/check-referenced-statements
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.
$ npx -y skills add frenzymath/Danus --skill check-referenced-statements --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/check-referenced-statements
Context preview
The summary Claude sees to decide when to auto-load this skill.
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.
SKILL.md
check-referenced-statements.SKILL.mdname: 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).
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:
{
"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.)
Read more
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).
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:
{
"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.)
Danus orchestrates mathematical reasoning agents with fact-graph memory. A main agent (Claude Code) steers a swarm of autonomous codex workers that prove; a cold-start verifier is the sole authority on correctness: a result becomes real only once it passes.
Other skills on danus.
- /consult
Consult a strong reasoning model for strategy — feed it the current elaboration, take its reply as the next master_guidance, and dispatch workers from it. This is the main agent's high-intelligence step (workers prove; the consult decomposes and steers). Runs over the gpt_pro
Open skill - /elaboration
Write a high-signal-to-noise mathematical progress synthesis of a project from the shared stores (global memory + fact graph), following a fixed verdict→routes→interfaces→dangers→bridges template and a strict honesty discipline. Use it each strategic cycle, right before the
Open skill - /human-summary
Write a human-readable mathematical progress report (compiled PDF) on a project for the operator / the mathematician who posed the problem. This is NOT `elaboration` (dense input for the strategy consult) and NOT the dashboard. Render from the fact graph's verified
Open skill - /initialize
First-run setup interview for a Danus deployment. Run it on the FIRST session, whenever runtime/.danus-initialized is absent or OPERATOR.md is still the blank template, or when the operator asks to set up / initialize / onboard / re-configure. It greets the operator, explains
Open skill - /write-paper
Turn a project's verified fact graph into a publishable LaTeX paper in a configurable house style — a standalone amsart .tex with a real bibliography, compiled to PDF. Use when a project's target theorem is established and the operator wants the paper, or asks to
Open skill - /synthesize-verification-report
Aggregate all detected errors and gaps into the final verification report, apply strict accept/reject logic, and produce repair hints when rejected.
Open skill

