-field, similar-field, foundational, benchmark, review, and application papers. Do not only cite near-identical SOTA papers.
  • Do not invent bibliography. Use local PDFs/metadata, DOI/arXiv/Crossref-like metadata, official publisher pages, or user-provided reference files.
  • Mark uncertain items as [VERIFY] and do not use them in final writing until the user verifies them.
  • This bank is a candidate pool. Final writing should select a coherent subset, not dump all candidates into the paper.

Read references/citation-support-bank.md when detailed rules are needed.

Flow

  1. Collection pass: Build the initial candidate pool with at least citation_target_count * 3 rows. Leave Verified and Verification Note columns empty during this pass.
  2. Verification pass: Run citation_quality_audit.py to verify each DOI against Crossref, score citation quality, analyze diversity gaps, and produce citation_quality_audit.md. Fill in the Verified column as yes, mismatch, dead, or error based on the audit results.
  3. Curation: Select the final subset of verified, recent, and field-appropriate citations for the manuscript. Do not use unverified or mismatched citations in final writing until the user confirms them.

Check

python scripts/citation_bank_check.py paper_rewriting_output/citation_support_bank.md --target-count 20 --markdown
python scripts/citation_quality_audit.py paper_rewriting_output --write

If the config has a different citation_target_count, use that value.

Comments

Markdown supported