What makes Math Worksheets notable?

988 downloads. Trust evidence available

How should Math Worksheets be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Math Worksheets

Generate professional math practice worksheets and full answer keys as PDFs. Compiles LaTeX to PDF using tectonic (free, no account needed). Supports any mat... Skill: Math Worksheets Owner: trondw Summary: Generate professional math practice worksheets and full answer keys as PDFs. Compiles LaTeX to PDF using tectonic (free, no account needed). Supports any mat... Tags: latest:2.0.0 Version history: v2.0.0 | 2026-02-24T06:48:04.382Z | auto **Major update: worksheet verification now uses structured data files (JSON), improving reliability and security.** - Replaced code-base

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

988

Updated

Oct 11, 2026

Version

2.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 988 downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 988 downloadsadoption · observed Oct 11, 2026
Latest release: 2.0.0release · observed Feb 24, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 2.0.0release
**Major update: worksheet verification now uses structured data files (JSON), improving reliability and security.** - Replaced code-based verification ("verify.py" with explicit Python check calls) with a JSON-based format, interpreted by the bundled script. - Updated documentation to require a JSON verification file describing each problem and its expected answer. - `scripts/verify.py` now parses the JSON verification file and evaluates answers using SymPy—no generated code is executed. - Removed legacy script `scripts/fetch_model_config.sh` as part of verification process cleanup. - README and guides updated to reflect the new workflow for problem verification.
Observed Feb 24, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s175jxj1rjk3azjdda2kdgbaps884t6j:math-worksheets

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-trondw-math-worksheets/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

61,909 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: math-worksheets
description: Generate professional math practice worksheets and full answer keys as PDFs. Compiles LaTeX to PDF using tectonic (free, no account needed). Supports any math topic from elementary through high school (Pre-Algebra, Algebra 1/2, Geometry, Pre-Calc). Handles coordinate plane grids, geometric figures, tables, and multi-part problems. Use when a user asks for a math worksheet, practice problems, homework help sheet, or answer key for any K-12 math topic.
---

# Math Worksheet Generator

Generate a student worksheet PDF + full step-by-step answer key PDF for any K-12 math topic. Compiles LaTeX with `tectonic` (no TeX installation required — it auto-downloads packages).

## Model Selection (Automatic)

This skill auto-detects the best available reasoning model and uses it for problem generation. Reasoning models (o1, o3, DeepSeek R1, Gemini DeepThink) work through math step-by-step and make significantly fewer errors than standard models.

Model rankings are kept fresh via a three-layer fallback:
1. **Hosted JSON** (fetched from GitHub, 7-day cache) — updated by maintainers as models ship
2. **Bundled JSON** (`references/model-rankings.json`) — updated with each skill release on ClawhHub
3. **Hardcoded defaults** in the script — last-resort, never stale enough to cause failures

To update rankings without waiting for a skill release: edit the hosted JSON at the GitHub URL in `references/model-rankings.md`. The skill picks it up within 7 days.

**Step 0 — run model detection before anything else:**

```bash
SKILL_DIR="$(dirname "$0")"
result=$(bash "$SKILL_DIR/scripts/check_reasoning_model.sh")
status=$(echo "$result" | awk '{print $1}')   # FOUND, FALLBACK, or NONE
model_alias=$(echo "$result" | awk '{print $2}')
model_full=$(echo "$result" | awk '{print $3}')
```

Then branch on the status:

**`FOUND_REASONING`** (o3, o1, DeepThink, DeepSeek R1) — best case, use for problem generation:
```
sessions_spawn(task="<problem generation prompt>", model=model_alias)
```
No warning needed. Sub-agent writes the .tex files + verify script, announces completion.

**`FOUND_STRONG`** (Claude Opus) — excellent quality, use it without alarming the user:
```
sessions_spawn(task="<generation prompt>", model=model_alias)
```
Optionally add a quiet note: *"Using Opus — solid math accuracy and excellent LaTeX. For the hardest Algebra 2 problems, a reasoning model (DeepThink/o1) would be marginally better."*

**`NONE`** — standard model only; proceed but surface a clear recommendation:
```
⚠️ No reasoning model or Opus detected. Worksheet generated with [current model].
For best accuracy, especially on multi-step problems, configure one of:
  • Gemini 2.5 Pro DeepThink  — google.generativeai.com (free tier available)
  • o1 / o3                   — platform.openai.com
  • DeepSeek R1               — platform.deepseek.com (very affordable)
  • Claude Opus               — console.anthropic.com
SymPy verification will catch most errors r

README.md

# math-worksheets — OpenClaw Skill

**v2.0.0** · [Changelog](#changelog)

Generate professional math practice worksheets, answer keys, and study guides for K-12 students. Three PDFs every time: worksheet → answer key → skills summary cheat sheet.

## Features

- **Three documents per request** — worksheet, step-by-step answer key, skills summary with formula boxes and mini examples
- **LaTeX quality** — coordinate planes, geometric figures, tables, multi-part problems via tectonic (no TeX installation required)
- **SymPy verification** — answers are verified with a computer algebra system before compiling; incorrect answers are caught before reaching students
- **Auto reasoning-model detection** — automatically uses the best available model (DeepThink, o1/o3, DeepSeek R1, Claude Opus) for math generation; shows setup guidance if none configured. All detection is local — no network calls.
- **Channel mirroring** — sends back via the same channel the request came from (Telegram, iMessage, email)
- **K-12 coverage** — Pre-Algebra through Pre-Calculus (see `references/problem-library.md` for full topic menu)

## Install

```bash
openclaw skills install math-worksheets
```

Or download `math-worksheets.skill` from [ClawhHub](https://clawhub.com) and install locally.

**Prerequisites:**
```bash
brew install tectonic   # LaTeX compiler — auto-downloads packages on first use
```

**Python 3** is also required (standard on macOS). The skill uses it for model detection and answer verification.

**sympy** is required for answer verification:
```bash
pip3 install sympy
```

## Usage

Just ask naturally:

> *"Make Lucy a 20-problem worksheet on exponents and roots"*
> *"Leo needs practice on graphing polynomials — use his homework photo as a guide"*
> *"Factoring trinomials worksheet for an 8th grader, 15 problems"*

The skill handles everything: model selection, problem generation, SymPy verification, compile, and delivery.

## Skill Contents

```
math-worksheets/
├── SKILL.md                          ← workflow and instructions
├── scripts/
│   ├── check_reasoning_model.sh     ← auto-detects best available model (local only)
│   ├── compile.sh                   ← tectonic PDF compiler wrapper
│   ├── run_verify.sh                ← gates compilation on SymPy pass
│   └── verify.py                   ← SymPy verification template
└── references/
    ├── latex-templates.md           ← LaTeX patterns (coordinate planes, figures, answer key)
    ├── problem-library.md           ← K-12 problem type menu by course
    ├── model-rankings.md            ← human-readable model guidance
    └── model-rankings.json          ← bundled model ranking reference
```

## Changelog

### v2.0.0 — 2026-02-23
- **Security:** Eliminated RCE surface — verification no longer generates or executes AI-written Python code. The AI now writes a structured JSON data file (`verify_TOPIC_DATE.json`); the fixed, auditable `scripts/verify.py` evaluates it using SymPy. No user input is ever exe

_meta.json

{
  "ownerId": "kn7eytttvr7rqp77955nfqkmg180svwc",
  "slug": "math-worksheets",
  "version": "2.0.0",
  "publishedAt": 1771915684382
}

references/latex-templates.md

# LaTeX Templates Reference

## Document Shell

```latex
\documentclass[12pt]{article}
\usepackage[margin=1in, top=0.75in, bottom=0.75in]{geometry}
\usepackage{amsmath, amssymb, tikz, pgfplots, enumitem, fancyhdr, multicol, array, booktabs}
\pgfplotsset{compat=1.18}

\pagestyle{fancy}
\fancyhf{}
\fancyhead[L]{\textbf{TOPIC Practice}}
\fancyhead[R]{\small Name: \underline{\hspace{4.5cm}}~Date: \underline{\hspace{1.8cm}}}
\fancyfoot[C]{\thepage}
\renewcommand{\headrulewidth}{0.4pt}

\newcounter{prob}
\newcommand{\problem}[1]{\stepcounter{prob}\vspace{0.4cm}\noindent\textbf{\large\theprob.}\quad #1\vspace{0.3cm}}

\begin{document}
\begin{center}
  {\LARGE\textbf{TOPIC Practice Worksheet}}\\[0.3cm]
  {\large COURSE \quad $\bullet$ \quad DATE}
\end{center}
\noindent\rule{\linewidth}{0.4pt}\vspace{0.2cm}

% [problems here]

\end{document}
```

## Problem Patterns

### Simple algebraic problem
```latex
\problem{Solve for $x$: \quad $2x^2 - 5x - 3 = 0$}
\vspace{6cm}
```

### Two-column layout (shorter problems)
```latex
\begin{multicols}{2}
\begin{enumerate}[label=\textbf{\arabic*.}, itemsep=4cm]
  \item $3x + 7 = 22$
  \item $-2(x - 5) = 14$
  \item $\dfrac{x}{4} + 3 = 9$
  \item $5x - 3 = 2x + 9$
\end{enumerate}
\end{multicols}
```

### Multi-part problem
```latex
\problem{Given $f(x) = 3x^2 - 2x + 1$, find:}
\begin{enumerate}[label=(\alph*), itemsep=3cm, leftmargin=1.5cm]
  \item $f(0)$
  \item $f(-2)$
  \item $f(x+1)$ — expand and simplify
  \vspace{2cm}
\end{enumerate}
```

### Function table
```latex
\problem{Complete the table for $y = 3x - 2$.}
\vspace{0.3cm}
\begin{center}
\begin{tabular}{|>{\centering\arraybackslash}m{1.5cm}|>{\centering\arraybackslash}m{1.5cm}|}
\hline
\textbf{$x$} & \textbf{$y$} \\
\hline
$-2$ & \rule{1.2cm}{0pt} \\[0.5cm]\hline
$0$  & \\[0.5cm]\hline
$1$  & \\[0.5cm]\hline
$3$  & \\[0.5cm]\hline
\end{tabular}
\end{center}
\vspace{1cm}
```

## Coordinate Planes

### Blank grid (student fills in — algebraic range)
```latex
\begin{center}
\begin{tikzpicture}
\begin{axis}[
    axis lines=center, xmin=-6, xmax=6, ymin=-6, ymax=6,
    xtick={-6,-4,...,6}, ytick={-6,-4,...,6},
    grid=both,
    grid style={line width=0.15pt, draw=gray!30},
    major grid style={line width=0.3pt, draw=gray!50},
    tick label style={font=\small},
    xlabel={$x$}, ylabel={$y$},
    width=9cm, height=9cm, enlargelimits=false
]
\end{axis}
\end{tikzpicture}
\end{center}
```

### Blank grid (full −10 to 10, Pre-Algebra style)
```latex
\begin{axis}[
    axis lines=center, xmin=-10, xmax=10, ymin=-10, ymax=10,
    xtick={-10,-8,...,10}, ytick={-10,-8,...,10},
    minor tick num=1, grid=both,
    grid style={line width=0.12pt, draw=gray!20},
    major grid style={line width=0.3pt, draw=gray!50},
    tick label style={font=\scriptsize},
    xlabel={$x$}, ylabel={$y$}, width=9cm, height=9cm
]
\end{axis}
```

### Completed graph (answer key — plot a function)
```latex
\addplot[blue, thick, domain=-1:5, samples=100] {x^2 - 4*x + 3};
\addplot[only marks, mark=

references/model-rankings.json

{
  "last_updated": "2026-02-22",
  "source": "bundled — update via https://github.com/stellawuellner/math-worksheets-skill",
  "tiers": {
    "FOUND_REASONING": {
      "description": "Reasoning models — step-by-step internal chain-of-thought, highest math accuracy",
      "patterns": [
        { "alias": "o3",        "match": "openai/o3" },
        { "alias": "o1",        "match": "openai/o1" },
        { "alias": "deepthink", "match": "gemini-2.5-pro-deepthink" },
        { "alias": "deepthink", "match": "gemini-2.0-pro-deepthink" },
        { "alias": "deepseek",  "match": "deepseek-r1" }
      ]
    },
    "FOUND_STRONG": {
      "description": "Strong non-reasoning models — excellent math and LaTeX quality, use when no reasoning model available",
      "patterns": [
        { "alias": "opus", "match": "claude-opus-4" },
        { "alias": "opus", "match": "claude-opus-3-5" }
      ]
    }
  }
}

Github ReposUpdated 3d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular