break-up-proposition
Break an existing proposition, theorem, or corollary into a labelled enumerate with separately signposted proofs while preserving its mathematics.
Skill by tdupu
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/tdupu-break-up-proposition
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/break-up-proposition
What's inside
- Skill name
break-up-proposition- Description
- Break an existing proposition, theorem, or corollary into a labelled enumerate with separately signposted proofs while preserving its mathematics. Use for a style-driven decomposition; adding new items is optional and must be evidence-backed.
- License
- GPL-3.0
- Instructions
- 105 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# break-up-proposition
Use this leaf after `using-latexpowers` has resolved the canonical manuscript
and target region. It rewrites one existing theorem-class statement into an
enumerated interface and keeps the proof readable and traceable. It is a
refactoring skill: it does not turn an unproved idea into a result and does
not require new items when the existing statement already contains the right
claims.
## Scope and stop conditions
- Work on one proposition at a time in the declared canonical `.tex` file.
- Preserve the proposition's hypotheses, conclusions, theorem label, proof,
citations, human markers, and surrounding order unless the user explicitly
changes them.
- Add an item only when the user requests it or the evidence and surrounding
manuscript establish a genuinely separate conclusion. Record its source and
proof obligation before editing.
- Stop and route to `using-mathpowers` or `write-proposition` if a proposed
item needs a new proof, changes the quantifiers, or is not supported by the
existing argument. Do not silently strengthen or weaken the result.
- Stop if the statement's parts are actually separate named theorems. Split
those into separate theorem-class environments instead of manufacturing an
enumeration.
## Before editing
1. Read the repository's `WRITERS.md`, `STYLE.md`, `LATEX.md`, and any local
powers policy through `using-latexpowers`. Resolve the canonical file and
the exact proposition region; do not edit a generated or sibling variant.
2. Read the complete proposition and proof, then search the manuscript for
its theorem label, every existing part reference, and nearby labels. Run
the repository's label/reference checker before the edit when available.
3. Make an item map: one semantic conclusion per item, the evidence or proof
paragraph that establishes it, and every site that will cite it. Preserve
the original order unless there is a stated reason to reorder it.
4. Choose stable semantic item labels such as
`item:pc-invariance` or `item:branch-control`; never use labels whose only
meaning is an ordinal. Check that every new label is unique.
## Statement transformation
Keep the theorem-class environment limited to the hypotheses and the
conclusion. When the proposition has multiple conclusions, use an explicit
enumerate:
```tex
\begin{proposition}\label{prop:example}
Assume ... . Then:
\begin{enumerate}
\item ... .\label{item:first-conclusion}
\item ... .\label{item:second-conclusion}
\end{enumerate}
\end{proposition}
```
Each item must be independently meaningful and must state a conclusion, not
motivation, unpacking, or a proof step. Keep explanatory consequences outside
the theorem-class environment unless they are themselves part of the claimed
result. If there is only one conclusion after the refactor, do not enumerate
merely to create an item number.
Item labels are an interface. Update every consumer in the same change to use
`\eqref{item:<slug>}`. Never cite a part by a literal `(1)`, `(2)`, or by an
unstable ordinal. Preserve the proposition's top-level label and update any
old part labels deliberately; do not leave aliases or duplicate labels behind.
## Proof transformation
Use one `proof` environment for the proposition unless the repository's style
contract requires another form. Inside it, give a signpost and proof for each
enumerated item, in item order:
```tex
\begin{proof}
\noindent\emph{Proof of \eqref{item:first-conclusion}.}
...
\noindent\emph{Proof of \eqref{item:second-conclusion}.}
...
\end{proof}
```
The `\eqref` renders the current item number while keeping the proof tied to
the stable label. Each signposted block must discharge exactly its item. A
later block may cite an earlier item with `\eqref{item:<slug>}`; state that
dependency rather than repeating an unproved assertion. Give a short proof
for an immediate item or move it out of the proposition; never leave an
enumerated item without a corresponding proof signpost.
## After editing
Review the diff item by item: the enumerated statement is mathematically
equivalent to the original unless an explicitly authorized, evidence-backed
item was added; every item has a proof block; no proof paragraph or negative
result was dropped; and all part references use the new labels. Re-run the
label/reference checker, the repository's LaTeX/style checks, and the
canonical build. Inspect the source as well as the PDF because compilation
cannot detect an omitted conclusion or a proof attached to the wrong item.
Report the target file, the item-to-proof map, any added items and their
evidence, references updated, and the validation results. Do not commit or
sync as part of this leaf unless the user separately authorizes that action.From tdupu/agent-skills-public, GPL-3.0.
More from tdupu/agent-skills-public
- 0.570score
assemble-recording-series
tdupu
Assemble one lecture or talk video from a folder of raw takes, whatever the capture tool wrote - flat screen-capture files, or per-session folders with the…
SkillAFreshness: AClaude Code +9 - 0.570score
check-paragraph
tdupu
Judge ONE paragraph of prose (LaTeX allowed) as its stated reader and return a fixed six-line verdict — topic sentence, one idea, reader can follow, claim…
SkillAFreshness: AClaude Code +9 - 0.565score
check-documentation-policy
tdupu
Audit mathcity documentation against POLICY-documentation.md.
SkillAFreshness: AClaude Code +9 - 0.565score
behavior-verify
tdupu
Use when an edit to a skill, an instruction file, or a prompt has to be shown to have changed the agent behavior it was meant to fix.
SkillAFreshness: AClaude Code +9 - 0.565score
check-citations
tdupu
Read-only citation audit for .tex files.
SkillAFreshness: AClaude Code +9 - 0.565score
check-grant-format
tdupu
Audit an NSF proposal folder against Grants/GRANT-FORMAT.md (page limits, fonts, margins, required headings, no URLs in the description, prior-support items…
SkillAFreshness: AClaude Code +9 - 0.565score
check-grant-style
tdupu
Audit an NSF Project Description and Summary against Grants/GRANT-STYLE.md (every project has a plan and names what is new; results in prose with citations…
SkillAFreshness: AClaude Code +9 - 0.565score
check-latex
tdupu
Produce the evidence block the human adjudicator needs to approve or reject a notes.tex (or any notes-tier .tex) change before push/merge.
SkillAFreshness: AClaude Code +9 - 0.565score
check-latex-hygiene
tdupu
Audit LaTeX beads, branches, or .tex diffs against the LaTeX Subdomain Policy (mathcity/subdomains/latex/POLICY.md, LX-rules).
SkillAFreshness: AClaude Code +9 - 0.565score
check-lmfdb-hygiene
tdupu
Audit an LMFDB-type bead, diff, experiment proposal, or live type against the LMFDB Subdomain Policy (mathcity/subdomains/lmfdb/POLICY.md) — labels valid…
SkillAFreshness: AClaude Code +9 - 0.564score
behavior-cause
tdupu
Use when a reproduced agent behavior has to be traced to the artifacts whose text produced it.
SkillAFreshness: AClaude Code +9 - 0.561score
add-figure
tdupu
Insert a verified mathematical graphic into the declared LaTeX manuscript at the passage it explains, with a substantive caption, unique label, prose…
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 14, 2026 (14 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- GPL-3.0
- Repository
- github.com/tdupu/agent-skills-public
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from tdupu
- 0.570score
assemble-recording-series
tdupu
Assemble one lecture or talk video from a folder of raw takes, whatever the capture tool wrote - flat screen-capture files, or per-session folders with the…
SkillAFreshness: AClaude Code +9 - 0.570score
check-paragraph
tdupu
Judge ONE paragraph of prose (LaTeX allowed) as its stated reader and return a fixed six-line verdict — topic sentence, one idea, reader can follow, claim…
SkillAFreshness: AClaude Code +9 - 0.565score
check-citations
tdupu
Read-only citation audit for .tex files.
SkillAFreshness: AClaude Code +9 - 0.565score
behavior-verify
tdupu
Use when an edit to a skill, an instruction file, or a prompt has to be shown to have changed the agent behavior it was meant to fix.
SkillAFreshness: AClaude Code +9 - 0.565score
check-documentation-policy
tdupu
Audit mathcity documentation against POLICY-documentation.md.
SkillAFreshness: AClaude Code +9 - 0.565score
check-grant-format
tdupu
Audit an NSF proposal folder against Grants/GRANT-FORMAT.md (page limits, fonts, margins, required headings, no URLs in the description, prior-support items…
SkillAFreshness: AClaude Code +9
Cite this page
break-up-proposition skill. Agent Mart. https://agentmart.dev/skills/tdupu-break-up-proposition (last updated 2026-10-24)