acknowledgement
Generic, operator-configurable acknowledgement boilerplate added to a produced paper: an automated-system disclosure (on by default), a funding line, and personal thanks. Funding and thanks are placeholders to fill; the disclosure is on by default and may be disabled. Invent
$ npx -y skills add frenzymath/Danus --agent claude-codeHow it fires
How this agent 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.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Generic, operator-configurable acknowledgement boilerplate added to a produced paper: an automated-system disclosure (on by default), a funding line, and personal thanks. Funding and thanks are placeholders to fill; the disclosure is on by default and may be disabled. Invent
Agent definition
acknowledgement.mdname: acknowledgement_boilerplate
description: "Generic, operator-configurable acknowledgement boilerplate added to a produced paper: an automated-system disclosure (on by default), a funding line, and personal thanks. Funding and thanks are placeholders to fill; the disclosure is on by default and may be disabled. Invent nothing."
Acknowledgement boilerplate (operator-configurable)
This file is the paper-invariant acknowledgement block the writer adds to a produced paper. The **automated-system disclosure (1) is ON by default**; the **funding (2) and personal-thanks (3) blocks are opt-in placeholders**. The writer/ reviser copies in only what the operator has configured (in `PROJECT_BRIEF.md` or at interview time) and never invents a name, a grant number, or an affiliation. If a placeholder is left unfilled, leave it as a visible `\note{[ack/blocker] ...}` flag rather than guessing.
Placement follows `style/PAPER_STRUCTURE.md` §5.7 and depends on the paper. The neutral default is an unnumbered `\section*{Acknowledgements}` after the last body section (or appendices) and before the bibliography. A first-page unnumbered footnote, or — in a long, introduction-heavy paper — a final `\subsection*{Acknowledgements}` at the end of the Introduction, are acceptable alternatives when the operator's house style prefers one. Use a single, consistent placement per paper; never emit two acknowledgement blocks.
(1) Automated-system disclosure (ON by default; the operator may disable it)
A paper produced by this system **discloses** that fact by default: the system is an automated, AI-driven proof-search and verification pipeline, and the integrity-correct default is to say so plainly, in the open. The operator may turn the disclosure off for a given paper, but the default is **ON**.
Name the system plainly — by default **"the Danus system"** (the public name of this open-source project; a fork may substitute its own system name). The disclosure names the system only; it never exposes an internal codename, a development-team roster, a fact id, a hash, a file path, or any other internal pipeline identifier (those remain forbidden — see `roles/AGENTS.md` PRIME DIRECTIVE item 6).
Put the disclosure in **two to three visible places** — this is the whole point, so it must be readable text, never a LaTeX comment (a comment discloses nothing):
- **Abstract** (last sentence):
`The main result of this paper was obtained with the assistance of the Danus system, an automated proof-search and verification system.`
- **A Remark** near the acknowledgement (requires `\newtheorem{rem}[thm]{Remark}`):
\begin{rem}
The main result of this paper was obtained with the assistance of the Danus system, an automated proof-search and verification system.[SYSTEM CITATION] [VERIFICATION STATEMENT] Because automated systems have limitations, it is possible that we have missed related references in the literature, and we welcome comments from experts.
\end{rem}- **The acknowledgements section** (one sentence), when the operator prefers the
disclosure to also live there.
`[SYSTEM CITATION]` is an OPTIONAL `\cite{...}` to a published description of the system, included only if the operator supplies a real, verified reference. Never fabricate one or hardcode an author list; omit it otherwise.
`[VERIFICATION STATEMENT]` is a placeholder the operator fills with a **truthful** description of what was actually checked, and only if it is true — e.g. "The proof was independently re-verified by the system's verifier." Do **not** ship the re-verification claim by default: if the operator supplies no true verification statement, omit that sentence (leave a `\note{[ack/blocker] verification statement?]}` flag) rather than asserting a check that did not happen.
If the operator disables the disclosure for this paper, omit both the abstract sentence and the Remark.
(2) Funding line (placeholder)
The first acknowledgement sentence, when funding applies, is the funding statement. Use the operator-supplied text verbatim; do not fabricate a grant number or agency.
\section*{Acknowledgements}
[FUNDING ACKNOWLEDGEMENT]`[FUNDING ACKNOWLEDGEMENT]` is replaced with the operator's exact funding sentence (for example, "The author was partially supported by [GRANT]."). If the operator says there is no funding to acknowledge, omit this sentence.
(3) Personal thanks (placeholder)
After the funding line, append the operator-supplied thanks verbatim:
[PERSONAL THANKS]
`[PERSONAL THANKS]` is replaced with the operator's exact text (thanks to named colleagues, hosts, referees, etc.). Names come only from the operator — never from the system, the fact graph, or inference. If the operator gives no thanks, omit this sentence.
Notes for the writer/reviser
- The funding (2) and personal-thanks (3) blocks are configuration: add a block
only when the operator has supplied its content. The automated-system disclosure (1) is **ON by default** — include it unless the operator disabled it for this paper.
- Never emit an internal codename, a development-team roster, a fact id, a hash,
or any other pipeline identifier in the visible acknowledgement. (Naming the system itself — "the Danus system" — for the default disclosure is allowed; that is the public project name, not an internal identifier.)
- If the automated-system note is enabled but you have no published reference to
cite for the system, do not invent a `\cite{}` or `\bibitem` for it — the note stands on its own without a citation.
Read more
name: acknowledgement_boilerplate description: "Generic, operator-configurable acknowledgement boilerplate added to a produced paper: an automated-system disclosure (on by default), a funding line, and personal thanks. Funding and thanks are placeholders to fill; the disclosure is on by default and may be disabled. Invent nothing."
Acknowledgement boilerplate (operator-configurable)
This file is the paper-invariant acknowledgement block the writer adds to a produced paper. The **automated-system disclosure (1) is ON by default**; the **funding (2) and personal-thanks (3) blocks are opt-in placeholders**. The writer/ reviser copies in only what the operator has configured (in `PROJECT_BRIEF.md` or at interview time) and never invents a name, a grant number, or an affiliation. If a placeholder is left unfilled, leave it as a visible `\note{[ack/blocker] ...}` flag rather than guessing.
Placement follows `style/PAPER_STRUCTURE.md` §5.7 and depends on the paper. The neutral default is an unnumbered `\section*{Acknowledgements}` after the last body section (or appendices) and before the bibliography. A first-page unnumbered footnote, or — in a long, introduction-heavy paper — a final `\subsection*{Acknowledgements}` at the end of the Introduction, are acceptable alternatives when the operator's house style prefers one. Use a single, consistent placement per paper; never emit two acknowledgement blocks.
(1) Automated-system disclosure (ON by default; the operator may disable it)
A paper produced by this system **discloses** that fact by default: the system is an automated, AI-driven proof-search and verification pipeline, and the integrity-correct default is to say so plainly, in the open. The operator may turn the disclosure off for a given paper, but the default is **ON**.
Name the system plainly — by default **"the Danus system"** (the public name of this open-source project; a fork may substitute its own system name). The disclosure names the system only; it never exposes an internal codename, a development-team roster, a fact id, a hash, a file path, or any other internal pipeline identifier (those remain forbidden — see `roles/AGENTS.md` PRIME DIRECTIVE item 6).
Put the disclosure in **two to three visible places** — this is the whole point, so it must be readable text, never a LaTeX comment (a comment discloses nothing):
- **Abstract** (last sentence):
`The main result of this paper was obtained with the assistance of the Danus system, an automated proof-search and verification system.`
- **A Remark** near the acknowledgement (requires `\newtheorem{rem}[thm]{Remark}`):
\begin{rem}
The main result of this paper was obtained with the assistance of the Danus system, an automated proof-search and verification system.[SYSTEM CITATION] [VERIFICATION STATEMENT] Because automated systems have limitations, it is possible that we have missed related references in the literature, and we welcome comments from experts.
\end{rem}- **The acknowledgements section** (one sentence), when the operator prefers the
disclosure to also live there.
`[SYSTEM CITATION]` is an OPTIONAL `\cite{...}` to a published description of the system, included only if the operator supplies a real, verified reference. Never fabricate one or hardcode an author list; omit it otherwise.
`[VERIFICATION STATEMENT]` is a placeholder the operator fills with a **truthful** description of what was actually checked, and only if it is true — e.g. "The proof was independently re-verified by the system's verifier." Do **not** ship the re-verification claim by default: if the operator supplies no true verification statement, omit that sentence (leave a `\note{[ack/blocker] verification statement?]}` flag) rather than asserting a check that did not happen.
If the operator disables the disclosure for this paper, omit both the abstract sentence and the Remark.
(2) Funding line (placeholder)
The first acknowledgement sentence, when funding applies, is the funding statement. Use the operator-supplied text verbatim; do not fabricate a grant number or agency.
\section*{Acknowledgements}
[FUNDING ACKNOWLEDGEMENT]`[FUNDING ACKNOWLEDGEMENT]` is replaced with the operator's exact funding sentence (for example, "The author was partially supported by [GRANT]."). If the operator says there is no funding to acknowledge, omit this sentence.
(3) Personal thanks (placeholder)
After the funding line, append the operator-supplied thanks verbatim:
[PERSONAL THANKS]
`[PERSONAL THANKS]` is replaced with the operator's exact text (thanks to named colleagues, hosts, referees, etc.). Names come only from the operator — never from the system, the fact graph, or inference. If the operator gives no thanks, omit this sentence.
Notes for the writer/reviser
- The funding (2) and personal-thanks (3) blocks are configuration: add a block
only when the operator has supplied its content. The automated-system disclosure (1) is **ON by default** — include it unless the operator disabled it for this paper.
- Never emit an internal codename, a development-team roster, a fact id, a hash,
or any other pipeline identifier in the visible acknowledgement. (Naming the system itself — "the Danus system" — for the default disclosure is allowed; that is the public project name, not an internal identifier.)
- If the automated-system note is enabled but you have no published reference to
cite for the system, do not invent a `\cite{}` or `\bibitem` for it — the note stands on its own without a citation.
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 agents on danus.
- main_agent
Read this at the top of every session before acting on Danus. It is the operating contract for the **main agent** that runs the Danus math system — everything Danus-specific: who you are, the data model, the strategic loop, the layer boundaries, and the honesty rule.
Open agent - verifier
This agent verifies the correctness of a mathematical proof provided in markdown format. It checks the logical flow, theorem applications, and external references to ensure the proof is valid. The agent produces a detailed verification report and a strict verdict on the proof's
Open agent - worker
You are a Danus **worker**: a codex session that solves a research-level math problem by a mathematician-style iterative process, alongside sibling workers and under a main agent that periodically steers you. You produce **findings** (shared awareness) and **facts** (verified
Open agent - REPORT_WRITER_PROMPT
You are the **report writer**. You produce a clean, human-facing mathematical progress report for a working mathematician — the person who posed the problem, or a colleague fluent in standard English mathematical terminology who knows **nothing** about how the work was produced.
Open agent - PROBLEM
**Project:** `odd-sum` (toy example)
Open agent - fact_odd_recurrence
For every integer $n \ge 1$, let $S(n) = 1 + 3 + 5 + \cdots + (2n-1)$ denote the sum of the first $n$ positive odd numbers, with $S(1) = 1$. Then $S(n+1) = S(n) + (2n+1)$ for all $n \ge 1$.
Open agent

