agentleFS
wangyi0403wangyi0403/dl-research-workflow/.agents/skills/citation-verification/SKILL.md

citation-verification

Skill4 starsChanged 40 days agoMITView on GitHub

Verify citation metadata and support for manuscript claims during drafting or pre-submission; never invent references.

11 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use results-report, daily-coding and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Galaxy-DawnSkill

    results-report

    This skill should be used when the user asks to "write an experiment report", "summarize experimental results", "do experiment retrospection", "write a results report", "写实验总结报告", "写实验复盘", or mentions turning completed experiment artifacts into a structured, decision-oriented research report. It assumes strict analysis should come from `results-analysis` first.

    Also in 3 projects that use this

  • Clay-HHKSkill

    daily-coding

    Daily coding assistant that auto-triggers when writing/modifying code, providing a core checklist.

    Also in 3 projects that use this

  • Clay-HHKSkill

    kaggle-learner

    This skill should be used when the user asks to "learn from Kaggle", "study Kaggle solutions", "analyze Kaggle competitions", or mentions Kaggle competition URLs. Provides access to extracted knowledge from winning Kaggle solutions across NLP, CV, time series, tabular, and multimodal domains.

    Also in 3 projects that use this

  • kharlamenkodevSkill

    bug-detective

    Also in 3 projects that use this

  • MicrosoftSkill

    web-design-reviewer

    This skill enables visual inspection of websites running locally or remotely to identify and fix design issues. Triggers on requests like "review website design", "check the UI", "fix the layout", "find design problems". Detects issues with responsive design, accessibility, visual consistency, and layout breakage, then performs fixes at the source code level.

    Also in 4 projects that use this

  • AnthropicSkill

    command-development

    This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.

    Also in 3 projects that use this

  • +2 more from Clay-HHK

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify each reference as both a bibliographic record and evidence for the sentence that cites it.

    line 8
  2. Very specific:

    Read the manuscript, bibliography, and any existing Evidence ID records.

    line 10
  3. Distinctive:

    Prefer the canonical DOI/publisher record for final metadata.

    line 19
  4. Distinctive:

    Keep discovery, bibliographic verification, lawful full-text acquisition, local parsing, and note storage as distinct provenance steps.

    line 21
  5. Distinctive:

    Do not require a particular search engine, citation count, or fixed author-year tolerance.

    line 22
  6. Distinctive:

    Do not edit prose, BibTeX, or claims unless the user separately asks for the correction.

    line 23

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Citation Verification

Verify each reference as both a bibliographic record and evidence for the sentence that cites it.

  1. Read the manuscript, bibliography, and any existing Evidence ID records. Build a list of unique citation keys and each location where a specific scientific claim relies on one.
  2. Resolve metadata through primary or authoritative scholarly records (for example DOI registration, publisher, conference proceedings, arXiv for its own version, or Research Core). Check title, authors, venue, year, identifier, and the cited version.
  3. For a claim-dependent citation, inspect the source itself and record the supporting section, table, figure, or page when available. Metadata alone does not verify that the source supports a claim.
  4. Mark every entry verified, metadata-only, claim-not-supported, unresolved, conflicted, or replace/remove. Never infer missing metadata or fabricate a replacement citation.
  5. For consequential sources, preserve the canonical identifier and version, retrieval date/route, exact support location, and local artifact/hash when one exists. Obsidian or another note system may link the record, but it does not replace the original source or verification status.
  6. Record results in docs/11_pre_submission_audit.md under “引文核验”; preserve uncertain entries for author decision.

Rules

  • Prefer the canonical DOI/publisher record for final metadata; record preprint-versus-publication differences explicitly.
  • A literature search result, abstract-only record, or citation count can discover a source but cannot substantiate a detailed technical claim.
  • Keep discovery, bibliographic verification, lawful full-text acquisition, local parsing, and note storage as distinct provenance steps. Report a missing capability rather than silently changing the evidence route.
  • Do not require a particular search engine, citation count, or fixed author-year tolerance.
  • Do not edit prose, BibTeX, or claims unless the user separately asks for the correction.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.