メニュー
This skill should be used when the user asks to "evaluate Wolfram code", "run this Wolfram expression", or invokes /wolfram-hart:eval directly. It executes Wolfram Language code through the plugin's eval script.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
This skill should be used when the user asks to "check Wolfram setup", "verify wolframscript installation", or invokes /wolfram-hart:check directly. It checks local and cloud Wolfram Engine configuration status.
This skill should be used when the user asks to "show computation patterns", "browse Wolfram patterns", or invokes /wolfram-hart:patterns directly. It displays indexed, copy-paste-ready Wolfram computation templates.
This skill should be used when the user asks to "configure Wolfram settings", "change Wolfram mode", or invokes /wolfram-hart:setup directly. It manages per-project wolfram-hart settings.
This skill should be used when the user makes a math or science computation request — even when the answer seems easy to recall. Trigger phrases include: "what is the integral of x²", "solve x³ - 6x² + 11x = 6", "factor this polynomial", "find the eigenvalues of this matrix", "plot sin(x) from 0 to 2π", "convert 60 mph to km/h", "what's the Fourier transform of e^(-x²)", "minimize f(x,y) subject to a constraint". Also invoke for matrix operations of any size, exact symbolic integrals, ODE solving, data regression, modular arithmetic, and any mention of Wolfram, Mathematica, or Wolfram Language. Recalled math can silently contain errors; the Wolfram Engine verifies (e.g., a 4×4 matrix where recalled det=6 but the true det=12). Exception: truly trivial one-step problems (e.g., "what is 2+2") do not warrant the overhead.
| name | eval |
| description | This skill should be used when the user asks to "evaluate Wolfram code", "run this Wolfram expression", or invokes /wolfram-hart:eval directly. It executes Wolfram Language code through the plugin's eval script. |
| version | 1.1.0 |
| argument-hint | <wolfram-code> [timeout] |
| allowed-tools | Bash(bash:*), Read |
| disable-model-invocation | true |
Execute the following Wolfram Language code through the plugin's eval script:
$ARGUMENTS
Execution steps:
If $ARGUMENTS is empty or contains only whitespace, do not invoke the script.
Tell the user: "No Wolfram code provided. Usage:
/wolfram-hart:eval <wolfram-code> [timeout]" and show a brief example like
/wolfram-hart:eval Solve[x^2 == 4, x].
Parse the input. If the last whitespace-separated token is a bare integer >= 10
(e.g. 60, 120), treat it as a timeout override in seconds; everything before
it is the Wolfram code. Otherwise, the entire input is the code and the default
30-second timeout applies. This threshold avoids misinterpreting small numbers
that are part of the Wolfram expression itself.
If no explicit timeout is provided, the script uses the WOLFRAM_TIMEOUT
environment variable (settable via /wolfram-hart:setup), falling back to
30 seconds.
Run the code through the wrapper script:
bash ${CLAUDE_PLUGIN_ROOT}/skills/wolfram-hart/scripts/wolfram-eval.sh '<code>' [timeout]
Use single quotes around the code. If the code contains derivative apostrophes
(y'[x]), switch to double quotes and escape inner double quotes with \" and
dollar signs with \$ (e.g. \$VersionNumber).
Interpret the result:
Null (e.g.
because it ends with a semicolon). Suggest removing the trailing semicolon.Export), use the Read tool to display the image.---WARNINGS---, separate the result from warnings and
present both.bash ${CLAUDE_PLUGIN_ROOT}/skills/wolfram-hart/scripts/wolfram-check.sh
and relay install instructions./wolfram-hart:check to verify the installation.Present the result directly. Do not add extra commentary unless there is an error or warning to explain.