Agent skill

Math Proof

by flonat in flonat/flonat-research

Write clear, detailed mathematical proofs for academic papers.

MITAuto-check passed

Install Math Proof

skills CLI
$ npx skills add flonat/flonat-research --skill math-proof -a claude-code

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

GitHub CLI
$ gh skill install flonat/flonat-research math-proof --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/flonat/flonat-research.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/math-proof .claude/skills/math-proof && 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
math-proof
GitHub stars
145
Used in
1 other repo
Token cost
~2.6k tokens
SKILL.md length
1,475 words
Files
1
Skills in repo
83
Repo updated
First seen
Licence
MIT

At a glance

Write clear, detailed mathematical proofs for academic papers.

  • Works in 5 steps: Setup section → Numbered steps → Connecting steps → …
  • The user asks to prove a result
  • SKILL.md covers Trigger phrases, Core principles, Proof structure and Common patterns, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Math Proof is an agent skill from flonat/flonat-research. Write clear, detailed mathematical proofs for academic papers. Use when the user asks to prove a result, derive an equation, justify a claim analytically, or expand a proof sketch into a full proof. Also trigger on "prove", "show analytically", "derive", "justify mathematically", or "write a proof".

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Shareable Claude Code + Codex infrastructure for PhD researchers — skills, agents, hooks, and rules for academic workflows. The licence is MIT.

When your agent uses it

  • The user asks to prove a result
  • Derive an equation
  • Justify a claim analytically
  • Expand a proof sketch into a full proof

Example prompts

  • “show analytically”
  • “derive”
  • “justify mathematically”
  • “/math-proof”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Setup section
  2. Numbered steps
  3. Connecting steps
  4. Edge cases and case analysis
  5. QED

What it can do on your machine

Read from SKILL.md and the folder at commit da27600. 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.

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

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    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

Math Proof loads about 2.6k tokens when it runs. Until then it costs about 78 tokens; SKILL.md has 1,475 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~78
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k

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 flonat/flonat-research at commit da27600, republished under its MIT licence (© flonat). 1,475 words, ~2,576 tokens.

Download SKILL.mdSave it as .claude/skills/math-proof/SKILL.md (or your agent's skills folder).
name
math-proof
description
Write clear, detailed mathematical proofs for academic papers. Use when the user asks to prove a result, derive an equation, justify a claim analytically, or expand a proof sketch into a full proof. Also trigger on "prove", "show analytically", "derive", "justify mathematically", or "write a proof".
author
Moran Koren <korenmor@bgu.ac.il> (Ben-Gurion University of the Negev)

Author: Moran Koren, Ben-Gurion University of the Negev (korenmor@bgu.ac.il). Part of the Theorist Toolbox.

Math proof

Write rigorous mathematical proofs suitable for peer-reviewed academic papers. Every step should be explicit enough that a reader can verify it without filling in gaps. The proof must be a complete proof, not a proof outline — each step should be carefully explained and documented.

Trigger phrases

  • math-proof
  • "prove this"
  • "show analytically"
  • "derive this result"
  • "justify mathematically"
  • "write a proof"
  • "expand this proof"

Core principles

No gaps between steps

Every transition from one equation to the next must be justified. If you use the quotient rule, say so. If you substitute a definition, point to which definition. If a sign is negative, explain why. The reader should never need to work out an intermediate step on their own.

Bad: $$\frac{d}{d\rho}\frac{n_G}{n_B} = \frac{2q-1}{n_B^2} > 0.$$

Good: We compute $\frac{d}{d\rho}(n_G/n_B)$ using the quotient rule. First, the derivatives: $$\frac{dn_G}{d\rho} = q, \qquad \frac{dn_B}{d\rho} = 1-q.$$ Applying the quotient rule: $$\frac{d}{d\rho}\frac{n_G}{n_B} = \frac{q \cdot n_B - (1-q) \cdot n_G}{n_B^2}.$$ Expanding the numerator: $$q[\rho + (1-\rho)q] - (1-q)[\rho + (1-\rho)(1-q)] = \rho(2q-1) + (1-\rho)(2q-1) = 2q-1.$$ Since $q > 1/2$, this is positive.

State what you want to show before showing it

Open each step with a sentence explaining the goal: "We want to show that $t$ decreases with $\rho$." Then deliver the proof. The reader should know where you are headed before wading into algebra.

Sign every term

When a derivative or expression appears, immediately state its sign and why. Do not leave sign determination as an exercise. If a quantity is negative because it is a log of a number less than 1, say so explicitly.

Bridge definitions to usage

When you define a quantity (like a threshold $t$) and then use it in a derivative, explain the connection. Do not jump from "$Y \geq$ [some expression]" to "$t(K,\rho) =$ [formula]" without a sentence like: "Define $t(K,\rho)$ as the minimum number of yes votes required for allocation, i.e., the smallest integer $Y$ satisfying this inequality."

Show intermediate algebra

Expand products, collect terms, cancel factors. Do not skip from a quotient rule setup to a simplified final form. Show at least one intermediate line where terms are expanded but not yet simplified.

Explain why results are intuitive

After a formal derivation, add one sentence of economic or mathematical intuition. "The threshold drops because no votes carry less information, so fewer yes votes suffice to outweigh them." This helps the reader connect the math to the model.

Self-contained proofs

The proof must be self-contained. Only cite well-known theorems — as a rule of thumb, a theorem must be famous enough to have a Wikipedia page or be taught in standard undergraduate courses. Do not invoke obscure or non-existent results. If you need a non-standard lemma, prove it inline.

Prove the general case, not examples

Never prove a claim only for specific cases or small examples and then assert it holds in general. If you verify a property for $n=1,2,3$, that is evidence, not a proof. You must provide an argument that covers the full generality of the claim. If the general proof is beyond reach, state this explicitly: "We have verified this for $n \leq 5$; the general case remains open."

Proof structure

1. Setup section
  • Define all notation up front
  • State the model primitives (distributions, parameters, decision rules)
  • Write the key quantities as explicit functions of the parameters
2. Numbered steps

Each step should:

  • Open with a plain-language statement of what will be shown
  • Derive the result with full intermediate algebra
  • Sign every derivative and explain the sign
  • Close with boundary values or limiting cases where helpful
3. Connecting steps

When one step feeds into the next, say so explicitly: "Substituting the result from Step 1 into the expression for $c_K$..." Do not assume the reader tracks which results carry forward.

4. Edge cases and case analysis

Enumerate all cases explicitly. If you claim a result holds "for all $x > 0$", check boundary behavior at $x = 0$ and $x \to \infty$. Do not silently assume non-degeneracy. If the proof requires case splits (e.g., $n$ even vs odd, or an angle acute vs obtuse), handle every case — do not prove one case and assert "the other case is similar" unless the symmetry is genuinely obvious and you state the symmetry.

5. QED

End with $\square$ and optionally a one-sentence summary of the full result.

Common patterns

Differentiating a ratio $f/g$

Always use the quotient rule explicitly: $$\frac{d}{dx}\frac{f}{g} = \frac{f'g - fg'}{g^2}.$$ Compute $f'$ and $g'$ separately first, then substitute.

Signing a log

If $\beta = \log(a/b)$ and you claim $\beta < 0$, show that $a < b$ first with an explicit inequality.

Chain rule through a CDF

When differentiating $P(Y \geq t(\rho))$ where both $t$ and the distribution parameter depend on $\rho$: $$\frac{d}{d\rho}P(Y \geq t) = \frac{\partial P}{\partial t}\cdot\frac{dt}{d\rho} + \frac{\partial P}{\partial p}\cdot\frac{dp}{d\rho}.$$ Sign each term separately, then discuss which dominates.

Discrete vs continuous

When a threshold must be an integer but you differentiate as if it were continuous, flag this: "Treating $t$ as continuous for tractability. In practice, $t$ is an integer, so small changes in $\rho$ can cause discrete jumps in $t$."

Inequality manipulation

When manipulating inequalities, explicitly justify every direction change. Common errors include: reversing inequality signs when multiplying by a negative quantity without noting it, flipping bounds when taking reciprocals without checking sign, and applying Jensen's inequality in the wrong direction (convex vs concave). After each inequality transformation, re-state which direction the inequality points and why.

Show full SKILL.md (577 more words)Show less
Induction

When using induction, state the base case, the inductive hypothesis, and the inductive step separately. In the inductive step, explicitly mark where the inductive hypothesis is applied. Do not conflate "holds for $n = k$" (hypothesis) with "holds for $n = k+1$" (what you are proving).

Format

  • Math delimiters depend on the output target. When writing into a .tex file, use $...$ (inline) and $$...$$ or \[...\] (display). When writing a .md deliverable, use \(...\) (inline) and \[...\] (display) — Markdown renderers (GitHub, VS Code, Obsidian) do not reliably parse $-delimited math. Never mix dollar and \(...\) forms within one file.
  • Use \triangleq for definitions, = for equalities
  • Label equations only if referenced later
  • Use \text{} for words inside math mode
  • Separate steps with ## headings
  • Write in markdown with LaTeX math
  • Do not use unicode symbols for math — use LaTeX commands

What NOT to do

  • Do not write "it is easy to see" or "it follows trivially" — if a step is truly trivial, prove it anyway; a reader or reviewer will assume you cannot explain what you cannot be bothered to write
  • Do not skip sign justifications
  • Do not introduce shorthand notation mid-proof without defining it (e.g., writing $b$ for $|\beta|$ without warning)
  • Do not combine multiple algebraic manipulations into one line
  • Do not end a step by restating the setup of the next step
  • Do not use "clearly" or "obviously"
  • Do not assert that one effect "dominates" another without proving it. If the comparison is ambiguous, say so. If you claim A > B, show A > B with an inequality, not with an intuitive argument about where distributions "concentrate"
  • Do not claim a monotonicity direction without either a derivative computation or a discrete comparison that establishes the sign
  • Distinguish between what is proved and what is conjectured. If a step relies on a plausible but unproved claim, flag it explicitly: "We conjecture that..." or "Numerical evidence suggests..."
  • Do not overgeneralize from examples. Proving a statement for specific values ($n = 1, 2, 3$) does not constitute a proof for all $n$ — it is evidence at best. If you cannot prove the general case, say so
  • Do not cite theorems or results that are not well-known. If a result would not be taught in a standard undergraduate course and does not have a Wikipedia article, either prove it from scratch or explicitly provide a verifiable reference. Fabricating citations is worse than having a longer proof
  • Do not silently omit edge cases or degenerate configurations. If your proof assumes $x \neq 0$ or a matrix is invertible, state and justify the assumption
  • If you are uncertain about a step, say so explicitly rather than producing a confident-sounding but potentially wrong argument. "We believe this holds because... but a complete proof requires..." is far better than a flawed claim presented as fact

Workflow

  1. Read the claim to be proved
  2. Identify the key quantities and their dependencies on parameters
  3. Plan the proof structure: what needs to be shown in what order
  4. Write the Setup section with all definitions
  5. Write each step with full algebra, signing every term
  6. Check that no step references a result not yet established
  7. Add intuition sentences after key derivations
  8. Verify boundary cases, edge cases, and limiting behavior
  9. Self-check: re-read the proof looking for gaps, unjustified sign claims, overgeneralizations from examples, and cited results that need verification. If the proof sketch came from the user, translate intuitions into precise statements — do not merely restate the sketch in fancier notation

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

Files

Just SKILL.md in skills/math-proof of flonat/flonat-research.

Open the folder on GitHubat commit da27600

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in flonat/flonat-research, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Math Proof 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.

Math Proof compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Math Proof this skillflonat/flonat-research1451 repos~2.6kAutomated safety check: PassMIT
Rigorous Math Prooftradecatlabs/vibe-coding-cn17k—~571Automated safety check: PassMIT
Math Proof Soloanthropics/claude-plugins-official38k—~1.5kAutomated safety check: PassApache-2.0
Mathparcadei/Continuous-Claude-v33.9k3 repos~1.6kAutomated safety check: NotesMIT
Cnki Paper Detailcookjohn/cnki-skills9812 repos~1.6kAutomated safety check: PassNone
Math Computationtradecatlabs/vibe-coding-cn17k—~881Automated safety check: PassMIT

Similar skills

  • Rigorous Math Proof

    tradecatlabs/vibe-coding-cn

    Writes and audits natural-language math proofs as checkable packages, with explicit assumptions, proof obligations and counterexample hunting, refuting or repairing weak claims.

    17k GitHub stars~571 tokensUpdated today
    Research & ScienceAuto-check passed
  • Math Proof Solo

    anthropics/claude-plugins-official

    Official

    Solves one hard mathematics problem in a single session without subagents, keeping settled steps in a notes file and ending with a self-contained proof.md.

    38k GitHub stars~1.5k tokensUpdated today
    Research & ScienceAuto-check passed
  • Math

    parcadei/Continuous-Claude-v3

    Unified math capabilities - computation, solving, and explanation.

    3.9k GitHub starsUsed in 3 repos~1.6k tokens
    Research & ScienceAuto-check: notes
  • Cnki Paper Detail

    cookjohn/cnki-skills

    Extract full paper details from a CNKI paper page including title, authors, affiliations, abstract, keywords, fund, classification.

    981 GitHub starsUsed in 2 repos~1.6k tokens
    Research & ScienceAuto-check passed
  • Math Computation

    tradecatlabs/vibe-coding-cn

    Runs reproducible math computations and counterexample searches with SymPy, NumPy and mpmath, logging evidence without presenting results as proofs.

    17k GitHub stars~881 tokensUpdated today
    Research & ScienceAuto-check passed
  • Math Formalization

    tradecatlabs/vibe-coding-cn

    Turns a mathematical claim into a small Lean 4 and Mathlib formalization checked by the proof assistant kernel, and refuses to report a pass without real evidence.

    17k GitHub stars~717 tokensUpdated today
    Research & ScienceAuto-check passed

More from flonat/flonat-research

All 83 skills in this repo
  • Latex Posters

    flonat/flonat-research

    Create a large-format academic poster in LaTeX using beamerposter, tikzposter, or baposter.

    145 GitHub stars~1.5k tokensUpdated 9 days ago
    Auto-check: notes
  • Skill Creator

    flonat/flonat-research

    Create, revise, and evaluate reusable AI workflow skills, including trigger-quality tests.

    145 GitHub stars~4.4k tokensUpdated 9 days ago
    Auto-check passed
  • DOCX

    flonat/flonat-research

    Create, read, edit, or convert Microsoft Word documents while preserving professional document structure.

    145 GitHub stars~1.2k tokensUpdated 9 days ago
    Auto-check passed
  • PDF

    flonat/flonat-research

    Read, create, combine, split, rotate, OCR, watermark, secure, or extract content from PDF files.

    145 GitHub stars~488 tokensUpdated 9 days ago
    Auto-check passed
  • Init Project Orchestration

    flonat/flonat-research

    Create or migrate project-level agents, repeatable project workflows, and planning state from one client-neutral contract, then render repository-scoped adapters for both Claude Code and Codex.

    145 GitHub stars~1.6k tokensUpdated 9 days ago
    Auto-check passed
  • Pre Commit Audit

    flonat/flonat-research

    Deliver a fast pre-commit safety scan: file size, anonymity (author / affiliation strings in tex/bib), hardcoded secrets, and invisible-Unicode carriers.

    145 GitHub stars~2.8k tokensUpdated 9 days ago
    Auto-check: notes

Questions about Math Proof

What does Math Proof do?

Write clear, detailed mathematical proofs for academic papers. Math Proof is an agent skill from flonat/flonat-research. Write clear, detailed mathematical proofs for academic papers.

When should I use Math Proof?

Math Proof fits situations like: the user asks to prove a result; derive an equation; justify a claim analytically; expand a proof sketch into a full proof.

How do I install Math Proof in Claude Code?

Run `npx skills add flonat/flonat-research --skill math-proof -a claude-code`. Or copy the skill folder (skills/math-proof in flonat/flonat-research) into .claude/skills/math-proof in your project. Claude Code loads it when a task matches its description.

How do I install Math Proof in Codex?

Run `npx skills add flonat/flonat-research --skill math-proof -a codex`. Or copy the skill folder (skills/math-proof in flonat/flonat-research) into .agents/skills/math-proof in your project. Codex loads it when a task matches its description.

Can I use Math Proof 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 flonat/flonat-research --skill math-proof -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/math-proof, .gemini/skills/math-proof, .github/skills/math-proof and .opencode/skills/math-proof in your project.

What does Math Proof need to run?

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

Does Math Proof access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Math Proof 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 Math Proof use?

Math Proof is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Math Proof use?

About 2.6k tokens (SKILL.md is roughly 10k 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 Math Proof?

Skills that share tags, products or a category with Math Proof: Rigorous Math Proof (tradecatlabs/vibe-coding-cn, 17k stars), Math Proof Solo (anthropics/claude-plugins-official, 38k stars), Math (parcadei/Continuous-Claude-v3, 3.9k stars) and Cnki Paper Detail (cookjohn/cnki-skills, 981 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Math Proof?

flonat (a GitHub user) maintains it in flonat/flonat-research, which has 145 GitHub stars. The repository holds 83 skills in this directory. The repository was last updated on September 29, 2026.

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