Skip to content
Skills Library
Science & research · Research

academic-citation

/academic-citation

Search, verify, and map citations for CS/AI/ML papers. Produces VERIFIED/UNVERIFIED reference lists with Citation-to-Claim maps and Exemplar Sets. Use when: finding references for a paper section, verifying citation accuracy, building exemplar sets for introduction/related work learning, checking if existing citations are real and accurate, supplementing local literature library. Triggers on: 找引用, 文献检索, citation pass, find references, reference check, 补文献, citation verification, Exemplar Set, search papers, verify citation, 核验文献, 查引用, literature search, reference verification, citation verific

Licence
MIT
Last repository change
27.06.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
15
Scripts
3
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 27.06.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What to check before installing
  • 3 scripts in this package. Review them before installing, as Claude may execute them.

Scripts: scripts/citation_audit.py, scripts/convert-pdfs-to-md.py, scripts/convert_pdfs_to_md_mineru_api.py

What it does and when to use it

Search, verify, and map citations for CS/AI/ML papers. Produces VERIFIED/UNVERIFIED reference lists with Citation-to-Claim maps and Exemplar Sets. Use when: finding references for a paper section, verifying citation accuracy, building exemplar sets for introduction/related work learning, checking if existing citations are real and accurate, supplementing local literature library. Triggers on: 找引用, 文献检索, citation pass, find references, reference check, 补文献, citation verification, Exemplar Set, search papers, verify citation, 核验文献, 查引用, literature search, reference verification, citation verific

Original author description

Search, verify, and map citations for CS/AI/ML papers. Produces VERIFIED/UNVERIFIED reference lists with Citation-to-Claim maps and Exemplar Sets. Use when: finding references for a paper section, verifying citation accuracy, building exemplar sets for introduction/related work learning, checking if existing citations are real and accurate, supplementing local literature library. Triggers on: 找引用, 文献检索, citation pass, find references, reference check, 补文献, citation verification, Exemplar Set, search papers, verify citation, 核验文献, 查引用, literature search, reference verification, citation verific

How it works

  1. Router Protocol
  2. Modes
  3. Agent Dispatch
  4. Independent Use
Original SKILL.md headings · 61 lines, 515 words
SKILL.md preview
---
name: academic-citation
description: "Search, verify, and map citations for CS/AI/ML papers. Produces VERIFIED/UNVERIFIED reference lists with Citation-to-Claim maps and Exemplar Sets. Use when: finding references for a paper section, verifying citation accuracy, building exemplar sets for introduction/related work learning, checking if existing citations are real and accurate, supplementing local literature library. Triggers on: 找引用, 文献检索, citation pass, find references, reference check, 补文献, citation verification, Exemplar Set, search papers, verify citation, 核验文献, 查引用, literature search, reference verification, citation verification with reading, 引用确认, 全文阅读验证."
---

# Academic Citation

将此 skill 视为"文献取证代理",而不是搜索结果搬运器。

## Router Protocol

1. Read `manifest.yaml`. It declares `always_load` files, `axes`, and `references.on_demand`.
2. Read every file listed under `always_load`. These are the skill's binding rules — not reference material.
3. Apply the loaded material as constraints:
   - `stance.md` defines non-negotiable rules, source/inference boundary, and scope.
   - `red-lines.md` defines absolute prohibitions. Do not negotiate these.
   - `output-contract.md` defines deliverables per mode.
   - `anti-patterns.md` defines known failure modes and their correct alternatives.
4. If the user wants to use a local literature library, first distinguish:
   - `local_ref_md_dir`: an existing Markdown library containing `_index_ref.json`.
   - `local_ref_pdf_dir`: a PDF directory, or any local library directory that lacks `_index_ref.json`.
5. For `local_ref_pdf_dir`, stop before citation search. Tell the user to register a MinerU API token, set `MINERU_API_TOKEN`, run `scripts/convert-pdfs-to-md.py`, and return only after they confirm PDF→MD completion. Do not proceed to local reading until the generated MD directory has `_index_ref.json`.
6. Detect the workflow using the manifest's `workflow` axis. Literature reading output must separate source quotes from agent inference; only `source: 原文` or `source: 图片` content may be used as citation evidence.
7. Echo the selected mode to the user before executing.
8. Reach for `references/` only when the manifest's `references.on_demand` condition is satisfied.

## Modes

| Mode | Use when |
|---|---|
| `full-citation-pass` | Complete coverage for a full paper or core section |
| `targeted-citation-search` | Specific claim, section, or topic |
| `exemplar-set-only` | Build Exemplar Set only, not full citation list |
| `citation-verification` | Verify metadata of existing candidate list |
| `local-citation-pass` | Local MD library first, then web supplement |
| `citation-verification-with-reading` | Full-text reading after paper draft completion |

## Agent Dispatch

| Agent | Purpose |
|---|---|
| `agents/citation_agent.md` | Literature search strategy (4-class query templates, output schema) |
| `agents/literature-reader-agent.md` | Literature reading & extraction (MD full-text → LiteratureReadingReport) |

Dispatched by `academic-paper-writer` orchestrator at Step 3. Subagents search and verify only; they must not modify project files or write paper prose independently. `literature-reader-agent` is dispatched in parallel by `citation_agent` or the orchestrator at Step 3a/3b.

## Independent Use

| Input | Mode | Priority | Behavior |
|---|---|---|---|
| Section + keywords | full-citation-pass | 1 (explicit) | Full 6-step workflow |
| Citation list / seed papers | citation-verification | 1 (explicit) | Metadata only, no extra search |
| `local_ref_md_dir` provided and `_index_ref.json` exists | local-citation-pass | 2 (path trigger) | Local MD + batch parallel reader agent dispatch |
| Local PDF library path provided, or local path lacks `_index_ref.json` | pdf2md-preflight | 1 (blocking preflight) | Instruct MinerU setup and script command; wait for user confirmation |
| Section only | targeted-citation-search | 3 (single feature) | Auto-keyword, 4-class query |
| Explicit Exemplar Set request | exemplar-set-only | 1 (explicit) | Exemplar Set only |

**Multi-condition**: lower priority number wins.

| Scenario | Recommended |
|---|---|
| Just searching/verifying citations | This skill (standalone) |
| Integrating into paper drafting | academic-paper-writer orchestrator |
| Existing draft needs citation review | This skill → academic-reviser |
Files in this package (15)
  • SKILL.md 4 KB
  • manifest.yaml 2 KB
  • agents/citation_agent.md 9 KB
  • agents/literature-reader-agent.md 11 KB
  • references/citation-mapping.md 2 KB
  • references/search-strategy.md 3 KB
  • references/verification-protocol.md 3 KB
  • references/workflow-citation-pass.md 6 KB
  • scripts/citation_audit.py 3 KB
  • scripts/convert-pdfs-to-md.py 2 KB
  • scripts/convert_pdfs_to_md_mineru_api.py 23 KB
  • static/core/anti-patterns.md 1 KB
  • static/core/output-contract.md 1 KB
  • static/core/red-lines.md 1 KB
  • static/core/stance.md 3 KB

Versions

RepositoryScoreLicence
This page · joshua-zyy/academic-paper-writer100MIT
luffysolution-svg/omnischolar90MIT
xyd-gis/paper-toolkits90MIT

Database snapshot: 13.11.2026 · package version 4900dd54a530 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100citation-verification
    This skill provides reference guidance for citation verification in academic writing. Use when the user asks about "citation verification best practices", "how to verify references", "preventing fake citations", or needs guidance on citation accuracy. This skill supports…
  • 100paper-search
    Paper search — use when the user wants to find academic literature, build a reference list, verify citations exist, or needs reference expansion from anchor papers. Looks for research direction in research_proposal.md; asks if absent. literature-review reads this output.
  • 100citation-check
    Verify citations in AI-generated or human-written text against the local knowledge base. Catches hallucinated references, wrong metadata, and missing papers. Use when the user wants to check if citations are real and accurate.
  • 91citation-management
    Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation…
  • 100ieee-citation
    Check, clean, verify, and improve IEEE citations, references, BibTeX entries, citation positioning, related-work logic, DOI metadata, venue names, and reference formatting using routed citation and metadata guidance. Use when preparing IEEE manuscripts, fixing bibliography…
  • 100literature-verification
    A zero-fabrication citation and literature workflow for academic writing. Verifies every reference against a live bibliographic record before it enters a draft, checks that the paper actually supports the claim attached to it, builds reviews from an evidence matrix rather than…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.