Agent skill

Check Referenced Statements

by frenzymath in frenzymath/Danus

Validate externally referenced theorems by querying arXiv theorem search first and Codex's built-in web search second.

Apache-2.0Auto-check passedResearch & Science

Install Check Referenced Statements

skills CLI
$ npx skills add frenzymath/Danus --skill check-referenced-statements -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install frenzymath/Danus check-referenced-statements --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/frenzymath/Danus.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agents/skills/verify/check-referenced-statements .claude/skills/check-referenced-statements && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
check-referenced-statements
GitHub stars
476
Token cost
~852 tokens
SKILL.md length
393 words
Files
2
Skills in repo
16
Repo updated
First seen
Licence
Apache-2.0

At a glance

Validate externally referenced theorems by querying arXiv theorem search first and Codex's built-in web search second.

  • Works in 11 steps: Query search_arxiv_theorems using the… → Inspect returned results and compare… → Expand the definitions and terminology… → …
  • A markdown proof cites statements from external papers
  • SKILL.md covers Input Contract, Procedure, Output Contract and Tools
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Check Referenced Statements is an agent skill from frenzymath/Danus. Validate externally referenced theorems by querying arXiv theorem search first and Codex's built-in web search second. Use when a markdown proof cites statements from external papers.

Its SKILL.md is about 850 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Research & Science, covering Academic paper search and Web search. It works with arXiv. The repository describes itself as: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory. The licence is Apache-2.0.

When your agent uses it

  • A markdown proof cites statements from external papers
  • Tasks that involve Academic paper search
  • Tasks that involve Web search

Example prompts

  • “/check-referenced-statements”

Workflow steps

11 steps, taken from the first numbered list in SKILL.md.

  1. Query search_arxiv_theorems using the full referenced statement as query.
  2. Inspect returned results and compare theorem text directly to the referenced statement in reasoning.
  3. Expand the definitions and terminology appearing in the cited statement using the cited paper's context before deciding whether the…
  4. Check whether the same words in the current proof mean the same thing as they do in the cited paper. In mathematics, identical words can…
  5. Accept as matched and applicable only when both are true
  6. If the theorem exists but the current proof uses different definitions, hypotheses, ambient objects, or a subtly different defining…
  7. If the proof uses the cited statement to derive further conclusions, verify that transition too: a hand-wavy specialization or…
  8. If no match is found, use Codex's built-in web search with the same statement text.
  9. If still not found, emit a critical error
  10. When a step cites an internal fact_id (16 hex characters) rather than an external paper, apply the verifier contract's P3-supplement chain…
  11. Keep each reference check in context for the synthesis step (you persist nothing —

What it can do on your machine

Read from SKILL.md and the folder at commit 6d92e8d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Check Referenced Statements loads about 852 tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 393 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~852

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from frenzymath/Danus at commit 6d92e8d, republished under its Apache-2.0 licence (© frenzymath). 393 words, ~852 tokens.

Download SKILL.mdSave it as .claude/skills/check-referenced-statements/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
check-referenced-statements
description
Validate externally referenced theorems by querying arXiv theorem search first and Codex's built-in web search second. Use when a markdown proof cites statements from external papers.

Check Referenced Statements

Validate every external-paper reference used in the proof.

Input Contract

For each cited external theorem/lemma/definition:

  • location where it is used,
  • the full referenced statement text.

Procedure

  1. Query search_arxiv_theorems using the full referenced statement as query.
  2. Inspect returned results and compare theorem text directly to the referenced statement in reasoning.
  3. Expand the definitions and terminology appearing in the cited statement using the cited paper's context before deciding whether the theorem applies.
  4. Check whether the same words in the current proof mean the same thing as they do in the cited paper. In mathematics, identical words can carry different definitions in different contexts. Distinguish similar-looking definitions: compare their exact formulas, notation, and quantifiers; do not collapse two just because the names or formulas look close.
  5. Accept as matched and applicable only when both are true:
    • the result clearly corresponds to the cited statement,
    • the contextual definitions and hypotheses align with the current problem.
  6. If the theorem exists but the current proof uses different definitions, hypotheses, ambient objects, or a subtly different defining formula, record a critical error for incorrect application.
  7. If the proof uses the cited statement to derive further conclusions, verify that transition too: a hand-wavy specialization or instantiation is a gap; a logically invalid transition is a critical_error; if it deduces one property from another, compare their exact defining formulas before accepting.
  8. If no match is found, use Codex's built-in web search with the same statement text.
  9. If still not found, emit a critical error:
    • location: where the citation is used,
    • issue: referenced theorem appears non-existent or incorrectly cited.
  10. When a step cites an internal fact_id (16 hex characters) rather than an external paper, apply the verifier contract's P3-supplement chain check (agents/contracts/verifier.md): read the cited fact from the project fact graph and, if its own statement carries an unproven conditional premise, record the inherited defect as a critical_error. Read and apply the wording from the contract; do not fork it here.
  11. Keep each reference check in context for the synthesis step (you persist nothing — the verifier is stateless).
Show full SKILL.md (41 more words)Show less

Do not rely on dedicated comparison utility code; perform comparison through careful reasoning.

Output Contract

Produce one record per reference check, kept in context for synthesis:

json
{
  "location": "Lemma 2",
  "referenced_statement": "Exact statement text",
  "context_expansion": "In the cited paper, 'regular' means regular with respect to the valuation topology.",
  "arxiv_match_found": false,
  "web_match_found": false,
  "critical_error": {
    "location": "Lemma 2",
    "issue": "Referenced external theorem was not found in arXiv search or Codex built-in web search."
  }
}

Tools

  • search_arxiv_theorems
  • Codex's built-in web search

(Findings stay in context for synthesis — nothing is persisted.)

© frenzymath, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in agents/skills/verify/check-referenced-statements of frenzymath/Danus.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 6d92e8d

Compare with similar skills

Check Referenced Statements next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Check Referenced Statements compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Check Referenced Statements this skillfrenzymath/Danus476—~852Automated safety check: PassApache-2.0
Literature Review AgentAr9av/PaperOrchestra6791 repos~5.2kAutomated safety check: PassCustom licence
Argo Search and Verificationtaxueseek/argo188—~1.2kAutomated safety check: PassMIT
Research Lookupneflibata-feng/MyArxiv-Agent1262 repos~4.1kAutomated safety check: NotesMIT
Superlearnraiyanyahya/Superlearn122—~6.2kAutomated safety check: PassMIT
Research ProtocolAedelon/claude-code-blueprint120—~1.1kAutomated safety check: PassCustom licence

Similar skills

  • Literature Review Agent

    Ar9av/PaperOrchestra

    Step 3 of the PaperOrchestra pipeline (arXiv:2604.05018). An agent skill from Ar9av/PaperOrchestra.

    679 GitHub starsUsed in 1 repo~5.2k tokens
    Research & ScienceAuto-check passed
  • Unified web search, page fetching and evidence checking across hundreds of sources, with result verification, a research-dossier mode and vertical search engines.

    188 GitHub stars~1.2k tokensUpdated 4 days ago
    Research & ScienceAuto-check passed
  • Research Lookup

    neflibata-feng/MyArxiv-Agent

    Look up current research information using the Parallel Chat API (primary) or Perplexity sonar-pro-search (academic paper searches).

    126 GitHub starsUsed in 2 repos~4.1k tokens
    Research & ScienceAuto-check: notes
  • Superlearn

    raiyanyahya/Superlearn

    Build an interactive learning board on any topic. An agent skill from raiyanyahya/Superlearn.

    122 GitHub stars~6.2k tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed
  • Research Protocol

    Aedelon/claude-code-blueprint

    Conduct rigorous research with proper citations (DOI, arXiv, PMID) and source triangulation.

    120 GitHub stars~1.1k tokensUpdated 7 mo ago
    Research & ScienceAuto-check passed
  • Insane Search

    fivetaku/gptaku-plugins-codex

    Adaptive access for blocked websites — tries every method until one works.

    128 GitHub stars~5.6k tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

More from frenzymath/Danus

All 16 skills in this repo
  • Construct candidate counterexamples to test a proposed conjecture, lemma, or intermediate claim by keeping the assumptions true while making the claimed conclusion fail.

    476 GitHub stars~790 tokensUpdated 1 mo ago
    Auto-check passed
  • Construct Toy Examples

    frenzymath/Danus

    Generate and analyze simpler examples that satisfy both the assumptions and the conclusion of a theorem statement or subgoal.

    476 GitHub stars~541 tokensUpdated 1 mo ago
    Auto-check passed
  • Direct Proving

    frenzymath/Danus

    Screen a decomposition plan by first trying to prove all of its subgoals directly, then identifying the key stuck points if the plan does not fully go through.

    476 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Identify Key Failures

    frenzymath/Danus

    Synthesize the common stuck points across failed decomposition plans.

    476 GitHub stars~586 tokensUpdated 1 mo ago
    Auto-check passed
  • Derive immediate mathematical consequences from a theorem statement or subgoal.

    476 GitHub stars~587 tokensUpdated 1 mo ago
    Auto-check passed
  • Propose multiple subgoal decomposition plans for the current theorem using the information already gathered.

    476 GitHub stars~580 tokensUpdated 1 mo ago
    Auto-check passed

Works with

Questions about Check Referenced Statements

What does Check Referenced Statements do?

Validate externally referenced theorems by querying arXiv theorem search first and Codex's built-in web search second. Check Referenced Statements is an agent skill from frenzymath/Danus. Validate externally referenced theorems by querying arXiv theorem search first and Codex's built-in web search second.

When should I use Check Referenced Statements?

Check Referenced Statements fits situations like: A markdown proof cites statements from external papers; tasks that involve Academic paper search; tasks that involve Web search.

How do I install Check Referenced Statements in Claude Code?

Run `npx skills add frenzymath/Danus --skill check-referenced-statements -a claude-code`. Or copy the skill folder (agents/skills/verify/check-referenced-statements in frenzymath/Danus) into .claude/skills/check-referenced-statements in your project. Claude Code loads it when a task matches its description.

How do I install Check Referenced Statements in Codex?

Run `npx skills add frenzymath/Danus --skill check-referenced-statements -a codex`. Or copy the skill folder (agents/skills/verify/check-referenced-statements in frenzymath/Danus) into .agents/skills/check-referenced-statements in your project. Codex loads it when a task matches its description.

Can I use Check Referenced Statements in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add frenzymath/Danus --skill check-referenced-statements -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/check-referenced-statements, .gemini/skills/check-referenced-statements, .github/skills/check-referenced-statements and .opencode/skills/check-referenced-statements in your project.

What does Check Referenced Statements need to run?

SKILL.md names no scripts, command-line tools or credentials: Check Referenced Statements is instructions for the agent only.

Does Check Referenced Statements access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Check Referenced Statements safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Check Referenced Statements use?

Check Referenced Statements is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Check Referenced Statements use?

About 852 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Check Referenced Statements?

Skills that share tags, products or a category with Check Referenced Statements: Literature Review Agent (Ar9av/PaperOrchestra, 679 stars), Argo Search and Verification (taxueseek/argo, 188 stars), Research Lookup (neflibata-feng/MyArxiv-Agent, 126 stars) and Superlearn (raiyanyahya/Superlearn, 122 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Check Referenced Statements?

frenzymath (a GitHub organization) maintains it in frenzymath/Danus, which has 476 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on August 27, 2026.

Source: frenzymath/Danus on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.